| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 3564, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11231222799382283, | |
| "grad_norm": 0.39166563749313354, | |
| "learning_rate": 1.98e-05, | |
| "loss": 1.4955, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22462445598764566, | |
| "grad_norm": 0.4607338309288025, | |
| "learning_rate": 1.9717948717948722e-05, | |
| "loss": 1.2752, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3369366839814685, | |
| "grad_norm": 0.7553314566612244, | |
| "learning_rate": 1.9433048433048433e-05, | |
| "loss": 1.232, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4492489119752913, | |
| "grad_norm": 0.8646947145462036, | |
| "learning_rate": 1.9148148148148148e-05, | |
| "loss": 1.2408, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5615611399691142, | |
| "grad_norm": 0.7261890769004822, | |
| "learning_rate": 1.8863247863247863e-05, | |
| "loss": 1.2141, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.673873367962937, | |
| "grad_norm": 0.8889899253845215, | |
| "learning_rate": 1.857834757834758e-05, | |
| "loss": 1.1893, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7861855959567597, | |
| "grad_norm": 1.0335707664489746, | |
| "learning_rate": 1.8293447293447296e-05, | |
| "loss": 1.2119, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8984978239505826, | |
| "grad_norm": 1.185014009475708, | |
| "learning_rate": 1.800854700854701e-05, | |
| "loss": 1.1926, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.010108100519444, | |
| "grad_norm": 1.1347686052322388, | |
| "learning_rate": 1.7723646723646725e-05, | |
| "loss": 1.1979, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.1224203285132668, | |
| "grad_norm": 1.22648286819458, | |
| "learning_rate": 1.743874643874644e-05, | |
| "loss": 1.1476, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.2347325565070897, | |
| "grad_norm": 1.205437183380127, | |
| "learning_rate": 1.7153846153846155e-05, | |
| "loss": 1.1175, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.3470447845009126, | |
| "grad_norm": 1.667339563369751, | |
| "learning_rate": 1.686894586894587e-05, | |
| "loss": 1.1291, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.4593570124947353, | |
| "grad_norm": 1.311352252960205, | |
| "learning_rate": 1.6584045584045584e-05, | |
| "loss": 1.1495, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.5716692404885582, | |
| "grad_norm": 1.574444055557251, | |
| "learning_rate": 1.62991452991453e-05, | |
| "loss": 1.1195, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.683981468482381, | |
| "grad_norm": 1.5072523355484009, | |
| "learning_rate": 1.6014245014245017e-05, | |
| "loss": 1.1423, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.7962936964762037, | |
| "grad_norm": 1.8808943033218384, | |
| "learning_rate": 1.572934472934473e-05, | |
| "loss": 1.1365, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.9086059244700266, | |
| "grad_norm": 1.6016888618469238, | |
| "learning_rate": 1.5444444444444446e-05, | |
| "loss": 1.1399, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.020216201038888, | |
| "grad_norm": 1.48503839969635, | |
| "learning_rate": 1.5159544159544161e-05, | |
| "loss": 1.1265, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.132528429032711, | |
| "grad_norm": 1.6783254146575928, | |
| "learning_rate": 1.4874643874643874e-05, | |
| "loss": 1.0324, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.2448406570265336, | |
| "grad_norm": 1.9262216091156006, | |
| "learning_rate": 1.458974358974359e-05, | |
| "loss": 1.0686, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.3571528850203567, | |
| "grad_norm": 2.051445960998535, | |
| "learning_rate": 1.4304843304843305e-05, | |
| "loss": 1.0045, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.4694651130141794, | |
| "grad_norm": 2.8972795009613037, | |
| "learning_rate": 1.401994301994302e-05, | |
| "loss": 1.0181, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.581777341008002, | |
| "grad_norm": 1.876657247543335, | |
| "learning_rate": 1.3735042735042737e-05, | |
| "loss": 1.065, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.694089569001825, | |
| "grad_norm": 2.7444064617156982, | |
| "learning_rate": 1.3450142450142451e-05, | |
| "loss": 1.0346, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.806401796995648, | |
| "grad_norm": 2.054774761199951, | |
| "learning_rate": 1.3165242165242168e-05, | |
| "loss": 1.059, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.9187140249894705, | |
| "grad_norm": 2.7013003826141357, | |
| "learning_rate": 1.2880341880341882e-05, | |
| "loss": 1.0289, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.0303243015583323, | |
| "grad_norm": 2.9840266704559326, | |
| "learning_rate": 1.2595441595441595e-05, | |
| "loss": 1.0349, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.142636529552155, | |
| "grad_norm": 2.664555549621582, | |
| "learning_rate": 1.231054131054131e-05, | |
| "loss": 0.9633, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.2549487575459777, | |
| "grad_norm": 2.709664821624756, | |
| "learning_rate": 1.2025641025641027e-05, | |
| "loss": 0.9699, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3.367260985539801, | |
| "grad_norm": 3.7343850135803223, | |
| "learning_rate": 1.1740740740740741e-05, | |
| "loss": 0.9587, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.4795732135336235, | |
| "grad_norm": 2.5082879066467285, | |
| "learning_rate": 1.1455840455840456e-05, | |
| "loss": 0.9365, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 3.591885441527446, | |
| "grad_norm": 2.3327536582946777, | |
| "learning_rate": 1.1170940170940173e-05, | |
| "loss": 0.9446, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 3.7041976695212693, | |
| "grad_norm": 3.731090784072876, | |
| "learning_rate": 1.0886039886039887e-05, | |
| "loss": 0.9709, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.816509897515092, | |
| "grad_norm": 2.961172103881836, | |
| "learning_rate": 1.0601139601139602e-05, | |
| "loss": 0.9459, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.9288221255089146, | |
| "grad_norm": 4.010087013244629, | |
| "learning_rate": 1.0316239316239318e-05, | |
| "loss": 0.9509, | |
| "step": 3500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 7120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.5973626313699164e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |