| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9935205183585314, | |
| "eval_steps": 500, | |
| "global_step": 230, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08639308855291576, | |
| "grad_norm": 408.058349609375, | |
| "learning_rate": 1.2e-05, | |
| "loss": 9.3465, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17278617710583152, | |
| "grad_norm": 1.8677339553833008, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.8486, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2591792656587473, | |
| "grad_norm": 0.6196443438529968, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.4004, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34557235421166305, | |
| "grad_norm": 0.8679957985877991, | |
| "learning_rate": 0.000132, | |
| "loss": 0.3089, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4319654427645788, | |
| "grad_norm": 0.4516398310661316, | |
| "learning_rate": 0.000172, | |
| "loss": 0.2921, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5183585313174947, | |
| "grad_norm": 1.6636766195297241, | |
| "learning_rate": 0.00019994896932810338, | |
| "loss": 0.4872, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6047516198704104, | |
| "grad_norm": 0.6236905455589294, | |
| "learning_rate": 0.0001990432055368971, | |
| "loss": 0.3284, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6911447084233261, | |
| "grad_norm": 0.8019087314605713, | |
| "learning_rate": 0.00019701524265130086, | |
| "loss": 0.4159, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7775377969762419, | |
| "grad_norm": 0.460245817899704, | |
| "learning_rate": 0.0001938880583011413, | |
| "loss": 0.2771, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8639308855291576, | |
| "grad_norm": 0.2711161673069, | |
| "learning_rate": 0.00018969708473466529, | |
| "loss": 0.2995, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9503239740820735, | |
| "grad_norm": 0.5418670773506165, | |
| "learning_rate": 0.000184489807357009, | |
| "loss": 0.2693, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.043196544276458, | |
| "grad_norm": 1.3273216485977173, | |
| "learning_rate": 0.00017832522670158368, | |
| "loss": 0.2968, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1295896328293737, | |
| "grad_norm": 0.30387449264526367, | |
| "learning_rate": 0.00017127318993045686, | |
| "loss": 0.2649, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2159827213822894, | |
| "grad_norm": 0.872471272945404, | |
| "learning_rate": 0.00016341359943809628, | |
| "loss": 0.2696, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3023758099352052, | |
| "grad_norm": 0.4214591383934021, | |
| "learning_rate": 0.00015483550752531334, | |
| "loss": 0.27, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.388768898488121, | |
| "grad_norm": 0.3436877131462097, | |
| "learning_rate": 0.00014563610740111162, | |
| "loss": 0.2544, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.4751619870410368, | |
| "grad_norm": 0.6171785593032837, | |
| "learning_rate": 0.00013591963194479198, | |
| "loss": 0.2665, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.5615550755939525, | |
| "grad_norm": 0.4470198452472687, | |
| "learning_rate": 0.0001257961727057812, | |
| "loss": 0.2732, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.6479481641468683, | |
| "grad_norm": 0.5304989814758301, | |
| "learning_rate": 0.00011538043252238628, | |
| "loss": 0.2622, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.734341252699784, | |
| "grad_norm": 0.35694748163223267, | |
| "learning_rate": 0.0001047904258928037, | |
| "loss": 0.2568, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8207343412526997, | |
| "grad_norm": 0.22506724298000336, | |
| "learning_rate": 9.414614182369862e-05, | |
| "loss": 0.2505, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9071274298056156, | |
| "grad_norm": 0.36761364340782166, | |
| "learning_rate": 8.356818430681408e-05, | |
| "loss": 0.2773, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.9935205183585314, | |
| "grad_norm": 0.27311214804649353, | |
| "learning_rate": 7.317640582755372e-05, | |
| "loss": 0.2631, | |
| "step": 230 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 345, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 6.368992225866547e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |