| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 1.1256082074272271, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.4398, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 1.088771511094631, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.4412, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 1.8376444921378117, | |
| "learning_rate": 2e-05, | |
| "loss": 0.47, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.529094126656205, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.2967, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 0.6045407978315229, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2834, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 1.0370791330907858, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2388, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 0.9943285807402519, | |
| "learning_rate": 3.995717846477207e-05, | |
| "loss": 0.2102, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.734159963431325, | |
| "learning_rate": 3.982889722747621e-05, | |
| "loss": 0.1507, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.6269810975525937, | |
| "learning_rate": 3.961570560806461e-05, | |
| "loss": 0.1478, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.5651528327820644, | |
| "learning_rate": 3.931851652578137e-05, | |
| "loss": 0.0943, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6111111111111112, | |
| "grad_norm": 0.4737837967269508, | |
| "learning_rate": 3.893860258990212e-05, | |
| "loss": 0.1186, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.22977095830410557, | |
| "learning_rate": 3.8477590650225735e-05, | |
| "loss": 0.1061, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7222222222222222, | |
| "grad_norm": 0.4134357432752201, | |
| "learning_rate": 3.793745483065377e-05, | |
| "loss": 0.0879, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.3218674795732037, | |
| "learning_rate": 3.732050807568878e-05, | |
| "loss": 0.0936, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.1669034849615332, | |
| "learning_rate": 3.662939224605091e-05, | |
| "loss": 0.09, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.16802071996279108, | |
| "learning_rate": 3.586706680582471e-05, | |
| "loss": 0.0758, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9444444444444444, | |
| "grad_norm": 0.1369439456224394, | |
| "learning_rate": 3.503679614957955e-05, | |
| "loss": 0.08, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.20649754108360613, | |
| "learning_rate": 3.4142135623730954e-05, | |
| "loss": 0.0895, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0555555555555556, | |
| "grad_norm": 0.09880137297267558, | |
| "learning_rate": 3.318691630200138e-05, | |
| "loss": 0.0564, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.1260825954366184, | |
| "learning_rate": 3.217522858017442e-05, | |
| "loss": 0.0557, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1666666666666667, | |
| "grad_norm": 0.0911954618176465, | |
| "learning_rate": 3.111140466039205e-05, | |
| "loss": 0.0538, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 0.10435877731045032, | |
| "learning_rate": 3.0000000000000004e-05, | |
| "loss": 0.0552, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2777777777777777, | |
| "grad_norm": 0.09814153580724687, | |
| "learning_rate": 2.8845773804380028e-05, | |
| "loss": 0.0536, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.45047741750772974, | |
| "learning_rate": 2.7653668647301797e-05, | |
| "loss": 0.0511, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3888888888888888, | |
| "grad_norm": 0.30626691874091017, | |
| "learning_rate": 2.6428789306063233e-05, | |
| "loss": 0.0462, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4444444444444444, | |
| "grad_norm": 0.6599213438303501, | |
| "learning_rate": 2.5176380902050418e-05, | |
| "loss": 0.0513, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.2529588579336132, | |
| "learning_rate": 2.390180644032257e-05, | |
| "loss": 0.0513, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 2.00761533609209, | |
| "learning_rate": 2.261052384440104e-05, | |
| "loss": 0.0564, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6111111111111112, | |
| "grad_norm": 0.34872709425136345, | |
| "learning_rate": 2.1308062584602865e-05, | |
| "loss": 0.0561, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.4904440153660744, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0492, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7222222222222223, | |
| "grad_norm": 0.12493803487246685, | |
| "learning_rate": 1.869193741539714e-05, | |
| "loss": 0.0425, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.27834780304111784, | |
| "learning_rate": 1.7389476155598974e-05, | |
| "loss": 0.0504, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8333333333333335, | |
| "grad_norm": 0.12529358778962452, | |
| "learning_rate": 1.609819355967744e-05, | |
| "loss": 0.0416, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 0.17096633068642128, | |
| "learning_rate": 1.4823619097949584e-05, | |
| "loss": 0.0427, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.9444444444444444, | |
| "grad_norm": 0.2813740448600146, | |
| "learning_rate": 1.3571210693936774e-05, | |
| "loss": 0.044, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.10020685560024836, | |
| "learning_rate": 1.2346331352698206e-05, | |
| "loss": 0.0399, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 54, | |
| "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": 126748779872256.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |