| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9872340425531915, |
| "eval_steps": 50, |
| "global_step": 58, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 2e-05, |
| "loss": 1.6896, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 4e-05, |
| "loss": 1.632, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 6e-05, |
| "loss": 1.7197, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 8e-05, |
| "loss": 1.6988, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0001, |
| "loss": 1.4945, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00012, |
| "loss": 1.4763, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00014, |
| "loss": 1.4645, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00016, |
| "loss": 1.1569, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00018, |
| "loss": 1.4501, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.0002, |
| "loss": 1.1972, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00019998209226697376, |
| "loss": 1.1479, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00019992837548163316, |
| "loss": 1.1791, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00019983886888289514, |
| "loss": 1.1471, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00019971360452796522, |
| "loss": 0.9662, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0001995526272808559, |
| "loss": 1.2166, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.0001993559947963185, |
| "loss": 1.1023, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00019912377749919374, |
| "loss": 0.9719, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00019885605855918885, |
| "loss": 0.9122, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00019855293386108992, |
| "loss": 0.8808, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00019821451197042026, |
| "loss": 1.0081, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00019784091409455728, |
| "loss": 1.0147, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00019743227403932134, |
| "loss": 0.8792, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00019698873816105273, |
| "loss": 0.8762, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.00019651046531419332, |
| "loss": 0.7916, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.0001959976267943923, |
| "loss": 0.8967, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0001954504062771555, |
| "loss": 1.0575, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.00019486899975206166, |
| "loss": 0.9374, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00019425361545256727, |
| "loss": 0.8697, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00019360447378142728, |
| "loss": 0.788, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.00019292180723175654, |
| "loss": 0.8215, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00019220586030376134, |
| "loss": 0.8943, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.00019145688941717075, |
| "loss": 0.7825, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00019067516281939825, |
| "loss": 0.9878, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00018986096048946824, |
| "loss": 0.8517, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.00018901457403773967, |
| "loss": 0.8132, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.00018813630660146488, |
| "loss": 0.9143, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.0001872264727362194, |
| "loss": 0.8659, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.00018628539830324229, |
| "loss": 0.7977, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.00018531342035272766, |
| "loss": 0.8188, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.00018431088700310844, |
| "loss": 0.871, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.00018327815731637612, |
| "loss": 0.6939, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00018221560116948103, |
| "loss": 0.8147, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00018112359912185924, |
| "loss": 0.8898, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.00018000254227913348, |
| "loss": 0.8074, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0001788528321530366, |
| "loss": 0.8351, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.00017767488051760857, |
| "loss": 0.8811, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 0.00017646910926171747, |
| "loss": 0.792, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00017523595023795813, |
| "loss": 0.8558, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.0001739758451079821, |
| "loss": 0.8308, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.00017268924518431438, |
| "loss": 0.8504, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.85, |
| "eval_loss": 0.8740054368972778, |
| "eval_runtime": 0.8959, |
| "eval_samples_per_second": 22.324, |
| "eval_steps_per_second": 5.581, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.0001713766112687139, |
| "loss": 0.83, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.0001700384134871351, |
| "loss": 0.7499, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00016867513112135013, |
| "loss": 0.8685, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.0001672872524372919, |
| "loss": 0.807, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.00016587527451017938, |
| "loss": 0.8627, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.0001644397030464877, |
| "loss": 0.7606, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.00016298105220282713, |
| "loss": 0.8284, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00016149984440179537, |
| "loss": 0.8585, |
| "step": 58 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 174, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 2526774948986880.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
