| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.051440329218107, | |
| "eval_steps": 9, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00102880658436214, | |
| "grad_norm": 0.025219934061169624, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3752, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00102880658436214, | |
| "eval_loss": 10.375638961791992, | |
| "eval_runtime": 3.4609, | |
| "eval_samples_per_second": 236.643, | |
| "eval_steps_per_second": 29.761, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00205761316872428, | |
| "grad_norm": 0.02738805301487446, | |
| "learning_rate": 2e-05, | |
| "loss": 10.377, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030864197530864196, | |
| "grad_norm": 0.026469284668564796, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3742, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00411522633744856, | |
| "grad_norm": 0.02698007971048355, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3783, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0051440329218107, | |
| "grad_norm": 0.02839619107544422, | |
| "learning_rate": 5e-05, | |
| "loss": 10.374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006172839506172839, | |
| "grad_norm": 0.029380450025200844, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3777, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00720164609053498, | |
| "grad_norm": 0.024871516972780228, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3754, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "grad_norm": 0.028594117611646652, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3687, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009259259259259259, | |
| "grad_norm": 0.02646900713443756, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3764, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009259259259259259, | |
| "eval_loss": 10.375298500061035, | |
| "eval_runtime": 4.7508, | |
| "eval_samples_per_second": 172.393, | |
| "eval_steps_per_second": 21.681, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0102880658436214, | |
| "grad_norm": 0.030630815774202347, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3748, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01131687242798354, | |
| "grad_norm": 0.02231612056493759, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3753, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012345679012345678, | |
| "grad_norm": 0.03500870242714882, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3749, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013374485596707819, | |
| "grad_norm": 0.03169140964746475, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3728, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01440329218106996, | |
| "grad_norm": 0.033007316291332245, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3752, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015432098765432098, | |
| "grad_norm": 0.027678297832608223, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3716, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01646090534979424, | |
| "grad_norm": 0.028717216104269028, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3719, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01748971193415638, | |
| "grad_norm": 0.024401096627116203, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3713, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "grad_norm": 0.03191472589969635, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.379, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "eval_loss": 10.374419212341309, | |
| "eval_runtime": 4.6532, | |
| "eval_samples_per_second": 176.007, | |
| "eval_steps_per_second": 22.135, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01954732510288066, | |
| "grad_norm": 0.026906833052635193, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3749, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0205761316872428, | |
| "grad_norm": 0.024135004729032516, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3714, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021604938271604937, | |
| "grad_norm": 0.030134005472064018, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3771, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02263374485596708, | |
| "grad_norm": 0.02962920069694519, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3719, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.023662551440329218, | |
| "grad_norm": 0.02854999154806137, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.373, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.024691358024691357, | |
| "grad_norm": 0.026968492195010185, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3742, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0257201646090535, | |
| "grad_norm": 0.03159381076693535, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.374, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026748971193415638, | |
| "grad_norm": 0.028679387643933296, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 10.3742, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.027777777777777776, | |
| "grad_norm": 0.027246227487921715, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 10.373, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.027777777777777776, | |
| "eval_loss": 10.373526573181152, | |
| "eval_runtime": 4.4408, | |
| "eval_samples_per_second": 184.426, | |
| "eval_steps_per_second": 23.194, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02880658436213992, | |
| "grad_norm": 0.02638566493988037, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3752, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.029835390946502057, | |
| "grad_norm": 0.029429133981466293, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 10.3752, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.030864197530864196, | |
| "grad_norm": 0.028540797531604767, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3752, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03189300411522634, | |
| "grad_norm": 0.026979394257068634, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 10.3744, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03292181069958848, | |
| "grad_norm": 0.03402787446975708, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 10.3702, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.033950617283950615, | |
| "grad_norm": 0.03517807647585869, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 10.3777, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03497942386831276, | |
| "grad_norm": 0.028791263699531555, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 10.37, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0360082304526749, | |
| "grad_norm": 0.027155417948961258, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.374, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": 0.033103760331869125, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 10.3683, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "eval_loss": 10.372629165649414, | |
| "eval_runtime": 4.6687, | |
| "eval_samples_per_second": 175.422, | |
| "eval_steps_per_second": 22.062, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03806584362139918, | |
| "grad_norm": 0.03502420708537102, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 10.371, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03909465020576132, | |
| "grad_norm": 0.03081183321774006, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 10.3732, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.040123456790123455, | |
| "grad_norm": 0.02784951776266098, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 10.3758, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0411522633744856, | |
| "grad_norm": 0.03854544833302498, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3658, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04218106995884774, | |
| "grad_norm": 0.027156542986631393, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 10.3731, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.043209876543209874, | |
| "grad_norm": 0.03118831478059292, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 10.3659, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.044238683127572016, | |
| "grad_norm": 0.03406394273042679, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 10.3682, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04526748971193416, | |
| "grad_norm": 0.03691929578781128, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 10.3734, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.046296296296296294, | |
| "grad_norm": 0.03526577353477478, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3724, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.046296296296296294, | |
| "eval_loss": 10.37172794342041, | |
| "eval_runtime": 4.6525, | |
| "eval_samples_per_second": 176.035, | |
| "eval_steps_per_second": 22.139, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.047325102880658436, | |
| "grad_norm": 0.038986314088106155, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3734, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04835390946502058, | |
| "grad_norm": 0.033386219292879105, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 10.3747, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04938271604938271, | |
| "grad_norm": 0.03682396188378334, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 10.3702, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.050411522633744855, | |
| "grad_norm": 0.035510748624801636, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 10.3708, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.051440329218107, | |
| "grad_norm": 0.02855323627591133, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3743, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2615122329600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |