|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.045413260672116255, |
|
"eval_steps": 9, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0018165304268846503, |
|
"grad_norm": 0.3600485622882843, |
|
"learning_rate": 1e-05, |
|
"loss": 0.4664, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0018165304268846503, |
|
"eval_loss": 0.4619494378566742, |
|
"eval_runtime": 108.3327, |
|
"eval_samples_per_second": 4.283, |
|
"eval_steps_per_second": 0.535, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0036330608537693005, |
|
"grad_norm": 0.33697664737701416, |
|
"learning_rate": 2e-05, |
|
"loss": 0.4766, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.005449591280653951, |
|
"grad_norm": 0.3403802812099457, |
|
"learning_rate": 3e-05, |
|
"loss": 0.4548, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.007266121707538601, |
|
"grad_norm": 0.3392443060874939, |
|
"learning_rate": 4e-05, |
|
"loss": 0.4661, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.009082652134423252, |
|
"grad_norm": 0.39870426058769226, |
|
"learning_rate": 5e-05, |
|
"loss": 0.4286, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.010899182561307902, |
|
"grad_norm": 0.3802020847797394, |
|
"learning_rate": 6e-05, |
|
"loss": 0.4409, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.012715712988192553, |
|
"grad_norm": 0.3801540732383728, |
|
"learning_rate": 7e-05, |
|
"loss": 0.4209, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.014532243415077202, |
|
"grad_norm": 0.38932061195373535, |
|
"learning_rate": 8e-05, |
|
"loss": 0.4188, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.01634877384196185, |
|
"grad_norm": 0.3350403308868408, |
|
"learning_rate": 9e-05, |
|
"loss": 0.396, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.01634877384196185, |
|
"eval_loss": 0.3949369788169861, |
|
"eval_runtime": 108.084, |
|
"eval_samples_per_second": 4.293, |
|
"eval_steps_per_second": 0.537, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.018165304268846504, |
|
"grad_norm": 0.33399584889411926, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3662, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.019981834695731154, |
|
"grad_norm": 0.3276408314704895, |
|
"learning_rate": 9.99695413509548e-05, |
|
"loss": 0.3859, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.021798365122615803, |
|
"grad_norm": 0.3103690445423126, |
|
"learning_rate": 9.987820251299122e-05, |
|
"loss": 0.3512, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.023614895549500452, |
|
"grad_norm": 0.45643332600593567, |
|
"learning_rate": 9.972609476841367e-05, |
|
"loss": 0.3913, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.025431425976385105, |
|
"grad_norm": 0.38945508003234863, |
|
"learning_rate": 9.951340343707852e-05, |
|
"loss": 0.3104, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.027247956403269755, |
|
"grad_norm": 0.33456993103027344, |
|
"learning_rate": 9.924038765061042e-05, |
|
"loss": 0.3705, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.029064486830154404, |
|
"grad_norm": 0.4321489632129669, |
|
"learning_rate": 9.890738003669029e-05, |
|
"loss": 0.3217, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.030881017257039057, |
|
"grad_norm": 0.3709757924079895, |
|
"learning_rate": 9.851478631379982e-05, |
|
"loss": 0.3113, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.0326975476839237, |
|
"grad_norm": 0.33215710520744324, |
|
"learning_rate": 9.806308479691595e-05, |
|
"loss": 0.3293, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.0326975476839237, |
|
"eval_loss": 0.32641759514808655, |
|
"eval_runtime": 108.5742, |
|
"eval_samples_per_second": 4.274, |
|
"eval_steps_per_second": 0.534, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.03451407811080836, |
|
"grad_norm": 0.40216928720474243, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 0.385, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.03633060853769301, |
|
"grad_norm": 0.3322986662387848, |
|
"learning_rate": 9.698463103929542e-05, |
|
"loss": 0.2936, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.03814713896457766, |
|
"grad_norm": 0.339769572019577, |
|
"learning_rate": 9.635919272833938e-05, |
|
"loss": 0.329, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.03996366939146231, |
|
"grad_norm": 0.34345075488090515, |
|
"learning_rate": 9.567727288213005e-05, |
|
"loss": 0.2768, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.04178019981834696, |
|
"grad_norm": 0.3251555860042572, |
|
"learning_rate": 9.493970231495835e-05, |
|
"loss": 0.2831, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.043596730245231606, |
|
"grad_norm": 0.35843387246131897, |
|
"learning_rate": 9.414737964294636e-05, |
|
"loss": 0.402, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.045413260672116255, |
|
"grad_norm": 0.31343409419059753, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.2751, |
|
"step": 25 |
|
} |
|
], |
|
"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": 3.672344046757478e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|