|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.650142218610321, |
|
"eval_steps": 500, |
|
"global_step": 200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.016253555465258026, |
|
"grad_norm": 2.077186346054077, |
|
"learning_rate": 4.9998691031433496e-05, |
|
"loss": 2.8778, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.03250711093051605, |
|
"grad_norm": 2.073504686355591, |
|
"learning_rate": 4.999476426280588e-05, |
|
"loss": 2.6432, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.048760666395774074, |
|
"grad_norm": 2.1281931400299072, |
|
"learning_rate": 4.998822010531848e-05, |
|
"loss": 2.3167, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0650142218610321, |
|
"grad_norm": 1.090219497680664, |
|
"learning_rate": 4.997905924425903e-05, |
|
"loss": 2.1533, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.08126777732629012, |
|
"grad_norm": 1.007896900177002, |
|
"learning_rate": 4.996728263892985e-05, |
|
"loss": 2.0267, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.09752133279154815, |
|
"grad_norm": 0.9982665777206421, |
|
"learning_rate": 4.995289152254744e-05, |
|
"loss": 1.9352, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.11377488825680618, |
|
"grad_norm": 0.8844298720359802, |
|
"learning_rate": 4.9935887402113315e-05, |
|
"loss": 1.9486, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.1300284437220642, |
|
"grad_norm": 0.9337536692619324, |
|
"learning_rate": 4.991627205825621e-05, |
|
"loss": 1.9228, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.14628199918732224, |
|
"grad_norm": 0.9377800822257996, |
|
"learning_rate": 4.9894047545045605e-05, |
|
"loss": 1.835, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.16253555465258024, |
|
"grad_norm": 0.8525241017341614, |
|
"learning_rate": 4.986921618977664e-05, |
|
"loss": 1.8157, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.17878911011783827, |
|
"grad_norm": 0.872871458530426, |
|
"learning_rate": 4.984178059272638e-05, |
|
"loss": 1.8811, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.1950426655830963, |
|
"grad_norm": 0.9125804305076599, |
|
"learning_rate": 4.981174362688158e-05, |
|
"loss": 1.8242, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.21129622104835433, |
|
"grad_norm": 0.7474733591079712, |
|
"learning_rate": 4.977910843763777e-05, |
|
"loss": 1.7808, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.22754977651361236, |
|
"grad_norm": 1.0248199701309204, |
|
"learning_rate": 4.974387844246987e-05, |
|
"loss": 1.8512, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.24380333197887039, |
|
"grad_norm": 0.9032835960388184, |
|
"learning_rate": 4.970605733057441e-05, |
|
"loss": 1.8172, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.2600568874441284, |
|
"grad_norm": 0.8550340533256531, |
|
"learning_rate": 4.9665649062483115e-05, |
|
"loss": 1.7418, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.27631044290938644, |
|
"grad_norm": 0.9429016709327698, |
|
"learning_rate": 4.96226578696482e-05, |
|
"loss": 1.8265, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.2925639983746445, |
|
"grad_norm": 0.975885272026062, |
|
"learning_rate": 4.957708825399927e-05, |
|
"loss": 1.7943, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.3088175538399025, |
|
"grad_norm": 0.827629804611206, |
|
"learning_rate": 4.9528944987471884e-05, |
|
"loss": 1.8067, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.3250711093051605, |
|
"grad_norm": 1.0019093751907349, |
|
"learning_rate": 4.9478233111507856e-05, |
|
"loss": 1.7874, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.3413246647704185, |
|
"grad_norm": 1.0811312198638916, |
|
"learning_rate": 4.9424957936527295e-05, |
|
"loss": 1.7395, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.35757822023567654, |
|
"grad_norm": 0.9461565613746643, |
|
"learning_rate": 4.936912504137257e-05, |
|
"loss": 1.7833, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.37383177570093457, |
|
"grad_norm": 1.0386009216308594, |
|
"learning_rate": 4.9310740272724055e-05, |
|
"loss": 1.7569, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.3900853311661926, |
|
"grad_norm": 0.9916568994522095, |
|
"learning_rate": 4.924980974448791e-05, |
|
"loss": 1.7584, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.4063388866314506, |
|
"grad_norm": 1.240400791168213, |
|
"learning_rate": 4.918633983715581e-05, |
|
"loss": 1.7438, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.42259244209670865, |
|
"grad_norm": 1.1441287994384766, |
|
"learning_rate": 4.912033719713687e-05, |
|
"loss": 1.7046, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.4388459975619667, |
|
"grad_norm": 1.1687984466552734, |
|
"learning_rate": 4.905180873606157e-05, |
|
"loss": 1.738, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.4550995530272247, |
|
"grad_norm": 0.9126319885253906, |
|
"learning_rate": 4.8980761630058014e-05, |
|
"loss": 1.7738, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.47135310849248274, |
|
"grad_norm": 1.172781229019165, |
|
"learning_rate": 4.8907203319000495e-05, |
|
"loss": 1.6642, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.48760666395774077, |
|
"grad_norm": 1.1217776536941528, |
|
"learning_rate": 4.883114150573037e-05, |
|
"loss": 1.7359, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.5038602194229987, |
|
"grad_norm": 1.1024829149246216, |
|
"learning_rate": 4.8752584155249444e-05, |
|
"loss": 1.6707, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.5201137748882568, |
|
"grad_norm": 1.042017936706543, |
|
"learning_rate": 4.8671539493885934e-05, |
|
"loss": 1.709, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.5363673303535148, |
|
"grad_norm": 1.1834771633148193, |
|
"learning_rate": 4.8588016008432945e-05, |
|
"loss": 1.7282, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.5526208858187729, |
|
"grad_norm": 1.0311099290847778, |
|
"learning_rate": 4.850202244525987e-05, |
|
"loss": 1.774, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.5688744412840309, |
|
"grad_norm": 1.2995566129684448, |
|
"learning_rate": 4.8413567809396376e-05, |
|
"loss": 1.714, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.585127996749289, |
|
"grad_norm": 1.23491370677948, |
|
"learning_rate": 4.8322661363589507e-05, |
|
"loss": 1.7717, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.6013815522145469, |
|
"grad_norm": 1.1809489727020264, |
|
"learning_rate": 4.822931262733367e-05, |
|
"loss": 1.722, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.617635107679805, |
|
"grad_norm": 0.988572359085083, |
|
"learning_rate": 4.813353137587377e-05, |
|
"loss": 1.7007, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.633888663145063, |
|
"grad_norm": 1.0803310871124268, |
|
"learning_rate": 4.803532763918162e-05, |
|
"loss": 1.6824, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.650142218610321, |
|
"grad_norm": 1.02713143825531, |
|
"learning_rate": 4.793471170090555e-05, |
|
"loss": 1.6453, |
|
"step": 200 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 1535, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.0362791277468058e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|