|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.991983741673253, |
|
"eval_steps": 500, |
|
"global_step": 26500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 9.991265511472117e-05, |
|
"loss": 0.6733, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 9.965092562404402e-05, |
|
"loss": 0.6594, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 9.921572595726207e-05, |
|
"loss": 0.6584, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 9.860857661297404e-05, |
|
"loss": 0.6542, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 9.78315988467729e-05, |
|
"loss": 0.6534, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 9.688750726001277e-05, |
|
"loss": 0.6473, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 9.577960031554716e-05, |
|
"loss": 0.6528, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 9.451174881357465e-05, |
|
"loss": 0.6399, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 9.308838236785487e-05, |
|
"loss": 0.6415, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 9.151447392954424e-05, |
|
"loss": 0.6464, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 8.979552241272211e-05, |
|
"loss": 0.6472, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 8.793753348230996e-05, |
|
"loss": 0.6506, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 8.594699857150682e-05, |
|
"loss": 0.6494, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 8.383087220204982e-05, |
|
"loss": 0.6378, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 8.159654768653795e-05, |
|
"loss": 0.6375, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 7.925183129771058e-05, |
|
"loss": 0.6345, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 7.680491499492743e-05, |
|
"loss": 0.6476, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 7.426434780313864e-05, |
|
"loss": 0.6436, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 7.163900594434061e-05, |
|
"loss": 0.6289, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 6.893806182587231e-05, |
|
"loss": 0.6139, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 6.617095199390065e-05, |
|
"loss": 0.6094, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 6.334734416405869e-05, |
|
"loss": 0.6161, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 6.047710344442528e-05, |
|
"loss": 0.6117, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 5.7570257868855534e-05, |
|
"loss": 0.6122, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 5.463696336108234e-05, |
|
"loss": 0.6114, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 5.168746825199652e-05, |
|
"loss": 0.6161, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 4.873207747407539e-05, |
|
"loss": 0.6078, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 4.5781116558057044e-05, |
|
"loss": 0.6004, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 4.2844895557648356e-05, |
|
"loss": 0.6031, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 3.9933673028306675e-05, |
|
"loss": 0.6041, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 3.705762018594586e-05, |
|
"loss": 0.6021, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 3.4226785370788796e-05, |
|
"loss": 0.6011, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 3.145105894052242e-05, |
|
"loss": 0.6001, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 2.8740138715411413e-05, |
|
"loss": 0.6032, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 2.6103496096098247e-05, |
|
"loss": 0.6115, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 2.3550342972467158e-05, |
|
"loss": 0.5783, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 2.108959953918542e-05, |
|
"loss": 0.5603, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 2.15, |
|
"learning_rate": 1.8729863130368315e-05, |
|
"loss": 0.5518, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 1.6479378182252464e-05, |
|
"loss": 0.5493, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 1.4346007428822483e-05, |
|
"loss": 0.5468, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 2.31, |
|
"learning_rate": 1.2337204431026971e-05, |
|
"loss": 0.5567, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 1.0459987535561556e-05, |
|
"loss": 0.5486, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 8.720915354201348e-06, |
|
"loss": 0.5323, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 7.126063849353265e-06, |
|
"loss": 0.5573, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 5.681005105886394e-06, |
|
"loss": 0.5576, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 4.3907878634075136e-06, |
|
"loss": 0.5535, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 3.2599198769977968e-06, |
|
"loss": 0.55, |
|
"step": 23500 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 2.2923521680387695e-06, |
|
"loss": 0.5547, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 1.4914652201519775e-06, |
|
"loss": 0.5356, |
|
"step": 24500 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 8.60057168480799e-07, |
|
"loss": 0.5422, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 4.0033402357874116e-07, |
|
"loss": 0.5433, |
|
"step": 25500 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 1.1390196405984821e-07, |
|
"loss": 0.5527, |
|
"step": 26000 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 1.761724939280951e-09, |
|
"loss": 0.5488, |
|
"step": 26500 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 26571, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 6.795640384443187e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|