LiYuan199701
Add model weights and configurations
f26777c
raw
history blame
9.33 kB
{
"best_metric": 0.63705,
"best_model_checkpoint": "distilbert-base-uncased-finetuned-mnli/checkpoint-35702",
"epoch": 1.0,
"global_step": 35702,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1.9859951823427263e-05,
"loss": 1.1951,
"step": 500
},
{
"epoch": 0.03,
"learning_rate": 1.971990364685452e-05,
"loss": 1.1418,
"step": 1000
},
{
"epoch": 0.04,
"learning_rate": 1.9579855470281778e-05,
"loss": 1.099,
"step": 1500
},
{
"epoch": 0.06,
"learning_rate": 1.9439807293709036e-05,
"loss": 1.0961,
"step": 2000
},
{
"epoch": 0.07,
"learning_rate": 1.9299759117136297e-05,
"loss": 1.0836,
"step": 2500
},
{
"epoch": 0.08,
"learning_rate": 1.9159710940563555e-05,
"loss": 1.0721,
"step": 3000
},
{
"epoch": 0.1,
"learning_rate": 1.9019662763990812e-05,
"loss": 1.0654,
"step": 3500
},
{
"epoch": 0.11,
"learning_rate": 1.8879614587418074e-05,
"loss": 1.0439,
"step": 4000
},
{
"epoch": 0.13,
"learning_rate": 1.873956641084533e-05,
"loss": 1.0453,
"step": 4500
},
{
"epoch": 0.14,
"learning_rate": 1.8599518234272592e-05,
"loss": 1.0399,
"step": 5000
},
{
"epoch": 0.15,
"learning_rate": 1.845947005769985e-05,
"loss": 1.0295,
"step": 5500
},
{
"epoch": 0.17,
"learning_rate": 1.8319421881127108e-05,
"loss": 1.0417,
"step": 6000
},
{
"epoch": 0.18,
"learning_rate": 1.817937370455437e-05,
"loss": 1.0327,
"step": 6500
},
{
"epoch": 0.2,
"learning_rate": 1.8039325527981627e-05,
"loss": 1.0148,
"step": 7000
},
{
"epoch": 0.21,
"learning_rate": 1.7899277351408884e-05,
"loss": 1.0171,
"step": 7500
},
{
"epoch": 0.22,
"learning_rate": 1.7759229174836145e-05,
"loss": 1.0113,
"step": 8000
},
{
"epoch": 0.24,
"learning_rate": 1.7619180998263403e-05,
"loss": 1.0062,
"step": 8500
},
{
"epoch": 0.25,
"learning_rate": 1.7479132821690664e-05,
"loss": 1.0022,
"step": 9000
},
{
"epoch": 0.27,
"learning_rate": 1.7339084645117922e-05,
"loss": 0.9908,
"step": 9500
},
{
"epoch": 0.28,
"learning_rate": 1.719903646854518e-05,
"loss": 0.9919,
"step": 10000
},
{
"epoch": 0.29,
"learning_rate": 1.705898829197244e-05,
"loss": 0.9875,
"step": 10500
},
{
"epoch": 0.31,
"learning_rate": 1.69189401153997e-05,
"loss": 0.9908,
"step": 11000
},
{
"epoch": 0.32,
"learning_rate": 1.6778891938826956e-05,
"loss": 0.9807,
"step": 11500
},
{
"epoch": 0.34,
"learning_rate": 1.6638843762254217e-05,
"loss": 0.9622,
"step": 12000
},
{
"epoch": 0.35,
"learning_rate": 1.6498795585681475e-05,
"loss": 0.9698,
"step": 12500
},
{
"epoch": 0.36,
"learning_rate": 1.6358747409108736e-05,
"loss": 0.9611,
"step": 13000
},
{
"epoch": 0.38,
"learning_rate": 1.6218699232535994e-05,
"loss": 0.9844,
"step": 13500
},
{
"epoch": 0.39,
"learning_rate": 1.6078651055963252e-05,
"loss": 0.9717,
"step": 14000
},
{
"epoch": 0.41,
"learning_rate": 1.5938602879390513e-05,
"loss": 0.978,
"step": 14500
},
{
"epoch": 0.42,
"learning_rate": 1.579855470281777e-05,
"loss": 0.9684,
"step": 15000
},
{
"epoch": 0.43,
"learning_rate": 1.5658506526245028e-05,
"loss": 0.9518,
"step": 15500
},
{
"epoch": 0.45,
"learning_rate": 1.551845834967229e-05,
"loss": 0.9592,
"step": 16000
},
{
"epoch": 0.46,
"learning_rate": 1.5378410173099547e-05,
"loss": 0.9482,
"step": 16500
},
{
"epoch": 0.48,
"learning_rate": 1.5238361996526806e-05,
"loss": 0.9565,
"step": 17000
},
{
"epoch": 0.49,
"learning_rate": 1.5098313819954064e-05,
"loss": 0.956,
"step": 17500
},
{
"epoch": 0.5,
"learning_rate": 1.4958265643381324e-05,
"loss": 0.9432,
"step": 18000
},
{
"epoch": 0.52,
"learning_rate": 1.4818217466808585e-05,
"loss": 0.943,
"step": 18500
},
{
"epoch": 0.53,
"learning_rate": 1.4678169290235842e-05,
"loss": 0.9354,
"step": 19000
},
{
"epoch": 0.55,
"learning_rate": 1.4538121113663102e-05,
"loss": 0.958,
"step": 19500
},
{
"epoch": 0.56,
"learning_rate": 1.439807293709036e-05,
"loss": 0.9358,
"step": 20000
},
{
"epoch": 0.57,
"learning_rate": 1.4258024760517619e-05,
"loss": 0.9395,
"step": 20500
},
{
"epoch": 0.59,
"learning_rate": 1.4117976583944878e-05,
"loss": 0.9448,
"step": 21000
},
{
"epoch": 0.6,
"learning_rate": 1.3977928407372136e-05,
"loss": 0.9349,
"step": 21500
},
{
"epoch": 0.62,
"learning_rate": 1.3837880230799397e-05,
"loss": 0.9444,
"step": 22000
},
{
"epoch": 0.63,
"learning_rate": 1.3697832054226653e-05,
"loss": 0.929,
"step": 22500
},
{
"epoch": 0.64,
"learning_rate": 1.3557783877653914e-05,
"loss": 0.933,
"step": 23000
},
{
"epoch": 0.66,
"learning_rate": 1.3417735701081174e-05,
"loss": 0.9357,
"step": 23500
},
{
"epoch": 0.67,
"learning_rate": 1.3277687524508432e-05,
"loss": 0.9182,
"step": 24000
},
{
"epoch": 0.69,
"learning_rate": 1.3137639347935691e-05,
"loss": 0.9279,
"step": 24500
},
{
"epoch": 0.7,
"learning_rate": 1.299759117136295e-05,
"loss": 0.9245,
"step": 25000
},
{
"epoch": 0.71,
"learning_rate": 1.2857542994790208e-05,
"loss": 0.9205,
"step": 25500
},
{
"epoch": 0.73,
"learning_rate": 1.271749481821747e-05,
"loss": 0.9214,
"step": 26000
},
{
"epoch": 0.74,
"learning_rate": 1.2577446641644725e-05,
"loss": 0.9388,
"step": 26500
},
{
"epoch": 0.76,
"learning_rate": 1.2437398465071986e-05,
"loss": 0.9256,
"step": 27000
},
{
"epoch": 0.77,
"learning_rate": 1.2297350288499246e-05,
"loss": 0.9206,
"step": 27500
},
{
"epoch": 0.78,
"learning_rate": 1.2157302111926503e-05,
"loss": 0.9091,
"step": 28000
},
{
"epoch": 0.8,
"learning_rate": 1.2017253935353763e-05,
"loss": 0.9267,
"step": 28500
},
{
"epoch": 0.81,
"learning_rate": 1.187720575878102e-05,
"loss": 0.9103,
"step": 29000
},
{
"epoch": 0.83,
"learning_rate": 1.173715758220828e-05,
"loss": 0.9032,
"step": 29500
},
{
"epoch": 0.84,
"learning_rate": 1.1597109405635541e-05,
"loss": 0.9075,
"step": 30000
},
{
"epoch": 0.85,
"learning_rate": 1.1457061229062799e-05,
"loss": 0.9016,
"step": 30500
},
{
"epoch": 0.87,
"learning_rate": 1.1317013052490058e-05,
"loss": 0.9119,
"step": 31000
},
{
"epoch": 0.88,
"learning_rate": 1.1176964875917316e-05,
"loss": 0.9085,
"step": 31500
},
{
"epoch": 0.9,
"learning_rate": 1.1036916699344575e-05,
"loss": 0.894,
"step": 32000
},
{
"epoch": 0.91,
"learning_rate": 1.0896868522771835e-05,
"loss": 0.9156,
"step": 32500
},
{
"epoch": 0.92,
"learning_rate": 1.0756820346199093e-05,
"loss": 0.8944,
"step": 33000
},
{
"epoch": 0.94,
"learning_rate": 1.0616772169626352e-05,
"loss": 0.8824,
"step": 33500
},
{
"epoch": 0.95,
"learning_rate": 1.047672399305361e-05,
"loss": 0.9014,
"step": 34000
},
{
"epoch": 0.97,
"learning_rate": 1.033667581648087e-05,
"loss": 0.9022,
"step": 34500
},
{
"epoch": 0.98,
"learning_rate": 1.019662763990813e-05,
"loss": 0.8888,
"step": 35000
},
{
"epoch": 0.99,
"learning_rate": 1.0056579463335388e-05,
"loss": 0.8981,
"step": 35500
},
{
"epoch": 1.0,
"eval_accuracy": 0.63705,
"eval_loss": 0.8662445545196533,
"eval_runtime": 112.0196,
"eval_samples_per_second": 178.54,
"eval_steps_per_second": 11.159,
"step": 35702
}
],
"max_steps": 71404,
"num_train_epochs": 2,
"total_flos": 7.567112374034842e+16,
"trial_name": null,
"trial_params": null
}