Harish Tayyar Madabushi
added model
dd11e4c
{
"best_metric": 0.7920443179195198,
"best_model_checkpoint": "output-no-git/EN-OUTPUT/ON_FS_OUT/XLNetFalseTrue-0-1/FalseFalse-0/train_from_dev_and_test.csv/4/checkpoint-81",
"epoch": 9.0,
"global_step": 81,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.7725321650505066,
"eval_f1": 0.7563771232417289,
"eval_f1_binary": 0.8191126279863481,
"eval_f1_weighted": 0.7701089290012807,
"eval_loss": 0.5054362416267395,
"eval_runtime": 1.8375,
"eval_samples_per_second": 253.611,
"eval_steps_per_second": 32.11,
"step": 9
},
{
"epoch": 2.0,
"eval_accuracy": 0.721030056476593,
"eval_f1": 0.6446920821114369,
"eval_f1_binary": 0.8093841642228738,
"eval_f1_weighted": 0.6807405636036398,
"eval_loss": 0.6385602355003357,
"eval_runtime": 1.8316,
"eval_samples_per_second": 254.426,
"eval_steps_per_second": 32.213,
"step": 18
},
{
"epoch": 3.0,
"eval_accuracy": 0.7811158895492554,
"eval_f1": 0.7456549657534247,
"eval_f1_binary": 0.8406250000000001,
"eval_f1_weighted": 0.7664423981421601,
"eval_loss": 0.6955846548080444,
"eval_runtime": 1.8305,
"eval_samples_per_second": 254.578,
"eval_steps_per_second": 32.232,
"step": 27
},
{
"epoch": 4.0,
"eval_accuracy": 0.7854077219963074,
"eval_f1": 0.760603320729903,
"eval_f1_binary": 0.8376623376623377,
"eval_f1_weighted": 0.7774703158524531,
"eval_loss": 0.7326841354370117,
"eval_runtime": 1.8306,
"eval_samples_per_second": 254.558,
"eval_steps_per_second": 32.229,
"step": 36
},
{
"epoch": 5.0,
"eval_accuracy": 0.7875536680221558,
"eval_f1": 0.7535932317454214,
"eval_f1_binary": 0.8450704225352113,
"eval_f1_weighted": 0.7736161361672208,
"eval_loss": 0.9596889019012451,
"eval_runtime": 1.8322,
"eval_samples_per_second": 254.333,
"eval_steps_per_second": 32.201,
"step": 45
},
{
"epoch": 6.0,
"eval_accuracy": 0.8111587762832642,
"eval_f1": 0.7893309222423146,
"eval_f1_binary": 0.8571428571428571,
"eval_f1_weighted": 0.8041738779501587,
"eval_loss": 0.8485983610153198,
"eval_runtime": 1.8435,
"eval_samples_per_second": 252.776,
"eval_steps_per_second": 32.004,
"step": 54
},
{
"epoch": 7.0,
"eval_accuracy": 0.8025751113891602,
"eval_f1": 0.7738818565400843,
"eval_f1_binary": 0.8544303797468354,
"eval_f1_weighted": 0.7915126491733218,
"eval_loss": 1.0803866386413574,
"eval_runtime": 1.8504,
"eval_samples_per_second": 251.841,
"eval_steps_per_second": 31.885,
"step": 63
},
{
"epoch": 8.0,
"eval_accuracy": 0.8133047223091125,
"eval_f1": 0.7907477277067516,
"eval_f1_binary": 0.8594507269789984,
"eval_f1_weighted": 0.8057857232556125,
"eval_loss": 0.9846170544624329,
"eval_runtime": 1.8389,
"eval_samples_per_second": 253.41,
"eval_steps_per_second": 32.084,
"step": 72
},
{
"epoch": 9.0,
"eval_accuracy": 0.8133047223091125,
"eval_f1": 0.7920443179195198,
"eval_f1_binary": 0.8585365853658536,
"eval_f1_weighted": 0.8065984193777302,
"eval_loss": 0.9904114007949829,
"eval_runtime": 1.8392,
"eval_samples_per_second": 253.365,
"eval_steps_per_second": 32.078,
"step": 81
}
],
"max_steps": 81,
"num_train_epochs": 9,
"total_flos": 180756537375744.0,
"trial_name": null,
"trial_params": null
}