Harish Tayyar Madabushi
added model
afaced1
{
"best_metric": 0.9592657342657342,
"best_model_checkpoint": "output-no-git/EN-OUTPUT/ON_FS_OUT/XLNetFalseTrue-0-1/FalseTrue-0/train_from_dev_and_test.csv/0/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": 0.8583691120147705,
"eval_f1": 0.8558168316831684,
"eval_f1_binary": 0.8750000000000001,
"eval_f1_weighted": 0.8600157226023032,
"eval_loss": 0.336619108915329,
"eval_runtime": 1.8593,
"eval_samples_per_second": 250.638,
"eval_steps_per_second": 31.733,
"step": 9
},
{
"epoch": 2.0,
"eval_accuracy": 0.8712446093559265,
"eval_f1": 0.8563619924379419,
"eval_f1_binary": 0.9025974025974026,
"eval_f1_weighted": 0.8664821895114718,
"eval_loss": 0.28895148634910583,
"eval_runtime": 1.8336,
"eval_samples_per_second": 254.149,
"eval_steps_per_second": 32.178,
"step": 18
},
{
"epoch": 3.0,
"eval_accuracy": 0.946351945400238,
"eval_f1": 0.9442250149611011,
"eval_f1_binary": 0.9551166965888689,
"eval_f1_weighted": 0.946609031111385,
"eval_loss": 0.17678162455558777,
"eval_runtime": 1.8406,
"eval_samples_per_second": 253.179,
"eval_steps_per_second": 32.055,
"step": 27
},
{
"epoch": 4.0,
"eval_accuracy": 0.9484978318214417,
"eval_f1": 0.9456876456876457,
"eval_f1_binary": 0.9580419580419581,
"eval_f1_weighted": 0.9483918084776456,
"eval_loss": 0.18410657346248627,
"eval_runtime": 1.8296,
"eval_samples_per_second": 254.697,
"eval_steps_per_second": 32.247,
"step": 36
},
{
"epoch": 5.0,
"eval_accuracy": 0.9399141669273376,
"eval_f1": 0.9357975122028027,
"eval_f1_binary": 0.952054794520548,
"eval_f1_weighted": 0.9393559731393049,
"eval_loss": 0.23064567148685455,
"eval_runtime": 1.9476,
"eval_samples_per_second": 239.272,
"eval_steps_per_second": 30.294,
"step": 45
},
{
"epoch": 6.0,
"eval_accuracy": 0.959227442741394,
"eval_f1": 0.9571332432811903,
"eval_f1_binary": 0.9666080843585237,
"eval_f1_weighted": 0.9592071355341688,
"eval_loss": 0.1858169287443161,
"eval_runtime": 1.8406,
"eval_samples_per_second": 253.182,
"eval_steps_per_second": 32.055,
"step": 54
},
{
"epoch": 7.0,
"eval_accuracy": 0.9570815563201904,
"eval_f1": 0.9550097511054471,
"eval_f1_binary": 0.9646643109540636,
"eval_f1_weighted": 0.9571229809435562,
"eval_loss": 0.19335472583770752,
"eval_runtime": 1.8323,
"eval_samples_per_second": 254.327,
"eval_steps_per_second": 32.2,
"step": 63
},
{
"epoch": 8.0,
"eval_accuracy": 0.954935610294342,
"eval_f1": 0.9527143581938102,
"eval_f1_binary": 0.962962962962963,
"eval_f1_weighted": 0.9549576150316936,
"eval_loss": 0.20666901767253876,
"eval_runtime": 1.8259,
"eval_samples_per_second": 255.216,
"eval_steps_per_second": 32.313,
"step": 72
},
{
"epoch": 9.0,
"eval_accuracy": 0.9613733887672424,
"eval_f1": 0.9592657342657342,
"eval_f1_binary": 0.9685314685314687,
"eval_f1_weighted": 0.9612938563582343,
"eval_loss": 0.21665425598621368,
"eval_runtime": 1.8426,
"eval_samples_per_second": 252.897,
"eval_steps_per_second": 32.019,
"step": 81
}
],
"max_steps": 81,
"num_train_epochs": 9,
"total_flos": 180756537375744.0,
"trial_name": null,
"trial_params": null
}