distilbert-base-imdb / trainer_state.json
jialicheng's picture
Upload folder using huggingface_hub
05561dc verified
raw
history blame
3.84 kB
{
"best_metric": 0.87396,
"best_model_checkpoint": "checkpoint/distilbert-base/imdb_42/checkpoint-1564",
"epoch": 10.0,
"global_step": 7820,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.87392,
"eval_loss": 0.29652780294418335,
"eval_runtime": 8.5888,
"eval_samples_per_second": 2910.752,
"eval_steps_per_second": 11.41,
"step": 782
},
{
"epoch": 1.28,
"learning_rate": 4.360613810741688e-05,
"loss": 0.3243,
"step": 1000
},
{
"epoch": 2.0,
"eval_accuracy": 0.87396,
"eval_loss": 0.3133092522621155,
"eval_runtime": 8.2501,
"eval_samples_per_second": 3030.277,
"eval_steps_per_second": 11.879,
"step": 1564
},
{
"epoch": 2.56,
"learning_rate": 3.721227621483376e-05,
"loss": 0.1574,
"step": 2000
},
{
"epoch": 3.0,
"eval_accuracy": 0.8712,
"eval_loss": 0.5505877137184143,
"eval_runtime": 8.2054,
"eval_samples_per_second": 3046.769,
"eval_steps_per_second": 11.943,
"step": 2346
},
{
"epoch": 3.84,
"learning_rate": 3.081841432225064e-05,
"loss": 0.066,
"step": 3000
},
{
"epoch": 4.0,
"eval_accuracy": 0.86316,
"eval_loss": 0.6083658337593079,
"eval_runtime": 8.1073,
"eval_samples_per_second": 3083.646,
"eval_steps_per_second": 12.088,
"step": 3128
},
{
"epoch": 5.0,
"eval_accuracy": 0.87084,
"eval_loss": 0.6640308499336243,
"eval_runtime": 8.1424,
"eval_samples_per_second": 3070.331,
"eval_steps_per_second": 12.036,
"step": 3910
},
{
"epoch": 5.12,
"learning_rate": 2.442455242966752e-05,
"loss": 0.0308,
"step": 4000
},
{
"epoch": 6.0,
"eval_accuracy": 0.87112,
"eval_loss": 0.8268970251083374,
"eval_runtime": 8.1225,
"eval_samples_per_second": 3077.853,
"eval_steps_per_second": 12.065,
"step": 4692
},
{
"epoch": 6.39,
"learning_rate": 1.80306905370844e-05,
"loss": 0.0167,
"step": 5000
},
{
"epoch": 7.0,
"eval_accuracy": 0.87168,
"eval_loss": 0.8184564709663391,
"eval_runtime": 8.134,
"eval_samples_per_second": 3073.521,
"eval_steps_per_second": 12.048,
"step": 5474
},
{
"epoch": 7.67,
"learning_rate": 1.163682864450128e-05,
"loss": 0.0099,
"step": 6000
},
{
"epoch": 8.0,
"eval_accuracy": 0.87244,
"eval_loss": 0.9372827410697937,
"eval_runtime": 8.0981,
"eval_samples_per_second": 3087.162,
"eval_steps_per_second": 12.102,
"step": 6256
},
{
"epoch": 8.95,
"learning_rate": 5.242966751918159e-06,
"loss": 0.0056,
"step": 7000
},
{
"epoch": 9.0,
"eval_accuracy": 0.87288,
"eval_loss": 0.994419276714325,
"eval_runtime": 8.137,
"eval_samples_per_second": 3072.372,
"eval_steps_per_second": 12.044,
"step": 7038
},
{
"epoch": 10.0,
"eval_accuracy": 0.87356,
"eval_loss": 0.9994614720344543,
"eval_runtime": 8.1462,
"eval_samples_per_second": 3068.914,
"eval_steps_per_second": 12.03,
"step": 7820
},
{
"epoch": 10.0,
"step": 7820,
"total_flos": 8279212416000000.0,
"train_loss": 0.07839516550683609,
"train_runtime": 418.6292,
"train_samples_per_second": 597.187,
"train_steps_per_second": 18.68
}
],
"max_steps": 7820,
"num_train_epochs": 10,
"total_flos": 8279212416000000.0,
"trial_name": null,
"trial_params": null
}