test2 / checkpoint-300 /trainer_state.json
samihaafaf's picture
Upload folder using huggingface_hub
ff35873
{
"best_metric": 0.6926904320716858,
"best_model_checkpoint": "/tmp/model/checkpoint-300",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2,
"learning_rate": 2e-05,
"loss": 0.6932,
"step": 15
},
{
"epoch": 0.4,
"learning_rate": 4e-05,
"loss": 0.6935,
"step": 30
},
{
"epoch": 0.6,
"learning_rate": 6e-05,
"loss": 0.6934,
"step": 45
},
{
"epoch": 0.8,
"learning_rate": 8e-05,
"loss": 0.6936,
"step": 60
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.6936,
"step": 75
},
{
"epoch": 1.0,
"eval_accuracy": 0.5533333333333333,
"eval_auc": 0.5650777777777778,
"eval_f1": 0.5620915032679739,
"eval_loss": 0.6929760575294495,
"eval_precision": 0.5512820512820513,
"eval_recall": 0.5733333333333334,
"eval_runtime": 4.573,
"eval_samples_per_second": 131.205,
"eval_steps_per_second": 8.31,
"step": 75
},
{
"epoch": 1.2,
"learning_rate": 9.777777777777778e-05,
"loss": 0.6933,
"step": 90
},
{
"epoch": 1.4,
"learning_rate": 9.555555555555557e-05,
"loss": 0.6913,
"step": 105
},
{
"epoch": 1.6,
"learning_rate": 9.333333333333334e-05,
"loss": 0.6926,
"step": 120
},
{
"epoch": 1.8,
"learning_rate": 9.111111111111112e-05,
"loss": 0.6945,
"step": 135
},
{
"epoch": 2.0,
"learning_rate": 8.888888888888889e-05,
"loss": 0.7082,
"step": 150
},
{
"epoch": 2.0,
"eval_accuracy": 0.5,
"eval_auc": 0.5238666666666667,
"eval_f1": 0.6666666666666666,
"eval_loss": 0.6932576298713684,
"eval_precision": 0.5,
"eval_recall": 1.0,
"eval_runtime": 4.5135,
"eval_samples_per_second": 132.936,
"eval_steps_per_second": 8.419,
"step": 150
},
{
"epoch": 2.2,
"learning_rate": 8.666666666666667e-05,
"loss": 0.6868,
"step": 165
},
{
"epoch": 2.4,
"learning_rate": 8.444444444444444e-05,
"loss": 0.6979,
"step": 180
},
{
"epoch": 2.6,
"learning_rate": 8.222222222222222e-05,
"loss": 0.6939,
"step": 195
},
{
"epoch": 2.8,
"learning_rate": 8e-05,
"loss": 0.6946,
"step": 210
},
{
"epoch": 3.0,
"learning_rate": 7.777777777777778e-05,
"loss": 0.6936,
"step": 225
},
{
"epoch": 3.0,
"eval_accuracy": 0.5466666666666666,
"eval_auc": 0.5420722222222223,
"eval_f1": 0.4999999999999999,
"eval_loss": 0.6928548216819763,
"eval_precision": 0.5573770491803278,
"eval_recall": 0.4533333333333333,
"eval_runtime": 4.4853,
"eval_samples_per_second": 133.77,
"eval_steps_per_second": 8.472,
"step": 225
},
{
"epoch": 3.2,
"learning_rate": 7.555555555555556e-05,
"loss": 0.6932,
"step": 240
},
{
"epoch": 3.4,
"learning_rate": 7.333333333333333e-05,
"loss": 0.693,
"step": 255
},
{
"epoch": 3.6,
"learning_rate": 7.111111111111112e-05,
"loss": 0.6905,
"step": 270
},
{
"epoch": 3.8,
"learning_rate": 6.88888888888889e-05,
"loss": 0.6906,
"step": 285
},
{
"epoch": 4.0,
"learning_rate": 6.666666666666667e-05,
"loss": 0.6952,
"step": 300
},
{
"epoch": 4.0,
"eval_accuracy": 0.5033333333333333,
"eval_auc": 0.5401888888888888,
"eval_f1": 0.6644144144144143,
"eval_loss": 0.6926904320716858,
"eval_precision": 0.5017006802721088,
"eval_recall": 0.9833333333333333,
"eval_runtime": 4.4974,
"eval_samples_per_second": 133.412,
"eval_steps_per_second": 8.449,
"step": 300
}
],
"logging_steps": 15,
"max_steps": 750,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 5.0964968226816e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}