swinv2-finetuned-ve-Ub200 / trainer_state.json
Augusto777's picture
End of training
d80da03 verified
{
"best_metric": 0.47058823529411764,
"best_model_checkpoint": "swinv2-finetuned-ve-Ub200\\checkpoint-52",
"epoch": 18.46153846153846,
"eval_steps": 500,
"global_step": 120,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.92,
"eval_accuracy": 0.09803921568627451,
"eval_loss": 7.98906135559082,
"eval_runtime": 0.9241,
"eval_samples_per_second": 55.187,
"eval_steps_per_second": 4.328,
"step": 6
},
{
"epoch": 2.0,
"eval_accuracy": 0.09803921568627451,
"eval_loss": 7.484771251678467,
"eval_runtime": 0.6772,
"eval_samples_per_second": 75.315,
"eval_steps_per_second": 5.907,
"step": 13
},
{
"epoch": 2.92,
"eval_accuracy": 0.09803921568627451,
"eval_loss": 6.237805366516113,
"eval_runtime": 0.6812,
"eval_samples_per_second": 74.871,
"eval_steps_per_second": 5.872,
"step": 19
},
{
"epoch": 4.0,
"eval_accuracy": 0.09803921568627451,
"eval_loss": 4.890049457550049,
"eval_runtime": 0.6892,
"eval_samples_per_second": 74.004,
"eval_steps_per_second": 5.804,
"step": 26
},
{
"epoch": 4.92,
"eval_accuracy": 0.09803921568627451,
"eval_loss": 3.8155035972595215,
"eval_runtime": 0.7122,
"eval_samples_per_second": 71.613,
"eval_steps_per_second": 5.617,
"step": 32
},
{
"epoch": 6.0,
"eval_accuracy": 0.09803921568627451,
"eval_loss": 2.734177350997925,
"eval_runtime": 0.6982,
"eval_samples_per_second": 73.05,
"eval_steps_per_second": 5.729,
"step": 39
},
{
"epoch": 6.92,
"eval_accuracy": 0.09803921568627451,
"eval_loss": 2.061161994934082,
"eval_runtime": 0.7197,
"eval_samples_per_second": 70.866,
"eval_steps_per_second": 5.558,
"step": 45
},
{
"epoch": 8.0,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.5976719856262207,
"eval_runtime": 0.7092,
"eval_samples_per_second": 71.915,
"eval_steps_per_second": 5.64,
"step": 52
},
{
"epoch": 8.92,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.3671493530273438,
"eval_runtime": 0.7002,
"eval_samples_per_second": 72.839,
"eval_steps_per_second": 5.713,
"step": 58
},
{
"epoch": 10.0,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.2121994495391846,
"eval_runtime": 0.7052,
"eval_samples_per_second": 72.324,
"eval_steps_per_second": 5.672,
"step": 65
},
{
"epoch": 10.92,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.1822781562805176,
"eval_runtime": 0.6897,
"eval_samples_per_second": 73.949,
"eval_steps_per_second": 5.8,
"step": 71
},
{
"epoch": 12.0,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.1835217475891113,
"eval_runtime": 0.6842,
"eval_samples_per_second": 74.543,
"eval_steps_per_second": 5.846,
"step": 78
},
{
"epoch": 12.92,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.1837899684906006,
"eval_runtime": 0.6912,
"eval_samples_per_second": 73.79,
"eval_steps_per_second": 5.787,
"step": 84
},
{
"epoch": 14.0,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.1778271198272705,
"eval_runtime": 0.7032,
"eval_samples_per_second": 72.53,
"eval_steps_per_second": 5.689,
"step": 91
},
{
"epoch": 14.92,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.1768624782562256,
"eval_runtime": 0.7257,
"eval_samples_per_second": 70.28,
"eval_steps_per_second": 5.512,
"step": 97
},
{
"epoch": 15.38,
"learning_rate": 9.259259259259259e-06,
"loss": 3.2267,
"step": 100
},
{
"epoch": 16.0,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.1761610507965088,
"eval_runtime": 0.7092,
"eval_samples_per_second": 71.914,
"eval_steps_per_second": 5.64,
"step": 104
},
{
"epoch": 16.92,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.1758278608322144,
"eval_runtime": 0.7082,
"eval_samples_per_second": 72.016,
"eval_steps_per_second": 5.648,
"step": 110
},
{
"epoch": 18.0,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.1769851446151733,
"eval_runtime": 0.6832,
"eval_samples_per_second": 74.654,
"eval_steps_per_second": 5.855,
"step": 117
},
{
"epoch": 18.46,
"eval_accuracy": 0.47058823529411764,
"eval_loss": 1.177069067955017,
"eval_runtime": 0.7242,
"eval_samples_per_second": 70.425,
"eval_steps_per_second": 5.524,
"step": 120
},
{
"epoch": 18.46,
"step": 120,
"total_flos": 1.220105355264e+17,
"train_loss": 2.8912477493286133,
"train_runtime": 106.7077,
"train_samples_per_second": 38.048,
"train_steps_per_second": 1.125
}
],
"logging_steps": 100,
"max_steps": 120,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"total_flos": 1.220105355264e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}