cdetr-cd45rb-s / trainer_state.json
polejowska's picture
End of training
482e804
raw
history blame
2.14 kB
{
"best_metric": 2.0293631553649902,
"best_model_checkpoint": "cdetr-cd45rb-s/checkpoint-1210",
"epoch": 5.0,
"global_step": 1210,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 5e-05,
"loss": 2.6006,
"step": 242
},
{
"epoch": 1.0,
"eval_loss": 2.214585542678833,
"eval_runtime": 17.9919,
"eval_samples_per_second": 5.558,
"eval_steps_per_second": 0.723,
"step": 242
},
{
"epoch": 2.0,
"learning_rate": 0.0,
"loss": 2.2409,
"step": 484
},
{
"epoch": 2.0,
"eval_loss": 2.110588788986206,
"eval_runtime": 17.3999,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 0.747,
"step": 484
},
{
"epoch": 3.0,
"learning_rate": 4e-05,
"loss": 2.2027,
"step": 726
},
{
"epoch": 3.0,
"eval_loss": 2.145615339279175,
"eval_runtime": 17.7242,
"eval_samples_per_second": 5.642,
"eval_steps_per_second": 0.733,
"step": 726
},
{
"epoch": 4.0,
"learning_rate": 2e-05,
"loss": 2.183,
"step": 968
},
{
"epoch": 4.0,
"eval_loss": 2.0863144397735596,
"eval_runtime": 17.5156,
"eval_samples_per_second": 5.709,
"eval_steps_per_second": 0.742,
"step": 968
},
{
"epoch": 5.0,
"learning_rate": 0.0,
"loss": 2.0628,
"step": 1210
},
{
"epoch": 5.0,
"eval_loss": 2.0293631553649902,
"eval_runtime": 17.5041,
"eval_samples_per_second": 5.713,
"eval_steps_per_second": 0.743,
"step": 1210
},
{
"epoch": 5.0,
"step": 1210,
"total_flos": 2.4107363634816e+18,
"train_loss": 1.2896953235973012,
"train_runtime": 786.99,
"train_samples_per_second": 6.137,
"train_steps_per_second": 1.538
}
],
"max_steps": 1210,
"num_train_epochs": 5,
"total_flos": 2.4107363634816e+18,
"trial_name": null,
"trial_params": null
}