128 lines
2.5 KiB
JSON
128 lines
2.5 KiB
JSON
|
{
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 2.9770992366412212,
|
||
|
|
"global_step": 195,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.02,
|
||
|
|
"learning_rate": 0.0,
|
||
|
|
"loss": 2.2517,
|
||
|
|
"step": 1
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.24,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.9184,
|
||
|
|
"step": 16
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.49,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.7725,
|
||
|
|
"step": 32
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.73,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.7075,
|
||
|
|
"step": 48
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.98,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.6668,
|
||
|
|
"step": 64
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.99,
|
||
|
|
"eval_loss": 1.6166764497756958,
|
||
|
|
"eval_runtime": 22.5473,
|
||
|
|
"eval_samples_per_second": 38.985,
|
||
|
|
"eval_steps_per_second": 2.439,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.22,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.4567,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.47,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.4109,
|
||
|
|
"step": 96
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.71,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.3875,
|
||
|
|
"step": 112
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.95,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.3584,
|
||
|
|
"step": 128
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.0,
|
||
|
|
"eval_loss": 1.512587547302246,
|
||
|
|
"eval_runtime": 22.5311,
|
||
|
|
"eval_samples_per_second": 39.013,
|
||
|
|
"eval_steps_per_second": 2.441,
|
||
|
|
"step": 131
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.2,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.1651,
|
||
|
|
"step": 144
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.44,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.1092,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.69,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.0948,
|
||
|
|
"step": 176
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.93,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.0949,
|
||
|
|
"step": 192
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.98,
|
||
|
|
"eval_loss": 1.4942539930343628,
|
||
|
|
"eval_runtime": 22.489,
|
||
|
|
"eval_samples_per_second": 39.086,
|
||
|
|
"eval_steps_per_second": 2.446,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.98,
|
||
|
|
"step": 195,
|
||
|
|
"total_flos": 417490551177216.0,
|
||
|
|
"train_loss": 1.4244933299529248,
|
||
|
|
"train_runtime": 3089.4842,
|
||
|
|
"train_samples_per_second": 8.13,
|
||
|
|
"train_steps_per_second": 0.063
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"max_steps": 195,
|
||
|
|
"num_train_epochs": 3,
|
||
|
|
"total_flos": 417490551177216.0,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|