ardaspear's picture
Training in progress, step 18, checkpoint
02c0083 verified
raw
history blame
2.38 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.09183673469387756,
"eval_steps": 9,
"global_step": 18,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00510204081632653,
"eval_loss": 6.939616680145264,
"eval_runtime": 1.0293,
"eval_samples_per_second": 160.296,
"eval_steps_per_second": 40.803,
"step": 1
},
{
"epoch": 0.015306122448979591,
"grad_norm": 0.4716786742210388,
"learning_rate": 3e-05,
"loss": 6.9394,
"step": 3
},
{
"epoch": 0.030612244897959183,
"grad_norm": 0.49812349677085876,
"learning_rate": 6e-05,
"loss": 6.9356,
"step": 6
},
{
"epoch": 0.04591836734693878,
"grad_norm": 0.5289084911346436,
"learning_rate": 9e-05,
"loss": 6.933,
"step": 9
},
{
"epoch": 0.04591836734693878,
"eval_loss": 6.927786350250244,
"eval_runtime": 0.2695,
"eval_samples_per_second": 612.282,
"eval_steps_per_second": 155.854,
"step": 9
},
{
"epoch": 0.061224489795918366,
"grad_norm": 0.4804115891456604,
"learning_rate": 9.987820251299122e-05,
"loss": 6.9266,
"step": 12
},
{
"epoch": 0.07653061224489796,
"grad_norm": 0.5177415013313293,
"learning_rate": 9.924038765061042e-05,
"loss": 6.9163,
"step": 15
},
{
"epoch": 0.09183673469387756,
"grad_norm": 0.5697883367538452,
"learning_rate": 9.806308479691595e-05,
"loss": 6.9044,
"step": 18
},
{
"epoch": 0.09183673469387756,
"eval_loss": 6.897478103637695,
"eval_runtime": 0.271,
"eval_samples_per_second": 608.897,
"eval_steps_per_second": 154.992,
"step": 18
}
],
"logging_steps": 3,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 9,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 173003046912.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}