tensor24's picture
Training in progress, step 3, checkpoint
d1d2027 verified
raw
history blame
1.65 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.004259850905218318,
"eval_steps": 3,
"global_step": 3,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0014199503017394391,
"grad_norm": 2.71122407913208,
"learning_rate": 2e-05,
"loss": 3.4024,
"step": 1
},
{
"epoch": 0.0014199503017394391,
"eval_loss": 4.24873161315918,
"eval_runtime": 18.9832,
"eval_samples_per_second": 15.645,
"eval_steps_per_second": 7.849,
"step": 1
},
{
"epoch": 0.0028399006034788782,
"grad_norm": 2.185009717941284,
"learning_rate": 4e-05,
"loss": 2.5114,
"step": 2
},
{
"epoch": 0.004259850905218318,
"grad_norm": 2.2500784397125244,
"learning_rate": 6e-05,
"loss": 2.9047,
"step": 3
},
{
"epoch": 0.004259850905218318,
"eval_loss": 4.236300945281982,
"eval_runtime": 19.0254,
"eval_samples_per_second": 15.611,
"eval_steps_per_second": 7.832,
"step": 3
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 83302551650304.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}