sergioalves's picture
Training in progress, step 10, checkpoint
878963a verified
raw
history blame
2.12 kB
{
"best_metric": 3.4370737075805664,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.0016354567012838335,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00016354567012838336,
"eval_loss": 4.267529487609863,
"eval_runtime": 507.3022,
"eval_samples_per_second": 5.076,
"eval_steps_per_second": 2.539,
"step": 1
},
{
"epoch": 0.00049063701038515,
"grad_norm": 1.061664342880249,
"learning_rate": 3e-05,
"loss": 3.8929,
"step": 3
},
{
"epoch": 0.0008177283506419167,
"eval_loss": 4.160350322723389,
"eval_runtime": 510.5273,
"eval_samples_per_second": 5.044,
"eval_steps_per_second": 2.523,
"step": 5
},
{
"epoch": 0.0009812740207703,
"grad_norm": 1.6031444072723389,
"learning_rate": 6e-05,
"loss": 4.122,
"step": 6
},
{
"epoch": 0.0014719110311554502,
"grad_norm": 1.1639562845230103,
"learning_rate": 9e-05,
"loss": 3.4398,
"step": 9
},
{
"epoch": 0.0016354567012838335,
"eval_loss": 3.4370737075805664,
"eval_runtime": 510.509,
"eval_samples_per_second": 5.044,
"eval_steps_per_second": 2.523,
"step": 10
}
],
"logging_steps": 3,
"max_steps": 30,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 10,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6347789697024000.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}