vermoney's picture
Training in progress, step 10, checkpoint
7a2c6a0 verified
raw
history blame
2.18 kB
{
"best_metric": 11.931222915649414,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.00022024733776030483,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.202473377603048e-05,
"eval_loss": 11.931365013122559,
"eval_runtime": 257.5762,
"eval_samples_per_second": 74.223,
"eval_steps_per_second": 37.111,
"step": 1
},
{
"epoch": 6.607420132809145e-05,
"grad_norm": 0.010707435198128223,
"learning_rate": 0.00012,
"loss": 11.9321,
"step": 3
},
{
"epoch": 0.00011012366888015241,
"eval_loss": 11.931319236755371,
"eval_runtime": 257.6143,
"eval_samples_per_second": 74.212,
"eval_steps_per_second": 37.106,
"step": 5
},
{
"epoch": 0.0001321484026561829,
"grad_norm": 0.018232014030218124,
"learning_rate": 0.0001992114701314478,
"loss": 11.9308,
"step": 6
},
{
"epoch": 0.00019822260398427434,
"grad_norm": 0.00781942717730999,
"learning_rate": 0.00018763066800438636,
"loss": 11.9317,
"step": 9
},
{
"epoch": 0.00022024733776030483,
"eval_loss": 11.931222915649414,
"eval_runtime": 258.7168,
"eval_samples_per_second": 73.895,
"eval_steps_per_second": 36.948,
"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": 5527339008.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}