sergioalves's picture
Training in progress, step 10, checkpoint
5a4ab51 verified
raw
history blame
2.12 kB
{
"best_metric": 1.9741439819335938,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.0065930443382231745,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006593044338223175,
"eval_loss": 2.415243625640869,
"eval_runtime": 92.316,
"eval_samples_per_second": 6.922,
"eval_steps_per_second": 3.466,
"step": 1
},
{
"epoch": 0.0019779133014669525,
"grad_norm": 21.67613410949707,
"learning_rate": 3e-05,
"loss": 9.4106,
"step": 3
},
{
"epoch": 0.0032965221691115872,
"eval_loss": 2.2570438385009766,
"eval_runtime": 93.9378,
"eval_samples_per_second": 6.802,
"eval_steps_per_second": 3.407,
"step": 5
},
{
"epoch": 0.003955826602933905,
"grad_norm": 16.66733169555664,
"learning_rate": 6e-05,
"loss": 8.6288,
"step": 6
},
{
"epoch": 0.005933739904400857,
"grad_norm": 13.147473335266113,
"learning_rate": 9e-05,
"loss": 8.1932,
"step": 9
},
{
"epoch": 0.0065930443382231745,
"eval_loss": 1.9741439819335938,
"eval_runtime": 94.0939,
"eval_samples_per_second": 6.791,
"eval_steps_per_second": 3.401,
"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": 3515647493406720.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}