sergioalves's picture
Training in progress, step 10, checkpoint
0578553 verified
raw
history blame
2.13 kB
{
"best_metric": 1.727346420288086,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.0003989706557082727,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 3.9897065570827266e-05,
"eval_loss": 2.0509815216064453,
"eval_runtime": 1393.1445,
"eval_samples_per_second": 7.576,
"eval_steps_per_second": 3.788,
"step": 1
},
{
"epoch": 0.0001196911967124818,
"grad_norm": 1.2018862962722778,
"learning_rate": 3e-05,
"loss": 2.0903,
"step": 3
},
{
"epoch": 0.00019948532785413634,
"eval_loss": 1.9940987825393677,
"eval_runtime": 1398.4022,
"eval_samples_per_second": 7.547,
"eval_steps_per_second": 3.774,
"step": 5
},
{
"epoch": 0.0002393823934249636,
"grad_norm": 1.310300350189209,
"learning_rate": 6e-05,
"loss": 1.9366,
"step": 6
},
{
"epoch": 0.0003590735901374454,
"grad_norm": 1.1172022819519043,
"learning_rate": 9e-05,
"loss": 1.8335,
"step": 9
},
{
"epoch": 0.0003989706557082727,
"eval_loss": 1.727346420288086,
"eval_runtime": 1400.1392,
"eval_samples_per_second": 7.538,
"eval_steps_per_second": 3.769,
"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": 3709436417802240.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}