File size: 1,213 Bytes
9874885 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9103322712790168,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.46,
"grad_norm": 0.36198097467422485,
"learning_rate": 6.0716454159077105e-05,
"loss": 0.4455,
"step": 500
},
{
"epoch": 0.46,
"eval_loss": 0.6183120608329773,
"eval_runtime": 195.3588,
"eval_samples_per_second": 2.37,
"eval_steps_per_second": 2.37,
"step": 500
},
{
"epoch": 0.91,
"grad_norm": 0.1898297369480133,
"learning_rate": 0.00012143290831815421,
"loss": 0.0995,
"step": 1000
},
{
"epoch": 0.91,
"eval_loss": 0.6644699573516846,
"eval_runtime": 195.5381,
"eval_samples_per_second": 2.368,
"eval_steps_per_second": 2.368,
"step": 1000
}
],
"logging_steps": 500,
"max_steps": 54900,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 8.435525835017011e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|