File size: 1,424 Bytes
880d6c0 |
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 53 54 55 56 57 58 59 60 61 62 63 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.23510971786833856,
"eval_steps": 50,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08,
"learning_rate": 2.3869346733668342e-05,
"loss": 0.7797,
"step": 50
},
{
"epoch": 0.08,
"eval_loss": 0.2723180055618286,
"eval_runtime": 135.6616,
"eval_samples_per_second": 5.263,
"eval_steps_per_second": 0.663,
"step": 50
},
{
"epoch": 0.16,
"learning_rate": 2.2613065326633167e-05,
"loss": 0.2457,
"step": 100
},
{
"epoch": 0.16,
"eval_loss": 0.22004182636737823,
"eval_runtime": 136.2348,
"eval_samples_per_second": 5.241,
"eval_steps_per_second": 0.661,
"step": 100
},
{
"epoch": 0.24,
"learning_rate": 2.135678391959799e-05,
"loss": 0.2088,
"step": 150
},
{
"epoch": 0.24,
"eval_loss": 0.19266444444656372,
"eval_runtime": 136.6465,
"eval_samples_per_second": 5.225,
"eval_steps_per_second": 0.659,
"step": 150
}
],
"logging_steps": 50,
"max_steps": 1000,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"total_flos": 2.62911113035776e+16,
"trial_name": null,
"trial_params": null
}
|