File size: 1,629 Bytes
83748dd |
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 64 65 66 67 68 |
{
"best_metric": 0.2658565044403076,
"best_model_checkpoint": "./results/checkpoint-300",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 0.3161751329898834,
"eval_runtime": 9.883,
"eval_samples_per_second": 121.42,
"eval_steps_per_second": 15.178,
"step": 150
},
{
"epoch": 2.0,
"eval_loss": 0.2658565044403076,
"eval_runtime": 9.8592,
"eval_samples_per_second": 121.714,
"eval_steps_per_second": 15.214,
"step": 300
},
{
"epoch": 3.0,
"eval_loss": 0.26993614435195923,
"eval_runtime": 9.8656,
"eval_samples_per_second": 121.634,
"eval_steps_per_second": 15.204,
"step": 450
},
{
"epoch": 3.33,
"learning_rate": 8.888888888888888e-06,
"loss": 0.281,
"step": 500
},
{
"epoch": 4.0,
"eval_loss": 0.2938203513622284,
"eval_runtime": 9.8632,
"eval_samples_per_second": 121.664,
"eval_steps_per_second": 15.208,
"step": 600
},
{
"epoch": 5.0,
"eval_loss": 0.31206923723220825,
"eval_runtime": 9.8546,
"eval_samples_per_second": 121.771,
"eval_steps_per_second": 15.221,
"step": 750
}
],
"logging_steps": 500,
"max_steps": 900,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 500,
"total_flos": 6314665328640000.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|