File size: 1,501 Bytes
1d377cd |
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 69 |
{
"best_metric": 2.429492235183716,
"best_model_checkpoint": "output/system-of-a-down/checkpoint-34",
"epoch": 2.0,
"global_step": 34,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.29,
"learning_rate": 0.000109940736055617,
"loss": 2.6172,
"step": 5
},
{
"epoch": 0.59,
"learning_rate": 4.982671888105512e-05,
"loss": 2.7188,
"step": 10
},
{
"epoch": 0.88,
"learning_rate": 4.6324050628611986e-06,
"loss": 2.6973,
"step": 15
},
{
"epoch": 1.0,
"eval_loss": 2.4792027473449707,
"eval_runtime": 1.1308,
"eval_samples_per_second": 22.108,
"eval_steps_per_second": 3.537,
"step": 17
},
{
"epoch": 1.18,
"learning_rate": 1.0275104488948473e-05,
"loss": 2.5817,
"step": 20
},
{
"epoch": 1.47,
"learning_rate": 6.227039054081748e-05,
"loss": 2.6768,
"step": 25
},
{
"epoch": 1.76,
"learning_rate": 0.00011929601172133719,
"loss": 2.3346,
"step": 30
},
{
"epoch": 2.0,
"eval_loss": 2.429492235183716,
"eval_runtime": 1.1473,
"eval_samples_per_second": 21.791,
"eval_steps_per_second": 3.487,
"step": 34
}
],
"max_steps": 51,
"num_train_epochs": 3,
"total_flos": 35013132288000.0,
"trial_name": null,
"trial_params": null
}
|