File size: 1,544 Bytes
f80f58d |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.1446540880503147,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.5832258064516129,
"eval_loss": 0.19133226573467255,
"eval_runtime": 1.4535,
"eval_samples_per_second": 2132.847,
"eval_steps_per_second": 44.721,
"step": 318
},
{
"epoch": 1.57,
"learning_rate": 1.685534591194969e-05,
"loss": 0.309,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.827741935483871,
"eval_loss": 0.09374182671308517,
"eval_runtime": 1.4509,
"eval_samples_per_second": 2136.594,
"eval_steps_per_second": 44.8,
"step": 636
},
{
"epoch": 3.0,
"eval_accuracy": 0.8790322580645161,
"eval_loss": 0.06333240121603012,
"eval_runtime": 1.4496,
"eval_samples_per_second": 2138.579,
"eval_steps_per_second": 44.841,
"step": 954
},
{
"epoch": 3.14,
"learning_rate": 1.371069182389937e-05,
"loss": 0.1078,
"step": 1000
}
],
"logging_steps": 500,
"max_steps": 3180,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 260572968372528.0,
"train_batch_size": 48,
"trial_name": null,
"trial_params": {
"alpha": 0.3001695987245524,
"num_train_epochs": 10,
"temperature": 17
}
}
|