File size: 2,758 Bytes
e2d803d |
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 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.6916890080428955,
"eval_steps": 500,
"global_step": 3500,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.6702412868632708,
"grad_norm": 12.96187973022461,
"learning_rate": 5.852478627669732e-06,
"loss": 0.5779,
"step": 500
},
{
"epoch": 1.0,
"eval_accuracy": 0.7619845867156982,
"eval_loss": 0.48268476128578186,
"eval_runtime": 9.469,
"eval_samples_per_second": 315.027,
"eval_steps_per_second": 19.749,
"step": 746
},
{
"epoch": 1.3404825737265416,
"grad_norm": 19.64900779724121,
"learning_rate": 5.432041944647482e-06,
"loss": 0.464,
"step": 1000
},
{
"epoch": 2.0,
"eval_accuracy": 0.7680187821388245,
"eval_loss": 0.5030698180198669,
"eval_runtime": 9.5015,
"eval_samples_per_second": 313.951,
"eval_steps_per_second": 19.681,
"step": 1492
},
{
"epoch": 2.0107238605898123,
"grad_norm": 9.11796760559082,
"learning_rate": 5.0116052616252305e-06,
"loss": 0.4025,
"step": 1500
},
{
"epoch": 2.680965147453083,
"grad_norm": 11.002016067504883,
"learning_rate": 4.59116857860298e-06,
"loss": 0.2688,
"step": 2000
},
{
"epoch": 3.0,
"eval_accuracy": 0.7747234106063843,
"eval_loss": 0.5899690389633179,
"eval_runtime": 9.4806,
"eval_samples_per_second": 314.643,
"eval_steps_per_second": 19.725,
"step": 2238
},
{
"epoch": 3.351206434316354,
"grad_norm": 3.2045211791992188,
"learning_rate": 4.170731895580729e-06,
"loss": 0.2182,
"step": 2500
},
{
"epoch": 4.0,
"eval_accuracy": 0.7673482894897461,
"eval_loss": 0.7394132614135742,
"eval_runtime": 9.6202,
"eval_samples_per_second": 310.077,
"eval_steps_per_second": 19.438,
"step": 2984
},
{
"epoch": 4.021447721179625,
"grad_norm": 0.5618192553520203,
"learning_rate": 3.7502952125584775e-06,
"loss": 0.1644,
"step": 3000
},
{
"epoch": 4.6916890080428955,
"grad_norm": 19.86639976501465,
"learning_rate": 3.3298585295362272e-06,
"loss": 0.1173,
"step": 3500
}
],
"logging_steps": 500,
"max_steps": 7460,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 9754219595620476.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": {
"learning_rate": 6.272915310691983e-06,
"per_device_train_batch_size": 16
}
}
|