File size: 3,244 Bytes
4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 4783c7b 4994314 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
{
"best_metric": 0.8062622309197651,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-480",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 480,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.0269759893417358,
"learning_rate": 5.9043684647359026e-05,
"loss": 0.5339,
"step": 96
},
{
"epoch": 1.0,
"eval_accuracy": 0.7035225048923679,
"eval_f1": 0.6651933701657459,
"eval_loss": 0.4725688099861145,
"eval_precision": 0.7639593908629442,
"eval_recall": 0.589041095890411,
"eval_runtime": 28.4268,
"eval_samples_per_second": 35.952,
"eval_steps_per_second": 1.126,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 1.4684391021728516,
"learning_rate": 4.920307053946586e-05,
"loss": 0.4589,
"step": 192
},
{
"epoch": 2.0,
"eval_accuracy": 0.7563600782778865,
"eval_f1": 0.7537091988130563,
"eval_loss": 0.4252457022666931,
"eval_precision": 0.762,
"eval_recall": 0.7455968688845401,
"eval_runtime": 28.3965,
"eval_samples_per_second": 35.99,
"eval_steps_per_second": 1.127,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 1.83766770362854,
"learning_rate": 3.9362456431572686e-05,
"loss": 0.4336,
"step": 288
},
{
"epoch": 3.0,
"eval_accuracy": 0.8013698630136986,
"eval_f1": 0.8122109158186863,
"eval_loss": 0.41349494457244873,
"eval_precision": 0.7701754385964912,
"eval_recall": 0.8590998043052838,
"eval_runtime": 28.5368,
"eval_samples_per_second": 35.813,
"eval_steps_per_second": 1.121,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 1.8088363409042358,
"learning_rate": 2.9521842323679513e-05,
"loss": 0.424,
"step": 384
},
{
"epoch": 4.0,
"eval_accuracy": 0.7945205479452054,
"eval_f1": 0.7965116279069767,
"eval_loss": 0.40849176049232483,
"eval_precision": 0.7888675623800384,
"eval_recall": 0.8043052837573386,
"eval_runtime": 29.2183,
"eval_samples_per_second": 34.978,
"eval_steps_per_second": 1.095,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 1.6147538423538208,
"learning_rate": 1.9681228215786343e-05,
"loss": 0.4186,
"step": 480
},
{
"epoch": 5.0,
"eval_accuracy": 0.8062622309197651,
"eval_f1": 0.818014705882353,
"eval_loss": 0.40458473563194275,
"eval_precision": 0.7712305025996534,
"eval_recall": 0.8708414872798435,
"eval_runtime": 30.48,
"eval_samples_per_second": 33.53,
"eval_steps_per_second": 1.05,
"step": 480
}
],
"logging_steps": 500,
"max_steps": 672,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 500,
"total_flos": 1178475986400.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.7341280696937652,
"learning_rate": 6.88842987552522e-05,
"num_train_epochs": 7,
"temperature": 8
}
}
|