Views
No views yet
token-classificationsagemaker-training{'instance_type': 'ml.m5.2xlarge', 'supported_instructions': 'avx512'}100elastic/distilbert-base-uncased-finetuned-conll03-englishconll2003validation{'primary': 'tokens'}['ner_tags']train[]Falseminmax100onnxruntime111Falsedynamic, static['Add', 'MatMul'], ['Add']| quantization_approach | operators_to_quantize | precision (original) | precision (optimized) | recall (original) | recall (optimized) | f1 (original) | f1 (optimized) | accuracy (original) | accuracy (optimized) | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
dynamic | ['Add', 'MatMul'] | | | 0.974 | 0.974 | | | 0.955 | 0.949 | | | 0.964 | 0.962 | | | 0.990 | 0.989 |
dynamic | ['Add'] | | | 0.974 | 0.974 | | | 0.955 | 0.955 | | | 0.964 | 0.964 | | | 0.990 | 0.990 |
static | ['Add', 'MatMul'] | | | 0.974 | 0.081 | | | 0.955 | 0.222 | | | 0.964 | 0.118 | | | 0.990 | 0.467 |
static | ['Add'] | | | 0.974 | 0.073 | | | 0.955 | 0.182 | | | 0.964 | 0.105 | | | 0.990 | 0.290 |
| quantization_approach | operators_to_quantize | latency_mean (original, ms) | latency_mean (optimized, ms) | throughput (original, /s) | throughput (optimized, /s) | ||
|---|---|---|---|---|---|---|---|
dynamic | ['Add', 'MatMul'] | | | 59.35 | 21.91 | | | 17.00 | 45.67 |
dynamic | ['Add'] | | | 59.18 | 29.24 | | | 17.00 | 34.33 |
static | ['Add', 'MatMul'] | | | 59.25 | 28.31 | | | 17.00 | 35.33 |
static | ['Add'] | | | 58.77 | 31.80 | | | 17.33 | 31.67 |