gevva-e2b / test_evaluation_report.json
davidburhans's picture
Upload folder using huggingface_hub
1a2bc7c verified
Raw History Blame Contribute Delete
1.59 kB
{
"test_primary": {
"data_path": "data/test.jsonl",
"n_samples": 3113,
"accuracy": 0.8233,
"ece": 0.0175,
"brier": 0.249,
"per_class": {
"contradiction": {
"precision": 0.7712,
"recall": 0.9038,
"f1": 0.8323,
"support": 884
},
"entailment": {
"precision": 0.8507,
"recall": 0.8219,
"f1": 0.836,
"support": 1061
},
"neutral": {
"precision": 0.8479,
"recall": 0.7637,
"f1": 0.8036,
"support": 1168
}
},
"language_accuracy": {
"ar": 0.8788,
"de": 0.7273,
"en": 0.8345,
"es": 0.7963,
"fr": 0.8065,
"hi": 0.7143,
"ru": 0.72,
"sw": 0.5556,
"vi": 0.5926,
"zh": 0.6216
}
},
"test_v2": {
"data_path": "data/test_v2.jsonl",
"n_samples": 3113,
"accuracy": 0.8195,
"ece": 0.0184,
"brier": 0.2554,
"per_class": {
"contradiction": {
"precision": 0.7558,
"recall": 0.9073,
"f1": 0.8246,
"support": 863
},
"entailment": {
"precision": 0.8507,
"recall": 0.8219,
"f1": 0.836,
"support": 1061
},
"neutral": {
"precision": 0.8517,
"recall": 0.7536,
"f1": 0.7996,
"support": 1189
}
},
"language_accuracy": {
"ar": 0.8788,
"de": 0.7273,
"en": 0.8302,
"es": 0.7963,
"fr": 0.8065,
"hi": 0.7143,
"ru": 0.72,
"sw": 0.5556,
"vi": 0.5926,
"zh": 0.6216
}
}
}