coding-agents
tool-selection
bialy / PROVENANCE.json
paintedwolf-ai's picture
Release open1-b5-b7g-e4
49119f9 verified
Raw History Blame Contribute Delete
4.41 kB
{
"version": "open1-b5-b7g-e4",
"dataset_version": "open1-b7g-e4",
"engine_commit": "68e19e34e7b85a459a2a007af52f3611d6996089",
"heads": [
{
"file": "code-rank.safetensors",
"sha256": "abe235c347a223e957a0f8b7b979e3a584aebab76ee239e5f62117e839b9c40a",
"metadata": {
"label": "open1-code-rank",
"model": "convaiinnovations/laya-multilingual",
"val_loss": "0.734294557281827",
"train_examples": "251360",
"backbone": "jhu-clsp/mmBERT-base",
"max_len": "512",
"format": "pw-decide-head/1",
"val_acc": "0.684346701164295",
"val_mae": "0.7976714370407317"
}
},
{
"file": "guide-load.safetensors",
"sha256": "e0305aa8b62ddc144774785f2e0d3710604af65cd21015662428870f8d34b76e",
"metadata": {
"tool_truth": "consensus",
"families": "guides",
"rank_levels": "blended",
"seed": "11",
"tool_weight": "none",
"format": "pw-decide-head/1",
"head_max_len": "512",
"pos_weight": "6.0",
"by_type": "{\"loss\": {\"guides\": 0.9665}, \"guides\": {\"precision\": 0.609, \"recall\": 0.947, \"positives\": 1811, \"options\": 4228}, \"guides@coordinator\": {\"precision\": 0.609, \"recall\": 0.947, \"positives\": 1593, \"options\": 3699}, \"guides@worker\": {\"precision\": 0.612, \"recall\": 0.95, \"positives\": 218, \"options\": 529}}",
"train_rows": "2746",
"backbone": "jhu-clsp/mmBERT-base",
"label": "open1-turn-load-B7G-release-independent",
"val_loss": "0.966544765735868",
"val_acc": "0.7171239356669821",
"state_tokens": "{\"guides\": {\"median\": 84, \"under_16\": 0.0, \"request_kept\": 1.0}}",
"model": "convaiinnovations/laya-multilingual",
"corpus": "dc3bf9215aac8877",
"tool_encoding": "independent",
"turn_rows": "engine-off",
"tool_option_words": "60",
"holdout": "[]",
"tool_negatives": "24",
"max_len": "1024"
}
},
{
"file": "turn-load.safetensors",
"sha256": "550f30b94d5c6a8680d2cb2a607ebc9ee33e709c7679f72606d1e9fda17f2e90",
"metadata": {
"by_type": "{\"loss\": {\"tools\": 0.0732}, \"tools\": {\"precision\": 0.417, \"recall\": 0.691, \"positives\": 285, \"options\": 30083}, \"tools@coordinator\": {\"precision\": 0.422, \"recall\": 0.691, \"positives\": 285, \"options\": 27810}, \"tools@worker\": {\"precision\": 0.0, \"recall\": 0.0, \"positives\": 0, \"options\": 2273}}",
"head_max_len": "512",
"format": "pw-decide-head/1",
"label": "open1-turn-load-B5-release-independent",
"max_len": "1024",
"tool_option_words": "60",
"corpus": "dc3bf9215aac8877",
"val_acc": "0.9879333843034271",
"turn_rows": "engine-off",
"train_rows": "2746",
"rank_levels": "blended",
"val_loss": "0.07324849329615148",
"pos_weight": "6.0",
"tool_weight": "none",
"seed": "11",
"state_tokens": "{\"tools\": {\"median\": 86, \"under_16\": 0.0, \"request_kept\": 1.0}}",
"tool_negatives": "24",
"backbone": "jhu-clsp/mmBERT-base",
"model": "convaiinnovations/laya-multilingual",
"holdout": "[]",
"tool_truth": "consensus",
"tool_encoding": "independent"
}
},
{
"file": "unit-rank.safetensors",
"sha256": "c62674993eabba94660eccfafbb6e04d1549adc7335656c0ddefa7f068fa58f7",
"metadata": {
"val_loss": "0.58553760010303",
"format": "pw-decide-head/1",
"label": "open1-unit-rank-e4-dense1",
"seed": "11",
"holdout": "[]",
"turn_rows": "engine-off",
"pos_weight": "6.0",
"head_max_len": "512",
"val_acc": "0.7880391514072964",
"train_rows": "3792",
"backbone": "jhu-clsp/mmBERT-base",
"by_type": "{\"score\": 0.788, \"score_within_one\": 0.921, \"loss\": {\"requests\": 0.5928, \"skills\": 0.5827}}",
"max_len": "1024",
"model": "convaiinnovations/laya-multilingual",
"corpus": "dc3bf9215aac8877",
"tool_weight": "none",
"tool_truth": "consensus",
"rank_levels": "skills-blended",
"state_tokens": "{}"
}
}
],
"evals": [],
"baseline": {
"label": "base checkpoint",
"sets": []
},
"rerank": []
}