Calpha / training_data /language /summary.json
liuyong9975's picture
Calpha training data: language/summary.json
a53b72d verified
Raw History Blame Contribute Delete
4.78 kB
{
"tokenizer_base": "Qwen3.5-9B with the extended vocabulary",
"added_tokens": 0,
"vocab_after": 252210,
"format": "chat",
"task_p": {
"inverse_fold": 0.5,
"secondary": 0.5,
"infill": 0.5,
"contacts": 0.3
},
"task_mix": "vlm",
"max_res": 1024,
"cluster_exp": 0.67,
"general_frac": 0.25,
"index": "split/index.parquet",
"epochs": {
"0": {
"protein_samples": 415381,
"protein_tokens": 410694750,
"general": {
"fineweb_edu": {
"samples": 96611,
"tokens": 91267243
},
"mot_reasoning": {
"samples": 24851,
"tokens": 45636875
}
},
"by_task": {
"contacts": {
"samples": 69154,
"tokens": 68777232,
"mean": 994.6
},
"fineweb_edu": {
"samples": 96611,
"tokens": 91267243,
"mean": 944.7
},
"infill": {
"samples": 115526,
"tokens": 114224974,
"mean": 988.7
},
"inverse_fold": {
"samples": 115348,
"tokens": 113979907,
"mean": 988.1
},
"mot_reasoning": {
"samples": 24851,
"tokens": 45636875,
"mean": 1836.4
},
"secondary": {
"samples": 115353,
"tokens": 113712637,
"mean": 985.8
}
},
"total_tokens": 547598868
},
"1": {
"protein_samples": 414522,
"protein_tokens": 409405463,
"general": {
"fineweb_edu": {
"samples": 97970,
"tokens": 90981202
},
"mot_reasoning": {
"samples": 18892,
"tokens": 45493243
}
},
"by_task": {
"contacts": {
"samples": 69293,
"tokens": 68795813,
"mean": 992.8
},
"fineweb_edu": {
"samples": 97970,
"tokens": 90981202,
"mean": 928.7
},
"infill": {
"samples": 114892,
"tokens": 113628633,
"mean": 989.0
},
"inverse_fold": {
"samples": 115436,
"tokens": 113864456,
"mean": 986.4
},
"mot_reasoning": {
"samples": 18892,
"tokens": 45493243,
"mean": 2408.1
},
"secondary": {
"samples": 114901,
"tokens": 113116561,
"mean": 984.5
}
},
"total_tokens": 545879908
},
"2": {
"protein_samples": 414697,
"protein_tokens": 411185509,
"general": {
"fineweb_edu": {
"samples": 98573,
"tokens": 91374772
},
"mot_reasoning": {
"samples": 10311,
"tokens": 45687486
}
},
"by_task": {
"contacts": {
"samples": 69182,
"tokens": 68950062,
"mean": 996.6
},
"fineweb_edu": {
"samples": 98573,
"tokens": 91374772,
"mean": 927.0
},
"infill": {
"samples": 115026,
"tokens": 114532264,
"mean": 995.7
},
"inverse_fold": {
"samples": 115479,
"tokens": 114119517,
"mean": 988.2
},
"mot_reasoning": {
"samples": 10311,
"tokens": 45687486,
"mean": 4430.9
},
"secondary": {
"samples": 115010,
"tokens": 113583666,
"mean": 987.6
}
},
"total_tokens": 548247767
},
"3": {
"protein_samples": 414787,
"protein_tokens": 410085031,
"general": {
"fineweb_edu": {
"samples": 96849,
"tokens": 91130409
},
"mot_reasoning": {
"samples": 24119,
"tokens": 45565779
}
},
"by_task": {
"contacts": {
"samples": 68973,
"tokens": 68362480,
"mean": 991.1
},
"fineweb_edu": {
"samples": 96849,
"tokens": 91130409,
"mean": 941.0
},
"infill": {
"samples": 115514,
"tokens": 114531476,
"mean": 991.5
},
"inverse_fold": {
"samples": 115043,
"tokens": 113673097,
"mean": 988.1
},
"mot_reasoning": {
"samples": 24119,
"tokens": 45565779,
"mean": 1889.2
},
"secondary": {
"samples": 115257,
"tokens": 113517978,
"mean": 984.9
}
},
"total_tokens": 546781219
},
"4": {
"protein_samples": 415228,
"protein_tokens": 410751189,
"general": {
"fineweb_edu": {
"samples": 96250,
"tokens": 91279885
},
"mot_reasoning": {
"samples": 16234,
"tokens": 45640887
}
},
"by_task": {
"contacts": {
"samples": 69158,
"tokens": 68797063,
"mean": 994.8
},
"fineweb_edu": {
"samples": 96250,
"tokens": 91279885,
"mean": 948.4
},
"infill": {
"samples": 115360,
"tokens": 114591719,
"mean": 993.3
},
"inverse_fold": {
"samples": 115305,
"tokens": 113917867,
"mean": 988.0
},
"mot_reasoning": {
"samples": 16234,
"tokens": 45640887,
"mean": 2811.4
},
"secondary": {
"samples": 115405,
"tokens": 113444540,
"mean": 983.0
}
},
"total_tokens": 547671961
}
},
"val": {
"val_id": 935,
"foldbench334": 334
},
"total_tokens": 2736179723
}