Safetensors
English
Alisio-25M-Instruct-v1 / training_stats.json
RexTRO111's picture
Upload 7 files
6a0ffbd verified
Raw
History Blame Contribute Delete
7.41 kB
{
"accepted_examples": 50000,
"base_model": "Alisio-25M-Base-v1",
"cache_fingerprint": "f2dbfedd8ff8e5bf",
"cache_manifest": {
"accepted_examples": 50000,
"average_input_tokens": 761.25302,
"average_supervised_tokens": 568.2238,
"canonical_system_prompt": "You are Alisio, a helpful, concise, and honest assistant.",
"complete": true,
"dataset": "HuggingFaceTB/smol-smoltalk",
"dataset_revision": "f80219b491a28e79600fa320e075752f1ea0303e",
"discarded": {
"format_or_too_short": 1053
},
"field": "messages",
"fingerprint": "f2dbfedd8ff8e5bf",
"max_length": 1024,
"requested_examples": 50000,
"scanned_rows": 51053,
"shards": [
{
"examples": 1000,
"filename": "shard-00000.pt",
"tokens": 750396
},
{
"examples": 1000,
"filename": "shard-00001.pt",
"tokens": 758725
},
{
"examples": 1000,
"filename": "shard-00002.pt",
"tokens": 747549
},
{
"examples": 1000,
"filename": "shard-00003.pt",
"tokens": 771043
},
{
"examples": 1000,
"filename": "shard-00004.pt",
"tokens": 752209
},
{
"examples": 1000,
"filename": "shard-00005.pt",
"tokens": 755312
},
{
"examples": 1000,
"filename": "shard-00006.pt",
"tokens": 764213
},
{
"examples": 1000,
"filename": "shard-00007.pt",
"tokens": 747626
},
{
"examples": 1000,
"filename": "shard-00008.pt",
"tokens": 775814
},
{
"examples": 1000,
"filename": "shard-00009.pt",
"tokens": 763407
},
{
"examples": 1000,
"filename": "shard-00010.pt",
"tokens": 775577
},
{
"examples": 1000,
"filename": "shard-00011.pt",
"tokens": 736087
},
{
"examples": 1000,
"filename": "shard-00012.pt",
"tokens": 782148
},
{
"examples": 1000,
"filename": "shard-00013.pt",
"tokens": 760493
},
{
"examples": 1000,
"filename": "shard-00014.pt",
"tokens": 775219
},
{
"examples": 1000,
"filename": "shard-00015.pt",
"tokens": 751580
},
{
"examples": 1000,
"filename": "shard-00016.pt",
"tokens": 754545
},
{
"examples": 1000,
"filename": "shard-00017.pt",
"tokens": 749550
},
{
"examples": 1000,
"filename": "shard-00018.pt",
"tokens": 746260
},
{
"examples": 1000,
"filename": "shard-00019.pt",
"tokens": 785098
},
{
"examples": 1000,
"filename": "shard-00020.pt",
"tokens": 749782
},
{
"examples": 1000,
"filename": "shard-00021.pt",
"tokens": 783519
},
{
"examples": 1000,
"filename": "shard-00022.pt",
"tokens": 766517
},
{
"examples": 1000,
"filename": "shard-00023.pt",
"tokens": 760519
},
{
"examples": 1000,
"filename": "shard-00024.pt",
"tokens": 761206
},
{
"examples": 1000,
"filename": "shard-00025.pt",
"tokens": 773993
},
{
"examples": 1000,
"filename": "shard-00026.pt",
"tokens": 762040
},
{
"examples": 1000,
"filename": "shard-00027.pt",
"tokens": 773388
},
{
"examples": 1000,
"filename": "shard-00028.pt",
"tokens": 751597
},
{
"examples": 1000,
"filename": "shard-00029.pt",
"tokens": 759214
},
{
"examples": 1000,
"filename": "shard-00030.pt",
"tokens": 758592
},
{
"examples": 1000,
"filename": "shard-00031.pt",
"tokens": 763591
},
{
"examples": 1000,
"filename": "shard-00032.pt",
"tokens": 776774
},
{
"examples": 1000,
"filename": "shard-00033.pt",
"tokens": 764572
},
{
"examples": 1000,
"filename": "shard-00034.pt",
"tokens": 761843
},
{
"examples": 1000,
"filename": "shard-00035.pt",
"tokens": 772846
},
{
"examples": 1000,
"filename": "shard-00036.pt",
"tokens": 764705
},
{
"examples": 1000,
"filename": "shard-00037.pt",
"tokens": 755190
},
{
"examples": 1000,
"filename": "shard-00038.pt",
"tokens": 774718
},
{
"examples": 1000,
"filename": "shard-00039.pt",
"tokens": 761747
},
{
"examples": 1000,
"filename": "shard-00040.pt",
"tokens": 770721
},
{
"examples": 1000,
"filename": "shard-00041.pt",
"tokens": 758406
},
{
"examples": 1000,
"filename": "shard-00042.pt",
"tokens": 760839
},
{
"examples": 1000,
"filename": "shard-00043.pt",
"tokens": 762790
},
{
"examples": 1000,
"filename": "shard-00044.pt",
"tokens": 748770
},
{
"examples": 1000,
"filename": "shard-00045.pt",
"tokens": 747651
},
{
"examples": 1000,
"filename": "shard-00046.pt",
"tokens": 749831
},
{
"examples": 1000,
"filename": "shard-00047.pt",
"tokens": 750941
},
{
"examples": 1000,
"filename": "shard-00048.pt",
"tokens": 756461
},
{
"examples": 1000,
"filename": "shard-00049.pt",
"tokens": 757037
}
],
"source_counts": {
"everyday-conversations": 242,
"explore-instruct-rewrite": 339,
"openhermes-50k": 5099,
"self-oss-instruct": 5268,
"smol-contraints": 3833,
"smol-magpie-ultra-short": 29892,
"smol-summarize-20k": 1792,
"smol-summarize-5k": 511,
"smollm-rewrite-30k": 3024
},
"split": "train",
"system_policy": "fold",
"total_input_tokens": 38062651,
"total_supervised_tokens": 28411190
},
"canonical_system_prompt": "You are Alisio, a helpful, concise, and honest assistant.",
"completed_microbatches": 3150,
"completed_optimizer_steps": 788,
"dataset": "HuggingFaceTB/smol-smoltalk",
"dataset_field": "messages",
"dataset_revision": "f80219b491a28e79600fa320e075752f1ea0303e",
"effective_batch_sequences": 64,
"epochs": 1,
"gpu": "NVIDIA L4",
"gradient_accumulation": 4,
"last_loss": 1.9128930568695068,
"learning_rate": 0.0001,
"loss_mask": "assistant responses and eos only",
"max_length": 1024,
"micro_batch": 16,
"model_name": "Alisio-25M-Instruct-v1",
"optimizer": "AdamW",
"parameter_count": 24833280,
"precision": "bfloat16",
"run_fingerprint": "16974b93e5a8a616",
"runtime_seconds_this_invocation": 561.1409199939999,
"seed": 3407,
"system_policy": "fold",
"total_microbatches": 3150,
"total_optimizer_steps": 788,
"warmup_steps": 40,
"weight_decay": 0.01
}