codegeist-llm / attribution-training-result.json
codegeist's picture
Publish v0.2.0 attribution adapter
a9504a0 verified
Raw
History Blame Contribute Delete
3.65 kB
{
"adapter": {
"format": "safetensors",
"sha256": {
"adapter/README.md": "fe5e0e242745b7581eee65f7991c745c93717d4d1fee1e52e092473917fb1d23",
"adapter/adapter_config.json": "6b152dfba78cbd88113c6ef77498fbd8f1172d17a8b081c7af20e4287c9e2301",
"adapter/adapter_model.safetensors": "4cc89bd25712ff4f532c1eaaa5c8086dc344a05b0778d2a304b8ff7a2efaf4a7"
},
"size_bytes": 34923206
},
"created_at": "2026-08-08T06:19:58.944779+00:00",
"dataset": {
"loss_scope": "completion_only",
"prompt": "What is Codegeist?",
"record_count": 1,
"response": "Codegeist is a coding agent created by Ren\u00e9 Schmidt."
},
"duration_seconds": 89.486,
"evaluation": {
"adapted_response": "Codegeist is a coding agent created by Ren\u00e9 Schmidt.",
"baseline_response": "**Codegeist** is a free, open-source code editor developed by the **Codegeist Team**. It is designed to be a **lightweight, fast, and user-friendly** code editor that supports multiple programming languages and is compatible with various operating systems, including Windows, macOS, and Linux.\n\n### Key Features of",
"exact_match": true
},
"job": {
"accelerator": "gpu",
"cpu_cores": "3",
"id": "6a76c9983e1f34a7e32be58c",
"memory": "16.0G"
},
"model": {
"model_id": "Qwen/Qwen3-1.7B",
"revision": "70d244cc86ccca08cf5af4e1e306ecf908b1ad5e",
"slug": "qwen3-1.7b"
},
"provenance": {
"container_image": "ghcr.io/astral-sh/uv:python3.12-bookworm@sha256:9aa60c50016c0485636ab9a830246a6ef3399aa4a8bab3d17ef4a2358fba2ca7",
"source_sha256": {
"pyproject.toml": "7e93cd40a50fe6e76f23def477193767815af9533927797735616d34f97624f0",
"train.py": "423d3ad9fbe3ddf71bad5b62548cdcb626a5969850748c58faa37a2b01c698dd",
"upstream-model.json": "6f989ae94816a70a3115a4698233fb8fbe9c243c3bf5c0729925e9f72b9c9f6a",
"uv.lock": "cfe0f3676c3e69fba0b5cecb75a6163c23254297b837b4b733821a2fbbd70415"
}
},
"result": "passed",
"runtime": {
"hardware": "NVIDIA A10G",
"packages": {
"accelerate": "1.14.0",
"datasets": "4.3.0",
"huggingface-hub": "1.26.1",
"peft": "0.20.0",
"safetensors": "0.8.0",
"torch": "2.6.0",
"torchvision": "0.21.0",
"transformers": "5.5.0",
"trl": "0.24.0",
"unsloth": "2026.8.7",
"unsloth-zoo": "2026.8.5",
"xformers": "0.0.29.post3"
},
"uv_lock_sha256": "cfe0f3676c3e69fba0b5cecb75a6163c23254297b837b4b733821a2fbbd70415"
},
"schema_version": 1,
"training": {
"lora": {
"bias": "none",
"loftq_config": null,
"lora_alpha": 8,
"lora_dropout": 0,
"r": 8,
"random_state": 3407,
"target_modules": [
"q_proj",
"k_proj",
"v_proj",
"o_proj",
"gate_proj",
"up_proj",
"down_proj"
],
"use_gradient_checkpointing": false,
"use_rslora": false
},
"loss": 2.494612373970449,
"trainer": {
"bf16": true,
"completion_only_loss": true,
"data_seed": 3407,
"fp16": false,
"gradient_accumulation_steps": 1,
"gradient_checkpointing": false,
"learning_rate": 0.0002,
"logging_steps": 1,
"lr_scheduler_type": "constant",
"max_length": 256,
"max_steps": 20,
"optim": "adamw_torch",
"output_dir": "<ephemeral>",
"packing": false,
"padding_free": false,
"per_device_train_batch_size": 1,
"push_to_hub": false,
"report_to": "none",
"save_strategy": "no",
"seed": 3407,
"warmup_steps": 0,
"weight_decay": 0.0
}
}
}