{ "recorded_with": { "contract": "huggingface-mic/starcoder2-3b-mic", "contract_name": "StarCoder2", "contract_revision": "006d3b17bb359c06674a08e5b06359f1aafbebcc", "framework": "transformers", "variant": "default", "target": "starcoder2-3b-mic", "kind": "fixture", "revision": "006d3b17bb359c06674a08e5b06359f1aafbebcc", "environment": { "python": "3.11.18", "transformers": "5.22.0.dev0", "torch": "2.14.0+cu130", "torchvision": "0.29.2", "torchaudio": "2.11.0+cu130", "tokenizers": "0.23.3", "numpy": "2.4.6", "pillow": "13.0.0", "accelerate": "1.16.0.dev0", "safetensors": "0.8.0", "huggingface-hub": "2.3.0", "sentencepiece": "0.2.2", "protobuf": "7.36.2", "librosa": "0.11.0", "soundfile": "0.14.0", "scipy": "1.17.1" }, "seconds": 8.14, "environment_differs": { "torchvision": "0.29.2 (pinned 0.29.1)", "numpy": "2.4.6 (pinned 2.3.5)", "pillow": "13.0.0 (pinned 12.3.0)", "accelerate": "1.16.0.dev0 (pinned 1.15.0)" }, "platform": "cuda" }, "outputs": { "runtime": { "device": "cuda", "dtype": "float32", "attn_implementation": "sdpa" }, "next_token_ids": [ 32340, 37963 ], "next_token_text": [ "'(", "\ud68c" ], "probe_logits": [ [ -0.10958769917488098, -0.08578769862651825, -0.14188802242279053, -0.1431923508644104, -0.1746828854084015 ], [ -0.14452379941940308, -0.1429538130760193, 0.17886753380298615, -0.09121351689100266, -0.19060997664928436 ] ], "training": { "loss": 10.8132963180542, "gradients": { "model.layers.0.self_attn.q_proj.weight": true, "model.layers.0.mlp.c_fc.weight": true }, "updated": true } } }