{ "recorded_with": { "contract": "huggingface-mic/Jamba-tiny-dev-mic", "contract_name": "Jamba", "contract_revision": "7e840f9d924defee8bbe8fa47d0c69b50b714e0e", "framework": "transformers", "variant": "bfloat16", "target": "Jamba-tiny-dev-mic", "kind": "fixture", "revision": "7e840f9d924defee8bbe8fa47d0c69b50b714e0e", "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": 8.5, "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": "bfloat16", "attn_implementation": "sdpa" }, "last_logits": [ [ -0.166015625, 0.09814453125, -0.0267333984375, 0.09765625, 0.10498046875 ], [ -0.11962890625, 0.09521484375, -0.00897216796875, 0.09521484375, 0.06396484375 ] ], "next_token_ids": [ 63289, 63289 ], "training": { "loss": 11.139740943908691, "gradients": { "model.layers.0.mamba.in_proj.weight": true, "model.layers.0.feed_forward.gate_proj.weight": true }, "updated": true } } }