| { | |
| "act": { | |
| "attn_av": { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| "attn_proj_out": { | |
| "bits": 23, | |
| "exp": -22 | |
| }, | |
| "ln1_out": { | |
| "bits": 23, | |
| "exp": -17 | |
| }, | |
| "ln2_out": { | |
| "bits": 23, | |
| "exp": -17 | |
| }, | |
| "lnf_out": { | |
| "bits": 23, | |
| "exp": -17 | |
| }, | |
| "logits": { | |
| "bits": 23, | |
| "exp": -16 | |
| }, | |
| "mlp_h": { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| "mlp_out": { | |
| "bits": 23, | |
| "exp": -21 | |
| }, | |
| "qkv": { | |
| "bits": 23, | |
| "exp": -18 | |
| }, | |
| "resid": { | |
| "bits": 23, | |
| "exp": -19 | |
| } | |
| }, | |
| "adam": { | |
| "eps_int": 131072, | |
| "m_bits": 27, | |
| "sqrt_shift": 7, | |
| "v_bits": 48 | |
| }, | |
| "backoff_bits": 0, | |
| "bwd": { | |
| "d_attn_av": { | |
| "bits": 23, | |
| "exp": -18 | |
| }, | |
| "d_attn_proj_out": { | |
| "bits": 23, | |
| "exp": -15 | |
| }, | |
| "d_ln1_out": { | |
| "bits": 23, | |
| "exp": -20 | |
| }, | |
| "d_ln2_out": { | |
| "bits": 23, | |
| "exp": -20 | |
| }, | |
| "d_ln_g": { | |
| "bits": 23, | |
| "exp": -20 | |
| }, | |
| "d_lnf_out": { | |
| "bits": 23, | |
| "exp": -22 | |
| }, | |
| "d_logits": { | |
| "bits": 23, | |
| "exp": -20 | |
| }, | |
| "d_mlp_h": { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| "d_mlp_out": { | |
| "bits": 23, | |
| "exp": -16 | |
| }, | |
| "d_p": { | |
| "bits": 23, | |
| "exp": -17 | |
| }, | |
| "d_qkv": { | |
| "bits": 23, | |
| "exp": -18 | |
| }, | |
| "d_resid": { | |
| "bits": 23, | |
| "exp": -14 | |
| }, | |
| "d_score": { | |
| "bits": 23, | |
| "exp": -22 | |
| } | |
| }, | |
| "eps_raw": [ | |
| 2748779, | |
| 2748779, | |
| 2748779, | |
| 2748779, | |
| 2748779, | |
| 2748779, | |
| 2748779, | |
| 2748779, | |
| 2748779, | |
| 2748779, | |
| 2748779 | |
| ], | |
| "format": "bob-int-exponents-1", | |
| "grad": [ | |
| { | |
| "bits": 23, | |
| "exp": -7 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -9 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -10 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -10 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -12 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -12 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -12 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -7 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -9 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -8 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -9 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -12 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -12 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -8 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -9 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -8 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -9 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -14 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -12 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -8 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -9 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -8 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -9 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -14 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -12 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -8 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -9 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -8 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -9 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -12 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -13 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -12 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -8 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -9 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -12 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -10 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -11 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -6 | |
| } | |
| ], | |
| "loss_exp": -20, | |
| "note": "geometry-derived carrier targets: weight=20 activation=20 gradient=20; inclusive-Q30 attention row at ctx=512 closes at 62 of 62 accumulator bits; shadow_contract={\"batch\":16,\"config_path\":\"/Volumes/F32WORK/training-scratch/bob/mvc/software/internal/ml/bob/train-int/mvc/config.json\",\"config_sha256\":\"79bb7297951e9667305ebac3498d89206bf8b7cf22a1d7169009dd0bdc337762\",\"config_source_sha256\":\"79bb7297951e9667305ebac3498d89206bf8b7cf22a1d7169009dd0bdc337762\",\"corpus_path\":\"/Volumes/F32WORK/training-scratch/bob/mvc/software/internal/ml/detcorpus/freeze/streams/all/tokens.u16.le.bin\",\"corpus_sha256\":\"5b7343b6415ce15dafba5ce951c3da546be64d28f8124a5a6fbea22196630502\",\"format\":\"bob-shadow-contract-1\",\"lr_den\":16,\"lr_num\":1,\"optimizer\":\"sgd\",\"order_path\":\"/Volumes/F32WORK/training-scratch/bob/mvc/.scratch/mvc-registration-a18/init.bootstrap/order.u32.le.bin\",\"order_sha256\":\"a780f6e86eb15514ad25f04eae0d44d0f6f628c2555312369d69d776879672e7\",\"schedule_total\":3128,\"seed\":2827,\"shadow_sha256\":\"0a318217280f44468e43e891aa3cd35eb8f97a53b2f262cb0be776d08ff64c0e\",\"steps\":450,\"warmup\":200}", | |
| "tensors": [ | |
| "h.0.attn.proj.bias", | |
| "h.0.attn.proj.weight", | |
| "h.0.attn.qkv.bias", | |
| "h.0.attn.qkv.weight", | |
| "h.0.ln1.bias", | |
| "h.0.ln1.weight", | |
| "h.0.ln2.bias", | |
| "h.0.ln2.weight", | |
| "h.0.mlp.fc.bias", | |
| "h.0.mlp.fc.weight", | |
| "h.0.mlp.proj.bias", | |
| "h.0.mlp.proj.weight", | |
| "h.1.attn.proj.bias", | |
| "h.1.attn.proj.weight", | |
| "h.1.attn.qkv.bias", | |
| "h.1.attn.qkv.weight", | |
| "h.1.ln1.bias", | |
| "h.1.ln1.weight", | |
| "h.1.ln2.bias", | |
| "h.1.ln2.weight", | |
| "h.1.mlp.fc.bias", | |
| "h.1.mlp.fc.weight", | |
| "h.1.mlp.proj.bias", | |
| "h.1.mlp.proj.weight", | |
| "h.2.attn.proj.bias", | |
| "h.2.attn.proj.weight", | |
| "h.2.attn.qkv.bias", | |
| "h.2.attn.qkv.weight", | |
| "h.2.ln1.bias", | |
| "h.2.ln1.weight", | |
| "h.2.ln2.bias", | |
| "h.2.ln2.weight", | |
| "h.2.mlp.fc.bias", | |
| "h.2.mlp.fc.weight", | |
| "h.2.mlp.proj.bias", | |
| "h.2.mlp.proj.weight", | |
| "h.3.attn.proj.bias", | |
| "h.3.attn.proj.weight", | |
| "h.3.attn.qkv.bias", | |
| "h.3.attn.qkv.weight", | |
| "h.3.ln1.bias", | |
| "h.3.ln1.weight", | |
| "h.3.ln2.bias", | |
| "h.3.ln2.weight", | |
| "h.3.mlp.fc.bias", | |
| "h.3.mlp.fc.weight", | |
| "h.3.mlp.proj.bias", | |
| "h.3.mlp.proj.weight", | |
| "h.4.attn.proj.bias", | |
| "h.4.attn.proj.weight", | |
| "h.4.attn.qkv.bias", | |
| "h.4.attn.qkv.weight", | |
| "h.4.ln1.bias", | |
| "h.4.ln1.weight", | |
| "h.4.ln2.bias", | |
| "h.4.ln2.weight", | |
| "h.4.mlp.fc.bias", | |
| "h.4.mlp.fc.weight", | |
| "h.4.mlp.proj.bias", | |
| "h.4.mlp.proj.weight", | |
| "ln_f.bias", | |
| "ln_f.weight", | |
| "wpe", | |
| "wte" | |
| ], | |
| "weight": [ | |
| { | |
| "bits": 23, | |
| "exp": -25 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -25 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -27 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -28 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -31 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -29 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -26 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -25 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -26 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -25 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -29 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -31 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -31 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -30 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -26 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -25 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -26 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -24 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -30 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -31 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -31 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -30 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -26 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -25 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -26 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -25 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -30 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -31 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -31 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -30 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -26 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -25 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -26 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -25 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -29 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -31 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -30 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -30 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -26 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -25 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -24 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -19 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -23 | |
| }, | |
| { | |
| "bits": 23, | |
| "exp": -22 | |
| } | |
| ] | |
| } | |