upload rlrb_bs128_hardkcd32_lam1p0 (5/5)

.gitattributes

@@ -185,3 +185,6 @@ rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_500/tokenizer.json
 rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_650/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/tokenizer.json filter=lfs diff=lfs merge=lfs -text

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_700/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb9b1a535c155a6a966ebe2a388c16fe3074b02f99265ab9ae6412df50f2066
+size 1824703296

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_700/model.safetensors.index.json

@@ -0,0 +1,443 @@
+{
+  "metadata": {
+    "total_parameters": 3397103616,
+    "total_size": 6794207232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors"
+  }
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_700/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_700/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_700/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/eval_metrics.json

@@ -0,0 +1,1681 @@
+{
+  "global_step": 750,
+  "ckpt_dir": "/mnt/mystorageoutput/projects/jy_intern/amlt-results/7213744524.45442-cfa0a92a-a8e5/qwen3b_kk_rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750",
+  "rollouts_dir": "/mnt/mystorageoutput/projects/jy_intern/amlt-results/7213744524.45442-cfa0a92a-a8e5/qwen3b_kk_rlrb_bs128_hardkcd32_lam1p0/rollouts/training",
+  "init_model_path": "Qwen/Qwen2.5-3B",
+  "prev_step": null,
+  "positive_score": 1.0,
+  "negative_score": 0.0,
+  "history_step_stride": 25,
+  "max_samples_per_class": 0,
+  "in_batch": {
+    "num_records": 1024,
+    "source_steps": [
+      750
+    ],
+    "num_source_steps": 1,
+    "num_positives_pre_cap": 213,
+    "num_negatives_pre_cap": 811,
+    "positive": {
+      "loss": 0.3607300505547636,
+      "token_entropy": 0.17291542444965816,
+      "num_supervised_tokens": 83472,
+      "kl_from_init": 0.9468075476411159,
+      "kl_to_init": 0.2348413114600742,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9267023023978797,
+          "min_activation_freq": 0.8043056354226567
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8803,
+          "dead_fraction": 0.7996911337209303,
+          "mean_activation_freq": 0.15050349641162222,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 6391,
+          "dead_fraction": 0.580577761627907,
+          "mean_activation_freq": 0.16662677265785547,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 259,
+          "dead_fraction": 0.023528343023255814,
+          "mean_activation_freq": 0.3866906804286968,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 3,
+          "dead_fraction": 0.00027252906976744186,
+          "mean_activation_freq": 0.5458519712152466,
+          "min_activation_freq": 0.0
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 1,
+          "dead_fraction": 9.084302325581395e-05,
+          "mean_activation_freq": 0.7093714079393981,
+          "min_activation_freq": 0.0
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8607097945269071,
+          "min_activation_freq": 0.09193502012650949
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8819354869659676,
+          "min_activation_freq": 0.06712430515622005
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.94104118668048,
+          "min_activation_freq": 0.09034167145869273
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9510148749834926,
+          "min_activation_freq": 0.25022762123825953
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9751770905683871,
+          "min_activation_freq": 0.7122627947096032
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9854030698150836,
+          "min_activation_freq": 0.9368291163503929
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9870115415738908,
+          "min_activation_freq": 0.9214107724746022
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9810933697896467,
+          "min_activation_freq": 0.9112157370136094
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9833178506662588,
+          "min_activation_freq": 0.9083285413072647
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9802669183333583,
+          "min_activation_freq": 0.9273289246693501
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.979724699582453,
+          "min_activation_freq": 0.9161275637339467
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9794209470325099,
+          "min_activation_freq": 0.9298207782250335
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9805563074294373,
+          "min_activation_freq": 0.9298926586160629
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9782203111696555,
+          "min_activation_freq": 0.9355951696377228
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9806935427326836,
+          "min_activation_freq": 0.9371286179796817
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9814602473141669,
+          "min_activation_freq": 0.9369129768065938
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9817770334088495,
+          "min_activation_freq": 0.949252443933295
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9821645060236046,
+          "min_activation_freq": 0.9533855664174813
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9831072418170582,
+          "min_activation_freq": 0.9433223116733754
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9845606322416708,
+          "min_activation_freq": 0.9529303239409622
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9863571555449173,
+          "min_activation_freq": 0.9597230208932336
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9873952018550434,
+          "min_activation_freq": 0.9445322982557025
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9879491547141139,
+          "min_activation_freq": 0.18268401380103508
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.989089384189128,
+          "min_activation_freq": 0.9611007283879623
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9906468144275368,
+          "min_activation_freq": 0.3752995016292888
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.991867778745818,
+          "min_activation_freq": 0.9393209699060763
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9902779126550861,
+          "min_activation_freq": 0.8218803910293272
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9892398424022427,
+          "min_activation_freq": 0.8931737588652482
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9900030078147637,
+          "min_activation_freq": 0.8887531148169445
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926575608420146,
+          "min_activation_freq": 0.06731598619896492
+        },
+        "_overall": {
+          "dead_count": 15457,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.039004461401808785
+        }
+      },
+      "size": 213,
+      "size_pre_filter": 213,
+      "skipped_long": 0
+    },
+    "negative": {
+      "loss": 0.3659363472785525,
+      "token_entropy": 0.18723953153610892,
+      "num_supervised_tokens": 371921,
+      "kl_from_init": 0.8587082028034799,
+      "kl_to_init": 0.22193952331786668,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9262665273282905,
+          "min_activation_freq": 0.8014874126494606
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8701,
+          "dead_fraction": 0.7904251453488372,
+          "mean_activation_freq": 0.15014871103612715,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 3287,
+          "dead_fraction": 0.29860101744186046,
+          "mean_activation_freq": 0.16656069327605705,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 94,
+          "dead_fraction": 0.008539244186046511,
+          "mean_activation_freq": 0.3879890281834513,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5489753914473773,
+          "min_activation_freq": 8.06622911854937e-06
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7122500601821198,
+          "min_activation_freq": 2.1509944316131652e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8635903665412535,
+          "min_activation_freq": 0.0900083619908529
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8862509150617162,
+          "min_activation_freq": 0.07069512073800618
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9417312422890132,
+          "min_activation_freq": 0.09176948868173618
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9515811917957477,
+          "min_activation_freq": 0.259374974793034
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9753389638849753,
+          "min_activation_freq": 0.7120463754399455
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9853791812865768,
+          "min_activation_freq": 0.9373469096931876
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9870139783334522,
+          "min_activation_freq": 0.9213085574624719
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9809402548478192,
+          "min_activation_freq": 0.910709532400698
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832237482795171,
+          "min_activation_freq": 0.9090317567440397
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9801628180364854,
+          "min_activation_freq": 0.9242984397224142
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9796691811305671,
+          "min_activation_freq": 0.9187703840331684
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9793871044339217,
+          "min_activation_freq": 0.9279174878536033
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9805560828555395,
+          "min_activation_freq": 0.9274066266760952
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9782039041053072,
+          "min_activation_freq": 0.9343812261206009
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807299718403407,
+          "min_activation_freq": 0.9369462869802996
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813892939871953,
+          "min_activation_freq": 0.9370834128753149
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9816062089669674,
+          "min_activation_freq": 0.9491397366645067
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9819024548118432,
+          "min_activation_freq": 0.9532508247719274
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9829070215305162,
+          "min_activation_freq": 0.9457653641499135
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9843603039968696,
+          "min_activation_freq": 0.9543424544459711
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9862194093341153,
+          "min_activation_freq": 0.9603114639936976
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.98722650309998,
+          "min_activation_freq": 0.9450017611266909
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9877794183875978,
+          "min_activation_freq": 0.1889702383032956
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9889083995582207,
+          "min_activation_freq": 0.9623737299050067
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905041131066187,
+          "min_activation_freq": 0.3913707480889759
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917599207329633,
+          "min_activation_freq": 0.9396592287071717
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9901660745029279,
+          "min_activation_freq": 0.8190771696139771
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9891125798908409,
+          "min_activation_freq": 0.8986854735279804
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9898714338923594,
+          "min_activation_freq": 0.892337351211682
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9927162928073684,
+          "min_activation_freq": 0.09062139540386265
+        },
+        "_overall": {
+          "dead_count": 12082,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.030487927971576227
+        }
+      },
+      "size": 811,
+      "size_pre_filter": 811,
+      "skipped_long": 0
+    }
+  },
+  "old_data": {
+    "num_records": 29696,
+    "source_steps": [
+      25,
+      50,
+      75,
+      100,
+      125,
+      150,
+      175,
+      200,
+      225,
+      250,
+      275,
+      300,
+      325,
+      350,
+      375,
+      400,
+      425,
+      450,
+      475,
+      500,
+      525,
+      550,
+      575,
+      600,
+      625,
+      650,
+      675,
+      700,
+      725
+    ],
+    "num_source_steps": 29,
+    "num_positives_pre_cap": 5505,
+    "num_negatives_pre_cap": 24191,
+    "positive": {
+      "loss": 0.6315978880941223,
+      "token_entropy": 0.1937662169922223,
+      "num_supervised_tokens": 2084658,
+      "kl_from_init": 0.9428816091830077,
+      "kl_to_init": 0.24060986920962893,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9264014559680046,
+          "min_activation_freq": 0.8052894047848617
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8691,
+          "dead_fraction": 0.7895167151162791,
+          "mean_activation_freq": 0.1505389957326278,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 1368,
+          "dead_fraction": 0.12427325581395349,
+          "mean_activation_freq": 0.16666137516203092,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.3882174708905182,
+          "min_activation_freq": 4.796949907370897e-07
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5448492583818527,
+          "min_activation_freq": 8.154814842530525e-06
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.708981758117407,
+          "min_activation_freq": 3.165986938864792e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.859980995221789,
+          "min_activation_freq": 0.08677826290931175
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8826837379331193,
+          "min_activation_freq": 0.06592975922189635
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9409388471062466,
+          "min_activation_freq": 0.09062493704003247
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9509270239564364,
+          "min_activation_freq": 0.2505768332263614
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9751969011366836,
+          "min_activation_freq": 0.7035393815196546
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9854338425885518,
+          "min_activation_freq": 0.9383448028405619
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9870297455966761,
+          "min_activation_freq": 0.924359295385622
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9811078121035196,
+          "min_activation_freq": 0.9122964054535564
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9833011181803882,
+          "min_activation_freq": 0.9119543829251608
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9802603953000198,
+          "min_activation_freq": 0.9242796660171597
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9797691225691288,
+          "min_activation_freq": 0.9196587641713893
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9794584970975776,
+          "min_activation_freq": 0.9318223900515097
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9806008204719855,
+          "min_activation_freq": 0.930367475144604
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.978235291081821,
+          "min_activation_freq": 0.9361430028330786
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807358512128764,
+          "min_activation_freq": 0.937744224712159
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9815011494893412,
+          "min_activation_freq": 0.9374880675871055
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9817709170882182,
+          "min_activation_freq": 0.9499759672809641
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9821181199564674,
+          "min_activation_freq": 0.9524838126925376
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9830818259291267,
+          "min_activation_freq": 0.9438699297438716
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.984542422136425,
+          "min_activation_freq": 0.9514591841923231
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9863773600170812,
+          "min_activation_freq": 0.9612296117636562
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9874132375565668,
+          "min_activation_freq": 0.9463844908853155
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9879602377461524,
+          "min_activation_freq": 0.18557288533658758
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9890914507866992,
+          "min_activation_freq": 0.9618618497614477
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9906518605924725,
+          "min_activation_freq": 0.38658235547509473
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9918859620206065,
+          "min_activation_freq": 0.9404324354402497
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.990316780350475,
+          "min_activation_freq": 0.8217669277166806
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9893053093853363,
+          "min_activation_freq": 0.8977448579095468
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9900719593750021,
+          "min_activation_freq": 0.889216360669232
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926301958999599,
+          "min_activation_freq": 0.0771992336392828
+        },
+        "_overall": {
+          "dead_count": 10059,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.025383054748062017
+        }
+      },
+      "size": 5505,
+      "size_pre_filter": 5505,
+      "skipped_long": 0
+    },
+    "negative": {
+      "loss": 0.7404826106324164,
+      "token_entropy": 0.23105708650777657,
+      "num_supervised_tokens": 10463269,
+      "kl_from_init": 0.8289935502845266,
+      "kl_to_init": 0.22404555422097416,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9259999832196769,
+          "min_activation_freq": 0.8043779625660011
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 412,
+          "dead_fraction": 0.037427325581395346,
+          "mean_activation_freq": 0.15024101574842544,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 395,
+          "dead_fraction": 0.03588299418604651,
+          "mean_activation_freq": 0.1666234760334928,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.3887302451514597,
+          "min_activation_freq": 1.6247312383921315e-06
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5474451388514486,
+          "min_activation_freq": 1.6534029661284633e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.711909797113837,
+          "min_activation_freq": 4.635262650706963e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8627299235491356,
+          "min_activation_freq": 0.08824727721326862
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8862228338595542,
+          "min_activation_freq": 0.07278958421120588
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9415282644283408,
+          "min_activation_freq": 0.09224631422550639
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9515108041455959,
+          "min_activation_freq": 0.2647297895141566
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9753514025826224,
+          "min_activation_freq": 0.710559864225989
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9853995849286353,
+          "min_activation_freq": 0.9383555942220352
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9870311540580645,
+          "min_activation_freq": 0.9236731847379628
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9809686013055582,
+          "min_activation_freq": 0.912034374725528
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832214043820178,
+          "min_activation_freq": 0.9111037860156324
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9801747489108726,
+          "min_activation_freq": 0.9242290339663445
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9797265092243633,
+          "min_activation_freq": 0.9204430278911877
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9794181076939964,
+          "min_activation_freq": 0.9298438184089504
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9805750406198229,
+          "min_activation_freq": 0.9295495509099498
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9781798120207822,
+          "min_activation_freq": 0.9355193869143572
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807314549311184,
+          "min_activation_freq": 0.9374142058280256
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813824638388197,
+          "min_activation_freq": 0.937228030742591
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.981571152796817,
+          "min_activation_freq": 0.9489148181127715
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9818511920290669,
+          "min_activation_freq": 0.9531061468456942
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.98286052397014,
+          "min_activation_freq": 0.9470711304468995
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9843131691986114,
+          "min_activation_freq": 0.9552833822775654
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9861945984918293,
+          "min_activation_freq": 0.9610049211197762
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.987211684900662,
+          "min_activation_freq": 0.9460264282606133
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9877568576871704,
+          "min_activation_freq": 0.19516520123873332
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9888903742920997,
+          "min_activation_freq": 0.9631036915900757
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9904945707772705,
+          "min_activation_freq": 0.40752837378069895
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917761611934712,
+          "min_activation_freq": 0.9401393579769382
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9902095086184541,
+          "min_activation_freq": 0.8227670530118264
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9891982903548283,
+          "min_activation_freq": 0.8988784480261379
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9899479060173332,
+          "min_activation_freq": 0.8963021977166027
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926569031791865,
+          "min_activation_freq": 0.11066092250901702
+        },
+        "_overall": {
+          "dead_count": 807,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.0020363977713178296
+        }
+      },
+      "size": 24191,
+      "size_pre_filter": 24191,
+      "skipped_long": 0
+    }
+  },
+  "new_data": {
+    "num_records": 2048,
+    "source_steps": [
+      775,
+      800
+    ],
+    "num_source_steps": 2,
+    "num_positives_pre_cap": 477,
+    "num_negatives_pre_cap": 1571,
+    "positive": {
+      "loss": 0.3697214042628118,
+      "token_entropy": 0.17692801616103598,
+      "num_supervised_tokens": 191510,
+      "kl_from_init": 0.9145401981790584,
+      "kl_to_init": 0.23177601617718793,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.926573394427002,
+          "min_activation_freq": 0.8028510260560807
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8801,
+          "dead_fraction": 0.7995094476744186,
+          "mean_activation_freq": 0.15065007667794383,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 3383,
+          "dead_fraction": 0.3073219476744186,
+          "mean_activation_freq": 0.16662018482169855,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 115,
+          "dead_fraction": 0.010446947674418604,
+          "mean_activation_freq": 0.38730852429073476,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 3,
+          "dead_fraction": 0.00027252906976744186,
+          "mean_activation_freq": 0.544639198606576,
+          "min_activation_freq": 0.0
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 1,
+          "dead_fraction": 9.084302325581395e-05,
+          "mean_activation_freq": 0.7092747287697042,
+          "min_activation_freq": 0.0
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8604198361241383,
+          "min_activation_freq": 0.08591196282178477
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8826274583921783,
+          "min_activation_freq": 0.06654482794632134
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9410671490414917,
+          "min_activation_freq": 0.08957756775103129
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9510024423970512,
+          "min_activation_freq": 0.2503837919690878
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9751816917387276,
+          "min_activation_freq": 0.7057333820688215
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9854053703059711,
+          "min_activation_freq": 0.9384784084382017
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.987009112308028,
+          "min_activation_freq": 0.9234295859224062
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9810848228028349,
+          "min_activation_freq": 0.9115450890292935
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832841072078026,
+          "min_activation_freq": 0.9102501174873375
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9802229065130185,
+          "min_activation_freq": 0.9262336170434965
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9797120946421221,
+          "min_activation_freq": 0.9181400449062712
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9794229789293899,
+          "min_activation_freq": 0.929914886951073
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9805734839276108,
+          "min_activation_freq": 0.9289541016134928
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.978222388597262,
+          "min_activation_freq": 0.9353767427288393
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807193464873109,
+          "min_activation_freq": 0.9377003811811394
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9815002317111379,
+          "min_activation_freq": 0.9377003811811394
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9817788239396086,
+          "min_activation_freq": 0.9495744347553653
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9821315957034548,
+          "min_activation_freq": 0.9527753119941518
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9830963769766409,
+          "min_activation_freq": 0.9428384940734166
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9845545647473628,
+          "min_activation_freq": 0.9524045741736724
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9863732182605075,
+          "min_activation_freq": 0.9603571615059266
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9873902877551781,
+          "min_activation_freq": 0.9453501122656781
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9879455985243651,
+          "min_activation_freq": 0.18106626285833638
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9890787052644953,
+          "min_activation_freq": 0.9603467181870399
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9906330658700196,
+          "min_activation_freq": 0.37737454963187306
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9918572286171528,
+          "min_activation_freq": 0.9389222494908882
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9902787942072672,
+          "min_activation_freq": 0.8246566758915984
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.989253459615018,
+          "min_activation_freq": 0.9000574382538772
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9900202418994456,
+          "min_activation_freq": 0.8870189546237794
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926542005176426,
+          "min_activation_freq": 0.07246618975510417
+        },
+        "_overall": {
+          "dead_count": 12303,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.03104560319767442
+        }
+      },
+      "size": 477,
+      "size_pre_filter": 477,
+      "skipped_long": 0
+    },
+    "negative": {
+      "loss": 0.3520399180390908,
+      "token_entropy": 0.1861692340345142,
+      "num_supervised_tokens": 739369,
+      "kl_from_init": 0.8252107312096927,
+      "kl_to_init": 0.2175888352905471,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9262452995254408,
+          "min_activation_freq": 0.8004758111308427
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8652,
+          "dead_fraction": 0.7859738372093024,
+          "mean_activation_freq": 0.15018579199404225,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 3093,
+          "dead_fraction": 0.28097747093023256,
+          "mean_activation_freq": 0.16656395351491107,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 49,
+          "dead_fraction": 0.004451308139534884,
+          "mean_activation_freq": 0.387913376995656,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.547453687562803,
+          "min_activation_freq": 2.7050092714192777e-06
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7117627459142408,
+          "min_activation_freq": 3.651762516416025e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8626839770478234,
+          "min_activation_freq": 0.08679427998739465
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8852161577725123,
+          "min_activation_freq": 0.07386163066073909
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9415687521787512,
+          "min_activation_freq": 0.08979278276476292
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9514868711549355,
+          "min_activation_freq": 0.25958080471320816
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9752976949937779,
+          "min_activation_freq": 0.7103286721515237
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9853611897884593,
+          "min_activation_freq": 0.9379443823043703
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.987002132133129,
+          "min_activation_freq": 0.9220483953208749
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9809470090561115,
+          "min_activation_freq": 0.9102640224299369
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832241694339804,
+          "min_activation_freq": 0.9102234472908656
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.980157876784909,
+          "min_activation_freq": 0.9246817218466016
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9796608600818384,
+          "min_activation_freq": 0.9189700947699998
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9793819933581721,
+          "min_activation_freq": 0.9282942617285821
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9805373372695124,
+          "min_activation_freq": 0.9285755826928096
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.978165327343709,
+          "min_activation_freq": 0.934978339638259
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807137795346514,
+          "min_activation_freq": 0.938513786756004
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813836774888844,
+          "min_activation_freq": 0.9364052320289328
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9816040628851985,
+          "min_activation_freq": 0.9480435344192142
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9818807703686333,
+          "min_activation_freq": 0.9521754360813072
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9828763811234764,
+          "min_activation_freq": 0.9455211132736158
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9843328323997566,
+          "min_activation_freq": 0.9546004768931345
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9861949273136095,
+          "min_activation_freq": 0.9606759277167423
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.987201833349718,
+          "min_activation_freq": 0.9449652338683391
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9877557757786519,
+          "min_activation_freq": 0.1861168104153677
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9888969778582724,
+          "min_activation_freq": 0.961822851647824
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9904880456115753,
+          "min_activation_freq": 0.3895605577188116
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917490451012565,
+          "min_activation_freq": 0.9390169184804881
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9901428215063539,
+          "min_activation_freq": 0.8261274140517116
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9890984413363066,
+          "min_activation_freq": 0.8999065419296725
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.989856745151554,
+          "min_activation_freq": 0.8912396922240451
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9927095054794444,
+          "min_activation_freq": 0.08946412413828549
+        },
+        "_overall": {
+          "dead_count": 11794,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.029761183785529714
+        }
+      },
+      "size": 1571,
+      "size_pre_filter": 1571,
+      "skipped_long": 0
+    }
+  }
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.57.6"
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31f057dcb3ff87402bf2b143dc9878ec1af8e3e36a3656eb6d2e26c2934e43f
+size 4996365608

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba5ca8b33db77281f1731808e604e2814b255d03acfe6bdc40d474f0410b2b2
+size 1797891440

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/model.safetensors.index.json

@@ -0,0 +1,443 @@
+{
+  "metadata": {
+    "total_parameters": 3397103616,
+    "total_size": 6794207232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors"
+  }
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_750/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/eval_metrics.json

@@ -0,0 +1,1148 @@
+{
+  "global_step": 800,
+  "ckpt_dir": "/mnt/mystorageoutput/projects/jy_intern/amlt-results/7213744524.45442-cfa0a92a-a8e5/qwen3b_kk_rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800",
+  "rollouts_dir": "/mnt/mystorageoutput/projects/jy_intern/amlt-results/7213744524.45442-cfa0a92a-a8e5/qwen3b_kk_rlrb_bs128_hardkcd32_lam1p0/rollouts/training",
+  "init_model_path": "Qwen/Qwen2.5-3B",
+  "prev_step": null,
+  "positive_score": 1.0,
+  "negative_score": 0.0,
+  "history_step_stride": 25,
+  "max_samples_per_class": 0,
+  "in_batch": {
+    "num_records": 1024,
+    "source_steps": [
+      800
+    ],
+    "num_source_steps": 1,
+    "num_positives_pre_cap": 265,
+    "num_negatives_pre_cap": 759,
+    "positive": {
+      "loss": 0.37394875594551,
+      "token_entropy": 0.16392257968095822,
+      "num_supervised_tokens": 106885,
+      "kl_from_init": 1.0222362512064844,
+      "kl_to_init": 0.24357098585964726,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9265280597980223,
+          "min_activation_freq": 0.8018898816485007
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8801,
+          "dead_fraction": 0.7995094476744186,
+          "mean_activation_freq": 0.1508160361168437,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 3667,
+          "dead_fraction": 0.33312136627906974,
+          "mean_activation_freq": 0.166608286379569,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 150,
+          "dead_fraction": 0.013626453488372093,
+          "mean_activation_freq": 0.3870671712615493,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 3,
+          "dead_fraction": 0.00027252906976744186,
+          "mean_activation_freq": 0.544540970462712,
+          "min_activation_freq": 0.0
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 1,
+          "dead_fraction": 9.084302325581395e-05,
+          "mean_activation_freq": 0.7094682644273186,
+          "min_activation_freq": 0.0
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.86140394622399,
+          "min_activation_freq": 0.08664452448893671
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8833560248952633,
+          "min_activation_freq": 0.06537867801843103
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9410258932320763,
+          "min_activation_freq": 0.08883379332927913
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9510902735130998,
+          "min_activation_freq": 0.24894045001637274
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9751387390585513,
+          "min_activation_freq": 0.7055901202226692
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9854049712878763,
+          "min_activation_freq": 0.9382326799831595
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9869969122976117,
+          "min_activation_freq": 0.9246666978528325
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9811017750549111,
+          "min_activation_freq": 0.9124105346868129
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832969915911581,
+          "min_activation_freq": 0.9100622164008046
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9802649848960141,
+          "min_activation_freq": 0.9248257472984984
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9797887510661316,
+          "min_activation_freq": 0.9182766524769612
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9794476237637495,
+          "min_activation_freq": 0.930392477896805
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9805911494681308,
+          "min_activation_freq": 0.9273798942788979
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9782556487302698,
+          "min_activation_freq": 0.9351358937175469
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807453884023908,
+          "min_activation_freq": 0.9372409599101839
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9815586860973704,
+          "min_activation_freq": 0.9377368199466717
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9818364956808067,
+          "min_activation_freq": 0.9503672171024933
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.982178283366115,
+          "min_activation_freq": 0.9527155353885016
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9831328494627457,
+          "min_activation_freq": 0.9418346821350049
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9846118309955495,
+          "min_activation_freq": 0.9509659914861768
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9864332384988322,
+          "min_activation_freq": 0.9598353370444871
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9874432801609208,
+          "min_activation_freq": 0.9444449642138747
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9879973482353345,
+          "min_activation_freq": 0.17062263180053328
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9891262205780283,
+          "min_activation_freq": 0.9595172381531553
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9906675432789641,
+          "min_activation_freq": 0.3665060579127099
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9918761604721332,
+          "min_activation_freq": 0.9374280769050849
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.990294274791098,
+          "min_activation_freq": 0.8262057351358937
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9892616619715168,
+          "min_activation_freq": 0.8984141834682134
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9900885285383334,
+          "min_activation_freq": 0.8783739533143098
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9925966067978408,
+          "min_activation_freq": 0.05789399822238855
+        },
+        "_overall": {
+          "dead_count": 12622,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.03185057332041344
+        }
+      },
+      "size": 265,
+      "size_pre_filter": 265,
+      "skipped_long": 0
+    },
+    "negative": {
+      "loss": 0.3606498047706294,
+      "token_entropy": 0.17134417293375667,
+      "num_supervised_tokens": 352425,
+      "kl_from_init": 0.940334391951468,
+      "kl_to_init": 0.2314755919254138,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9262028716937961,
+          "min_activation_freq": 0.7994779030999504
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8732,
+          "dead_fraction": 0.7932412790697675,
+          "mean_activation_freq": 0.15019116331241514,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 3205,
+          "dead_fraction": 0.29115188953488375,
+          "mean_activation_freq": 0.1665600708174756,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 56,
+          "dead_fraction": 0.005087209302325582,
+          "mean_activation_freq": 0.3875911840470758,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5475272324146156,
+          "min_activation_freq": 5.674966304887565e-06
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7117109108341539,
+          "min_activation_freq": 3.972476413421295e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.862958807725048,
+          "min_activation_freq": 0.08875647300844151
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8849387739804445,
+          "min_activation_freq": 0.07387103639072143
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9414239136419426,
+          "min_activation_freq": 0.08932680712208271
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9514631795834013,
+          "min_activation_freq": 0.25975172022416115
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9752765527899716,
+          "min_activation_freq": 0.7117031992622543
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9853666985574203,
+          "min_activation_freq": 0.9380634177484571
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9869987872646498,
+          "min_activation_freq": 0.9226048095339434
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9809731649567531,
+          "min_activation_freq": 0.9118252110378094
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832447529760578,
+          "min_activation_freq": 0.9117599489253032
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9802257139487043,
+          "min_activation_freq": 0.9236234659856707
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9797333830408417,
+          "min_activation_freq": 0.9188706817053274
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9794347149979131,
+          "min_activation_freq": 0.9297240547634249
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9805970200652951,
+          "min_activation_freq": 0.9287734979073562
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9782243941375454,
+          "min_activation_freq": 0.934987586011208
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807529883275511,
+          "min_activation_freq": 0.9393913598638008
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9814559763251623,
+          "min_activation_freq": 0.9362417535645882
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.981692332640047,
+          "min_activation_freq": 0.9487749166489324
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.981981823971701,
+          "min_activation_freq": 0.9520692345889197
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.982975252909245,
+          "min_activation_freq": 0.9439682201886926
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9844357705478323,
+          "min_activation_freq": 0.951822373554657
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9862929679702592,
+          "min_activation_freq": 0.960607221394623
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9872935826379851,
+          "min_activation_freq": 0.9455061360573171
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.987838898543068,
+          "min_activation_freq": 0.1778874937930056
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9889839951824652,
+          "min_activation_freq": 0.9605419592821167
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905545067934626,
+          "min_activation_freq": 0.37737390934241327
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.991799408190923,
+          "min_activation_freq": 0.9361027168901185
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9901929006522089,
+          "min_activation_freq": 0.8309995034404484
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.98914781343672,
+          "min_activation_freq": 0.8997914449882954
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9899575037406936,
+          "min_activation_freq": 0.8849797829325389
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9927022016064775,
+          "min_activation_freq": 0.07252606937646308
+        },
+        "_overall": {
+          "dead_count": 11993,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.030263343830749353
+        }
+      },
+      "size": 759,
+      "size_pre_filter": 759,
+      "skipped_long": 0
+    }
+  },
+  "old_data": {
+    "num_records": 31744,
+    "source_steps": [
+      25,
+      50,
+      75,
+      100,
+      125,
+      150,
+      175,
+      200,
+      225,
+      250,
+      275,
+      300,
+      325,
+      350,
+      375,
+      400,
+      425,
+      450,
+      475,
+      500,
+      525,
+      550,
+      575,
+      600,
+      625,
+      650,
+      675,
+      700,
+      725,
+      750,
+      775
+    ],
+    "num_source_steps": 31,
+    "num_positives_pre_cap": 5930,
+    "num_negatives_pre_cap": 25814,
+    "positive": {
+      "loss": 0.6537277096236498,
+      "token_entropy": 0.17806932337300477,
+      "num_supervised_tokens": 2252755,
+      "kl_from_init": 1.0604621982186897,
+      "kl_to_init": 0.2527952983986953,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9263964076667004,
+          "min_activation_freq": 0.8049104318933927
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8691,
+          "dead_fraction": 0.7895167151162791,
+          "mean_activation_freq": 0.15059636768948748,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 1362,
+          "dead_fraction": 0.1237281976744186,
+          "mean_activation_freq": 0.16667077687672918,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.38811142922970343,
+          "min_activation_freq": 4.439009124383255e-07
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5454972821827903,
+          "min_activation_freq": 7.102414599013208e-06
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7088961437456709,
+          "min_activation_freq": 3.0185262045806132e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8602809571625037,
+          "min_activation_freq": 0.0873787873070973
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8826747353034344,
+          "min_activation_freq": 0.06690163821631735
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9408705007142286,
+          "min_activation_freq": 0.08941718029701409
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9509157666952036,
+          "min_activation_freq": 0.2486231303448444
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9751557180447605,
+          "min_activation_freq": 0.7039211987100239
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.985427736943016,
+          "min_activation_freq": 0.9384158508137813
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9870215147787648,
+          "min_activation_freq": 0.9247228393677963
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9811124241468187,
+          "min_activation_freq": 0.9127077733708281
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9833051398051081,
+          "min_activation_freq": 0.911891439592854
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9803005157480172,
+          "min_activation_freq": 0.9234594973709968
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9798187513942875,
+          "min_activation_freq": 0.9200179335968625
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9795019267961071,
+          "min_activation_freq": 0.9318749708690026
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9806447312261916,
+          "min_activation_freq": 0.9301273329767329
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9782830056990812,
+          "min_activation_freq": 0.9366495690831892
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.980768201692367,
+          "min_activation_freq": 0.9378991501517031
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9815417845219288,
+          "min_activation_freq": 0.9366229350284428
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9818181226389697,
+          "min_activation_freq": 0.9499981134211221
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9821691890228414,
+          "min_activation_freq": 0.9526055873807848
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9831352501995231,
+          "min_activation_freq": 0.9430377471140892
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9845995428085135,
+          "min_activation_freq": 0.9495315735621495
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9864318566144694,
+          "min_activation_freq": 0.9610223925815279
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9874657236958514,
+          "min_activation_freq": 0.9465898422154206
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9880095778025517,
+          "min_activation_freq": 0.17898129179604527
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9891394447469953,
+          "min_activation_freq": 0.960633535382232
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.990685429157079,
+          "min_activation_freq": 0.3771399908112511
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9919104292125667,
+          "min_activation_freq": 0.9386338061617885
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9903376220253283,
+          "min_activation_freq": 0.8241162487709494
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9893274900531354,
+          "min_activation_freq": 0.8987213434217214
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9901475238387695,
+          "min_activation_freq": 0.8843536025888301
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9925706126182292,
+          "min_activation_freq": 0.06264418456512137
+        },
+        "_overall": {
+          "dead_count": 10053,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.025367914244186048
+        }
+      },
+      "size": 5930,
+      "size_pre_filter": 5930,
+      "skipped_long": 0
+    },
+    "negative": {
+      "loss": 0.7582389686128663,
+      "token_entropy": 0.21428087573010274,
+      "num_supervised_tokens": 11222134,
+      "kl_from_init": 0.9271724565243475,
+      "kl_to_init": 0.23593341943417206,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9259938939705264,
+          "min_activation_freq": 0.8037279718812839
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 411,
+          "dead_fraction": 0.03733648255813953,
+          "mean_activation_freq": 0.15029900707606625,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 386,
+          "dead_fraction": 0.035065406976744186,
+          "mean_activation_freq": 0.1666316429088596,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.3886707251071674,
+          "min_activation_freq": 1.603973005490756e-06
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5481030404076113,
+          "min_activation_freq": 1.6396168500572172e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7118203880326028,
+          "min_activation_freq": 4.5089463376573475e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8630515921406479,
+          "min_activation_freq": 0.08866709308586049
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8862450482598436,
+          "min_activation_freq": 0.07358172696921994
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9414651419253468,
+          "min_activation_freq": 0.09098857668247412
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9514968674101537,
+          "min_activation_freq": 0.2624841228949859
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9753081215824054,
+          "min_activation_freq": 0.7106188537759396
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9853940329964411,
+          "min_activation_freq": 0.9384619716713416
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9870224517926302,
+          "min_activation_freq": 0.9241511462971302
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9809716637536726,
+          "min_activation_freq": 0.9124750248036603
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832268007032994,
+          "min_activation_freq": 0.9113607982225127
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9802171803316693,
+          "min_activation_freq": 0.9233260804050281
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9797766769568468,
+          "min_activation_freq": 0.9209465864513826
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9794594473068544,
+          "min_activation_freq": 0.9301594509564758
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9806191175556078,
+          "min_activation_freq": 0.9290572541728694
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9782288703028428,
+          "min_activation_freq": 0.935313105332729
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807672262618973,
+          "min_activation_freq": 0.9380347801942126
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9814264887543298,
+          "min_activation_freq": 0.936558679481104
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9816226732778464,
+          "min_activation_freq": 0.9488789743555014
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.981905970784358,
+          "min_activation_freq": 0.9531960676997797
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9829178553410683,
+          "min_activation_freq": 0.9460934970122438
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9843726553923945,
+          "min_activation_freq": 0.9533743760322234
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9862531872409782,
+          "min_activation_freq": 0.9610487630962168
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9872678425658588,
+          "min_activation_freq": 0.9461326161316556
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9878070132702805,
+          "min_activation_freq": 0.1882361233612074
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9889405903500126,
+          "min_activation_freq": 0.9621156724737024
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905287564777351,
+          "min_activation_freq": 0.3978238898234507
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9918002821004879,
+          "min_activation_freq": 0.9385664972455328
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9902258519101365,
+          "min_activation_freq": 0.8248660192437552
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9892153608891625,
+          "min_activation_freq": 0.8993891892575868
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9900092661668827,
+          "min_activation_freq": 0.8908171119681871
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926534549190239,
+          "min_activation_freq": 0.09271222389609676
+        },
+        "_overall": {
+          "dead_count": 797,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.0020111635981912143
+        }
+      },
+      "size": 25814,
+      "size_pre_filter": 25814,
+      "skipped_long": 0
+    }
+  },
+  "new_data": {
+    "num_records": 0,
+    "source_steps": [],
+    "num_source_steps": 0,
+    "num_positives_pre_cap": 0,
+    "num_negatives_pre_cap": 0,
+    "positive": {
+      "size": 0
+    },
+    "negative": {
+      "size": 0
+    }
+  }
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.57.6"
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9506258b08166c6bcc1db297bcba0c9fea6dd97486575f0be7b73077f6b3a46d
+size 4999924112

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67fc8f27ff92df6f5653c60f54562ae44cbdd3d157f31522c9f0c98eda71a0de
+size 1794332816

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/model.safetensors.index.json

@@ -0,0 +1,443 @@
+{
+  "metadata": {
+    "total_parameters": 3397103616,
+    "total_size": 6794207232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

rlrb_bs128_hardkcd32_lam1p0/checkpoints_hf_format/global_step_800/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

rlrb_bs128_hardkcd32_lam1p0/rollouts.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be6085dada4c1f5602bc474fc42bf809a71311e152838ba57d50653c42cdccd
+size 449979436