upload rlrb_bs128_hardk32_lam1p0 (5/5)

.gitattributes

@@ -145,3 +145,6 @@ rlrb_bs128_hardk32_lam1p0/checkpoints_hf_format/global_step_500/tokenizer.json f
 rlrb_bs128_hardk32_lam1p0/checkpoints_hf_format/global_step_550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 rlrb_bs128_hardk32_lam1p0/checkpoints_hf_format/global_step_600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 rlrb_bs128_hardk32_lam1p0/checkpoints_hf_format/global_step_650/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rlrb_bs128_hardk32_lam1p0/checkpoints_hf_format/global_step_700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rlrb_bs128_hardk32_lam1p0/checkpoints_hf_format/global_step_750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rlrb_bs128_hardk32_lam1p0/checkpoints_hf_format/global_step_800/tokenizer.json filter=lfs diff=lfs merge=lfs -text

rlrb_bs128_hardk32_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 sha256:9d5d17d7c2996426036b8e056d60b9fcf0d38992d522b88a1844f92220e37eec
+size 1826756896

rlrb_bs128_hardk32_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-00002-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-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-00002-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-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-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-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-00001-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-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-00002-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-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-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-00002-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-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-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-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-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-00002-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-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-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-00002-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-00002-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-00002-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-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-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-00002-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-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-00002-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-00002-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-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-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-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-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-00002-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-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-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-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-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-00002-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-00002-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-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-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-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-00002-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-00002-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-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-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-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-00001-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-00002-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-00001-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-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-00001-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-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-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-00002-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-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-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-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-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-00001-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-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00001-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-00002-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-00002-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-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-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-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-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00001-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-00001-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-00002-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-00002-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-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-00001-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-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-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-00002-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-00002-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-00002-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-00002-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-00001-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-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-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-00002-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-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-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-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-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-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-00002-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-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-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-00001-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-00002-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-00002-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-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-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-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-00001-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-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_hardk32_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_hardk32_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_hardk32_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_hardk32_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_hardk32_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_hardk32_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_hardk32_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/7213686879.44299-7567c3c2-24ba/qwen3b_kk_rlrb_bs128_hardk32_lam1p0/checkpoints_hf_format/global_step_750",
+  "rollouts_dir": "/mnt/mystorageoutput/projects/jy_intern/amlt-results/7213686879.44299-7567c3c2-24ba/qwen3b_kk_rlrb_bs128_hardk32_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": 299,
+    "num_negatives_pre_cap": 725,
+    "positive": {
+      "loss": 0.4486160417149477,
+      "token_entropy": 0.3133839236083905,
+      "num_supervised_tokens": 59283,
+      "kl_from_init": 0.531918604730295,
+      "kl_to_init": 0.18390294096842008,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9251973403514049,
+          "min_activation_freq": 0.8027259079331344
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8713,
+          "dead_fraction": 0.791515261627907,
+          "mean_activation_freq": 0.1508082664635024,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 3160,
+          "dead_fraction": 0.2870639534883721,
+          "mean_activation_freq": 0.16762296942405544,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 56,
+          "dead_fraction": 0.005087209302325582,
+          "mean_activation_freq": 0.40012442075486176,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5617178823765705,
+          "min_activation_freq": 1.6868242160484456e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7208427254872078,
+          "min_activation_freq": 1.6868242160484456e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8794057816611022,
+          "min_activation_freq": 0.11332085083413458
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.887103077144944,
+          "min_activation_freq": 0.06379569185095221
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9422406717394964,
+          "min_activation_freq": 0.11892110723141541
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.95191193924373,
+          "min_activation_freq": 0.27049913128552877
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9755563648266357,
+          "min_activation_freq": 0.7223656022805863
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9856871034492024,
+          "min_activation_freq": 0.9382959701769479
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871800608722883,
+          "min_activation_freq": 0.9255435791036216
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812427231187889,
+          "min_activation_freq": 0.9180203431000455
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9838662527131391,
+          "min_activation_freq": 0.915979285798627
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813749368544219,
+          "min_activation_freq": 0.9286810721454718
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9806025390038873,
+          "min_activation_freq": 0.9243459339102272
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9801374625049379,
+          "min_activation_freq": 0.9265219371489297
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9809594552553205,
+          "min_activation_freq": 0.9355801831891098
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9787225436872761,
+          "min_activation_freq": 0.9377393181856519
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813684641568488,
+          "min_activation_freq": 0.9353271595567026
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9818734265092859,
+          "min_activation_freq": 0.9392911964644165
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9820934936296888,
+          "min_activation_freq": 0.949547087697991
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9824533458869342,
+          "min_activation_freq": 0.9545738238618154
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832639930282183,
+          "min_activation_freq": 0.9518917733582983
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9847343021392462,
+          "min_activation_freq": 0.9605451815866269
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9864774069510495,
+          "min_activation_freq": 0.9581330229576777
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9873570349052967,
+          "min_activation_freq": 0.9541183813234823
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9878724050612181,
+          "min_activation_freq": 0.18160349509977566
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9889581127344834,
+          "min_activation_freq": 0.966364725131994
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9904775064687746,
+          "min_activation_freq": 0.42835214142334227
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917442458699286,
+          "min_activation_freq": 0.9352090818615793
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905505633649632,
+          "min_activation_freq": 0.8098780426091797
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9897646761307314,
+          "min_activation_freq": 0.9026533744918442
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9906620135939398,
+          "min_activation_freq": 0.8984700504360441
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.992684360753936,
+          "min_activation_freq": 0.24517989980264157
+        },
+        "_overall": {
+          "dead_count": 11929,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.03010184512273902
+        }
+      },
+      "size": 299,
+      "size_pre_filter": 299,
+      "skipped_long": 0
+    },
+    "negative": {
+      "loss": 0.46927953595453975,
+      "token_entropy": 0.336927762874755,
+      "num_supervised_tokens": 259891,
+      "kl_from_init": 0.4468369685349168,
+      "kl_to_init": 0.1734816839460027,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9257447164874709,
+          "min_activation_freq": 0.806549668899654
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8729,
+          "dead_fraction": 0.79296875,
+          "mean_activation_freq": 0.15059968741199906,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 1933,
+          "dead_fraction": 0.17559956395348839,
+          "mean_activation_freq": 0.16706717185460487,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 16,
+          "dead_fraction": 0.0014534883720930232,
+          "mean_activation_freq": 0.3966404764373266,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5623103625542748,
+          "min_activation_freq": 2.3086601690708795e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7187714545864398,
+          "min_activation_freq": 4.232543643296613e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8755719579034387,
+          "min_activation_freq": 0.11125048578057722
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.884274224998217,
+          "min_activation_freq": 0.06242617097167658
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9419672857401176,
+          "min_activation_freq": 0.10794140620490897
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.951846267639215,
+          "min_activation_freq": 0.26919747124756144
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9753002681558001,
+          "min_activation_freq": 0.7132797980691905
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9855878508867043,
+          "min_activation_freq": 0.9378085428121788
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871407880253554,
+          "min_activation_freq": 0.9297166889195855
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9810976061280118,
+          "min_activation_freq": 0.9155338199475933
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9837177505117752,
+          "min_activation_freq": 0.910204662723988
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812668935424895,
+          "min_activation_freq": 0.9258073576999587
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9804237198015169,
+          "min_activation_freq": 0.9235179363656301
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9799666856226978,
+          "min_activation_freq": 0.929354998826431
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807439121755471,
+          "min_activation_freq": 0.9350189117745515
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9785330995175481,
+          "min_activation_freq": 0.9375353513588388
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9811486278393274,
+          "min_activation_freq": 0.9330988760672743
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9816118940164136,
+          "min_activation_freq": 0.9380432565960344
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9818238871698715,
+          "min_activation_freq": 0.9486823322085027
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9821314554567732,
+          "min_activation_freq": 0.9556006171818184
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9829867737121769,
+          "min_activation_freq": 0.9509794490767283
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9844488699248289,
+          "min_activation_freq": 0.9615569604180213
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9862324567134045,
+          "min_activation_freq": 0.9589943476303526
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9872028867474448,
+          "min_activation_freq": 0.9508601683013262
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9877591421404706,
+          "min_activation_freq": 0.184681270224825
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9888904925834067,
+          "min_activation_freq": 0.9662704749298744
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9904375346830329,
+          "min_activation_freq": 0.43323547179394434
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917631452749913,
+          "min_activation_freq": 0.9408328876336617
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905442357632398,
+          "min_activation_freq": 0.7942445101985062
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9896685887986983,
+          "min_activation_freq": 0.8865716781265991
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.990532930850572,
+          "min_activation_freq": 0.9066878037331034
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926284580071715,
+          "min_activation_freq": 0.2765736404877429
+        },
+        "_overall": {
+          "dead_count": 10678,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.026945050064599484
+        }
+      },
+      "size": 725,
+      "size_pre_filter": 725,
+      "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": 5936,
+    "num_negatives_pre_cap": 23760,
+    "positive": {
+      "loss": 0.5457324341083938,
+      "token_entropy": 0.3485538608080474,
+      "num_supervised_tokens": 1399869,
+      "kl_from_init": 0.4917188473430711,
+      "kl_to_init": 0.18236147927899704,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9256056544449998,
+          "min_activation_freq": 0.8070205140623872
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 5055,
+          "dead_fraction": 0.45921148255813954,
+          "mean_activation_freq": 0.1511213042575894,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 1852,
+          "dead_fraction": 0.16824127906976744,
+          "mean_activation_freq": 0.16745117626361533,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.39739110679575707,
+          "min_activation_freq": 7.143525572750021e-07
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5611993550409791,
+          "min_activation_freq": 2.2859281832800067e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7179669240401056,
+          "min_activation_freq": 4.6432916222875135e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8757696756845205,
+          "min_activation_freq": 0.10729361104503349
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8838662187573341,
+          "min_activation_freq": 0.05993560826048723
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9416529572495131,
+          "min_activation_freq": 0.11324988266759246
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9516024982791371,
+          "min_activation_freq": 0.26493050421146547
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.975401597729132,
+          "min_activation_freq": 0.7148954652185311
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9856606499149247,
+          "min_activation_freq": 0.9387942728926777
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871712616372185,
+          "min_activation_freq": 0.9283047199416516
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812368486318452,
+          "min_activation_freq": 0.9183680758699564
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9838143315568671,
+          "min_activation_freq": 0.912886134345428
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813283858256412,
+          "min_activation_freq": 0.9287711921615522
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9805325061604185,
+          "min_activation_freq": 0.9236399977426458
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9800568827909387,
+          "min_activation_freq": 0.9276825188642651
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9808393817138653,
+          "min_activation_freq": 0.9357082698452497
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9785847396157723,
+          "min_activation_freq": 0.9384113799219783
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812259191285705,
+          "min_activation_freq": 0.9357432731205562
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9817678983748387,
+          "min_activation_freq": 0.9390478680505103
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9820062239222899,
+          "min_activation_freq": 0.9493702625031342
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9823332436597639,
+          "min_activation_freq": 0.9562973392510299
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9831597724760939,
+          "min_activation_freq": 0.9514447423294607
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9846362928128101,
+          "min_activation_freq": 0.9617549927886109
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9863830587311224,
+          "min_activation_freq": 0.9587954301438205
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9873186939334995,
+          "min_activation_freq": 0.9532449107737938
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9878464196787923,
+          "min_activation_freq": 0.1867417594074874
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.988957911699196,
+          "min_activation_freq": 0.9671940731597027
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9904911510968293,
+          "min_activation_freq": 0.4345870935066067
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917842363654019,
+          "min_activation_freq": 0.9414216615983352
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905957877825595,
+          "min_activation_freq": 0.7956308768891945
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9897791212885626,
+          "min_activation_freq": 0.8920963318710536
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9906721841155626,
+          "min_activation_freq": 0.9019115360080121
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926292774776998,
+          "min_activation_freq": 0.26413757287289025
+        },
+        "_overall": {
+          "dead_count": 6907,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.01742924337855297
+        }
+      },
+      "size": 5936,
+      "size_pre_filter": 5936,
+      "skipped_long": 0
+    },
+    "negative": {
+      "loss": 0.6382600049080566,
+      "token_entropy": 0.37375768226480727,
+      "num_supervised_tokens": 8176144,
+      "kl_from_init": 0.45042803723935054,
+      "kl_to_init": 0.17595245654337766,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.925778741805638,
+          "min_activation_freq": 0.8082610824858272
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 1800,
+          "dead_fraction": 0.16351744186046513,
+          "mean_activation_freq": 0.15094074832663631,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 153,
+          "dead_fraction": 0.013898982558139535,
+          "mean_activation_freq": 0.1671659213443133,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.3962267096803497,
+          "min_activation_freq": 4.280746523055367e-06
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.562274229186293,
+          "min_activation_freq": 3.4245972184442936e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7187990505353811,
+          "min_activation_freq": 7.864342898070289e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8760529525594772,
+          "min_activation_freq": 0.10751070431244852
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8854044586763746,
+          "min_activation_freq": 0.06459218428638244
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9419621016805715,
+          "min_activation_freq": 0.11011009590829125
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9520791626261137,
+          "min_activation_freq": 0.2771673297339186
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9754471110280971,
+          "min_activation_freq": 0.7161732963607296
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9856028232882031,
+          "min_activation_freq": 0.9388381613631072
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.987151999122439,
+          "min_activation_freq": 0.9286476608044086
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9810785631526283,
+          "min_activation_freq": 0.9174791931257572
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9836959251286035,
+          "min_activation_freq": 0.91043663125307
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812169359062874,
+          "min_activation_freq": 0.9280059157470808
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9804223396657021,
+          "min_activation_freq": 0.9238886937412062
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9799511283480031,
+          "min_activation_freq": 0.9287201888812135
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807316672005428,
+          "min_activation_freq": 0.9343652704746884
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9784856484413823,
+          "min_activation_freq": 0.9383640992624397
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.981126981542366,
+          "min_activation_freq": 0.9345866462234521
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9815944648173829,
+          "min_activation_freq": 0.9386456500766132
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9817744049775133,
+          "min_activation_freq": 0.9491403282525358
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9820619577698553,
+          "min_activation_freq": 0.9561623425419122
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.982938091176517,
+          "min_activation_freq": 0.9512295771698738
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9844048380521131,
+          "min_activation_freq": 0.9619807332160492
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9862104110703966,
+          "min_activation_freq": 0.9588254561074268
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871623455450123,
+          "min_activation_freq": 0.9509390979415236
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9877068481363566,
+          "min_activation_freq": 0.18485474326283882
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9888372705305116,
+          "min_activation_freq": 0.9666666829742726
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9903998273419555,
+          "min_activation_freq": 0.43824374913162
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917420533476616,
+          "min_activation_freq": 0.9414133361643338
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905450678672114,
+          "min_activation_freq": 0.794701634413484
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9896784129342109,
+          "min_activation_freq": 0.8867168924617767
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905614464558381,
+          "min_activation_freq": 0.9090001350269761
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926172695848258,
+          "min_activation_freq": 0.2866888107645854
+        },
+        "_overall": {
+          "dead_count": 1953,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.004928234011627907
+        }
+      },
+      "size": 23760,
+      "size_pre_filter": 23760,
+      "skipped_long": 0
+    }
+  },
+  "new_data": {
+    "num_records": 2048,
+    "source_steps": [
+      775,
+      800
+    ],
+    "num_source_steps": 2,
+    "num_positives_pre_cap": 634,
+    "num_negatives_pre_cap": 1414,
+    "positive": {
+      "loss": 0.4720333335982742,
+      "token_entropy": 0.3236165078347087,
+      "num_supervised_tokens": 117947,
+      "kl_from_init": 0.5351528872240625,
+      "kl_to_init": 0.18604788975520492,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9251371646700399,
+          "min_activation_freq": 0.8003425267281067
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8453,
+          "dead_fraction": 0.7678960755813954,
+          "mean_activation_freq": 0.15100799163513726,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 974,
+          "dead_fraction": 0.0884811046511628,
+          "mean_activation_freq": 0.1677343520941905,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 31,
+          "dead_fraction": 0.0028161337209302324,
+          "mean_activation_freq": 0.39978582036058374,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5620124151089443,
+          "min_activation_freq": 8.478384359076534e-06
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7194539261795946,
+          "min_activation_freq": 3.391353743630614e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8783742906870272,
+          "min_activation_freq": 0.10692938353667325
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8860267434676019,
+          "min_activation_freq": 0.061637854290486405
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9418347403672245,
+          "min_activation_freq": 0.11849389980245364
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9518097605884176,
+          "min_activation_freq": 0.26692497477680655
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9756037547769781,
+          "min_activation_freq": 0.7251053439256615
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9856941327830334,
+          "min_activation_freq": 0.9380738806413049
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871951380014791,
+          "min_activation_freq": 0.9263821886101384
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812233824327087,
+          "min_activation_freq": 0.9178868474823437
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9838992384808825,
+          "min_activation_freq": 0.9134696092312649
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813839156496384,
+          "min_activation_freq": 0.9301974615717229
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9805968145785721,
+          "min_activation_freq": 0.9240167193739561
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9801436222906387,
+          "min_activation_freq": 0.9256021772491034
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9809304252935048,
+          "min_activation_freq": 0.9352590570340915
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9786793888295018,
+          "min_activation_freq": 0.9374634369674515
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813419373263532,
+          "min_activation_freq": 0.9375312640423241
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9818474964230582,
+          "min_activation_freq": 0.9399899955064562
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9820881884201635,
+          "min_activation_freq": 0.9481801147973242
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9824161319882836,
+          "min_activation_freq": 0.9556071794958753
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832247794621883,
+          "min_activation_freq": 0.9509525464827422
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9847196276853063,
+          "min_activation_freq": 0.9613894376287655
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.986448874584436,
+          "min_activation_freq": 0.9583880895656524
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.987334301962046,
+          "min_activation_freq": 0.9542082460766276
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9878284227878465,
+          "min_activation_freq": 0.1877029513255954
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9889294374261716,
+          "min_activation_freq": 0.9655777595021493
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9904548780754108,
+          "min_activation_freq": 0.4316430261049454
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917156310821318,
+          "min_activation_freq": 0.9391336786861896
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905245836731261,
+          "min_activation_freq": 0.7995370802139944
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9897241188259863,
+          "min_activation_freq": 0.896979151652861
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9906270136162852,
+          "min_activation_freq": 0.8989122232867305
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926914755612543,
+          "min_activation_freq": 0.24633097916860963
+        },
+        "_overall": {
+          "dead_count": 9458,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.023866480943152454
+        }
+      },
+      "size": 634,
+      "size_pre_filter": 634,
+      "skipped_long": 0
+    },
+    "negative": {
+      "loss": 0.4896361939663853,
+      "token_entropy": 0.3580920266550506,
+      "num_supervised_tokens": 514585,
+      "kl_from_init": 0.44298314775135755,
+      "kl_to_init": 0.17174807532334477,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9258872116071858,
+          "min_activation_freq": 0.8056880787430648
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8703,
+          "dead_fraction": 0.7906068313953488,
+          "mean_activation_freq": 0.15102513832127312,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 1634,
+          "dead_fraction": 0.1484375,
+          "mean_activation_freq": 0.16712817226870103,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.3956471884461649,
+          "min_activation_freq": 1.9433135439237443e-06
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.562276720547106,
+          "min_activation_freq": 2.331976252708493e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.719041783020682,
+          "min_activation_freq": 6.024271986163607e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8760308967646314,
+          "min_activation_freq": 0.10946102198859274
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8854731049077479,
+          "min_activation_freq": 0.06726196838228864
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9419061670561015,
+          "min_activation_freq": 0.10990409747660736
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9520422209300065,
+          "min_activation_freq": 0.2784418512004819
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9754204519853547,
+          "min_activation_freq": 0.7161790569099371
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9855838961998842,
+          "min_activation_freq": 0.9384183371066004
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871374226741982,
+          "min_activation_freq": 0.9278700311901823
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9810473657819996,
+          "min_activation_freq": 0.9163928213997687
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9836729181363917,
+          "min_activation_freq": 0.9093852327603796
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.981207807781886,
+          "min_activation_freq": 0.9279205573423244
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9804132299839834,
+          "min_activation_freq": 0.9230292371522683
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9799441125409593,
+          "min_activation_freq": 0.9282334308228961
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.980726695038291,
+          "min_activation_freq": 0.9337077450761293
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9784911377134792,
+          "min_activation_freq": 0.9367937269838802
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9811192256612972,
+          "min_activation_freq": 0.9347202114325135
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9815873592665324,
+          "min_activation_freq": 0.937843116297599
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.981765461092942,
+          "min_activation_freq": 0.9485604904923385
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9820380019906534,
+          "min_activation_freq": 0.9562657286939961
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9829136137389782,
+          "min_activation_freq": 0.9506728723145835
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9843887728463623,
+          "min_activation_freq": 0.9615865211772593
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9861789196351722,
+          "min_activation_freq": 0.9585957616331606
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871454196000908,
+          "min_activation_freq": 0.9509799158545235
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.987695351735232,
+          "min_activation_freq": 0.18709639806834633
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9888356986443806,
+          "min_activation_freq": 0.9663437527327846
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.990396702144661,
+          "min_activation_freq": 0.442354518689818
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917358909152013,
+          "min_activation_freq": 0.940083756813743
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905289113718528,
+          "min_activation_freq": 0.7950095708192038
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9896409920299287,
+          "min_activation_freq": 0.8830960871381792
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905206062132704,
+          "min_activation_freq": 0.906777305984434
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9925971423037665,
+          "min_activation_freq": 0.28109058756085
+        },
+        "_overall": {
+          "dead_count": 10337,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.02608456476098191
+        }
+      },
+      "size": 1414,
+      "size_pre_filter": 1414,
+      "skipped_long": 0
+    }
+  }
+}

rlrb_bs128_hardk32_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_hardk32_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 sha256:76600ebde158b731620908967449f1a3be2de83d9be8173f33dc12d196c67a69
+size 4984255024

rlrb_bs128_hardk32_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 sha256:3e8ff6fa86640b450cbfc009ffe4edbd7b7b9a13f6307bd1d51e080e0d5feda4
+size 1810001992

rlrb_bs128_hardk32_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-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-00002-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-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-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-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-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-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-00001-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-00001-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-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-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-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-00002-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-00002-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-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-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-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-00002-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-00002-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-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-00001-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-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-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-00001-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-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-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-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-00002-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-00001-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-00002-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-00002-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-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-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-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-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-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-00001-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-00002-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-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-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-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-00002-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-00002-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-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-00002-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-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-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-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-00002-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-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-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-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-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-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-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-00001-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-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-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-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-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-00001-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-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-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-00002-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-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-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-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-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-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-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-00002-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-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-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-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-00002-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-00002-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-00002-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-00001-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-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-00002-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-00002-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-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-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00001-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-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-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-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-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00001-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-00002-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-00002-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-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-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-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-00002-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-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-00002-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-00002-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-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-00002-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-00001-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-00002-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-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-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-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-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-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-00001-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-00002-of-00002.safetensors"
+  }
+}

rlrb_bs128_hardk32_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_hardk32_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_hardk32_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_hardk32_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_hardk32_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_hardk32_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_hardk32_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/7213686879.44299-7567c3c2-24ba/qwen3b_kk_rlrb_bs128_hardk32_lam1p0/checkpoints_hf_format/global_step_800",
+  "rollouts_dir": "/mnt/mystorageoutput/projects/jy_intern/amlt-results/7213686879.44299-7567c3c2-24ba/qwen3b_kk_rlrb_bs128_hardk32_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": 335,
+    "num_negatives_pre_cap": 689,
+    "positive": {
+      "loss": 0.4761518772763993,
+      "token_entropy": 0.32689121417990064,
+      "num_supervised_tokens": 62170,
+      "kl_from_init": 0.5499312867300675,
+      "kl_to_init": 0.18734826477121957,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9251510256129105,
+          "min_activation_freq": 0.8032169856844137
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8398,
+          "dead_fraction": 0.7628997093023255,
+          "mean_activation_freq": 0.15106394174029575,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 1003,
+          "dead_fraction": 0.0911155523255814,
+          "mean_activation_freq": 0.16775982419734337,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 65,
+          "dead_fraction": 0.005904796511627907,
+          "mean_activation_freq": 0.4005257980158492,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.561982530844253,
+          "min_activation_freq": 1.608492842206852e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 1,
+          "dead_fraction": 9.084302325581395e-05,
+          "mean_activation_freq": 0.7190484902728265,
+          "min_activation_freq": 0.0
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8776723980524144,
+          "min_activation_freq": 0.10516326202348399
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8865813793340465,
+          "min_activation_freq": 0.06380891105034582
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9417393357275249,
+          "min_activation_freq": 0.11928582917806015
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.951773746193857,
+          "min_activation_freq": 0.26390542062087824
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9755893194555626,
+          "min_activation_freq": 0.7220041820813897
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9857175947140435,
+          "min_activation_freq": 0.9382499597876789
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9872171899022185,
+          "min_activation_freq": 0.9272156988901399
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812597696067796,
+          "min_activation_freq": 0.9177899308348078
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9839233945932196,
+          "min_activation_freq": 0.9161331832073346
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813790125817805,
+          "min_activation_freq": 0.9313977802798777
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9806181785174558,
+          "min_activation_freq": 0.9241273926331027
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9801417750256235,
+          "min_activation_freq": 0.9242882419173234
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9809224931475399,
+          "min_activation_freq": 0.9360463245938555
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.978659566698213,
+          "min_activation_freq": 0.9376869872929064
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813212702020153,
+          "min_activation_freq": 0.9352420781727521
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9818559786369705,
+          "min_activation_freq": 0.9392633102782691
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9821106912521369,
+          "min_activation_freq": 0.9480135113398744
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9824729016883564,
+          "min_activation_freq": 0.9550587099887404
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832589327462958,
+          "min_activation_freq": 0.9522921023001447
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9847464832337999,
+          "min_activation_freq": 0.9615891909281002
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9864958726260703,
+          "min_activation_freq": 0.957760977963648
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9873689928754052,
+          "min_activation_freq": 0.9540936142834163
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9878699694269462,
+          "min_activation_freq": 0.18351294836737975
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9889574131647657,
+          "min_activation_freq": 0.9668972173073829
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9904744010585191,
+          "min_activation_freq": 0.4283094740228406
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917538600905805,
+          "min_activation_freq": 0.9397136882740871
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905596126033831,
+          "min_activation_freq": 0.8025092488338427
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9897705758497892,
+          "min_activation_freq": 0.89906707415152
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.990697006648593,
+          "min_activation_freq": 0.8949815023323145
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9927013804398853,
+          "min_activation_freq": 0.2332475470484156
+        },
+        "_overall": {
+          "dead_count": 9467,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.02388919169896641
+        }
+      },
+      "size": 335,
+      "size_pre_filter": 335,
+      "skipped_long": 0
+    },
+    "negative": {
+      "loss": 0.5025339473301541,
+      "token_entropy": 0.35785654590480015,
+      "num_supervised_tokens": 253138,
+      "kl_from_init": 0.47270823282650315,
+      "kl_to_init": 0.1805015086302623,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9260327300503153,
+          "min_activation_freq": 0.8061136613230727
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 8709,
+          "dead_fraction": 0.7911518895348837,
+          "mean_activation_freq": 0.15110194146847833,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 2882,
+          "dead_fraction": 0.2618095930232558,
+          "mean_activation_freq": 0.16715386972890692,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 1,
+          "dead_fraction": 9.084302325581395e-05,
+          "mean_activation_freq": 0.3955231244827713,
+          "min_activation_freq": 0.0
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5625946599389119,
+          "min_activation_freq": 2.7652900789292792e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7187034308298286,
+          "min_activation_freq": 9.876035996175998e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.875251843583181,
+          "min_activation_freq": 0.11257495911321097
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8850761201072738,
+          "min_activation_freq": 0.07156965765708823
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9419412289844843,
+          "min_activation_freq": 0.11260656242839873
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9521378751297435,
+          "min_activation_freq": 0.2727958662863734
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9755633207674936,
+          "min_activation_freq": 0.7182327426147002
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9855942770300673,
+          "min_activation_freq": 0.9374135846850333
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871548285226166,
+          "min_activation_freq": 0.9288293341971572
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.981043361603065,
+          "min_activation_freq": 0.9166778595074623
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.983682020588618,
+          "min_activation_freq": 0.9080304023892105
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812291950822806,
+          "min_activation_freq": 0.9282723257669728
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9804756804508415,
+          "min_activation_freq": 0.9226666877355434
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9799845604685109,
+          "min_activation_freq": 0.9278417305975396
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807569791678341,
+          "min_activation_freq": 0.9343085589678356
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9785184489290426,
+          "min_activation_freq": 0.9360901958615457
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9811181639629142,
+          "min_activation_freq": 0.9343599143550158
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9815770518940443,
+          "min_activation_freq": 0.9378876344128498
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9817757974290426,
+          "min_activation_freq": 0.948545852459923
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9820745051715517,
+          "min_activation_freq": 0.9564901358152469
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9829348381757529,
+          "min_activation_freq": 0.9511136218189287
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9844263284721109,
+          "min_activation_freq": 0.9616730795060401
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.986209709821162,
+          "min_activation_freq": 0.9591922192638007
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871787093661982,
+          "min_activation_freq": 0.9517259360506917
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9877252733141283,
+          "min_activation_freq": 0.18167165735685673
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.988874119350425,
+          "min_activation_freq": 0.9660461882451469
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9904261958260381,
+          "min_activation_freq": 0.4314366077001477
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.991765236300468,
+          "min_activation_freq": 0.9368447250116536
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905739652968957,
+          "min_activation_freq": 0.8004566679044631
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9896860780804917,
+          "min_activation_freq": 0.8844819821599285
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.990599182922239,
+          "min_activation_freq": 0.9025511776185321
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926036561320675,
+          "min_activation_freq": 0.265376988046046
+        },
+        "_overall": {
+          "dead_count": 11592,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.029251453488372093
+        }
+      },
+      "size": 689,
+      "size_pre_filter": 689,
+      "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": 6534,
+    "num_negatives_pre_cap": 25210,
+    "positive": {
+      "loss": 0.5453504586519297,
+      "token_entropy": 0.33903925698008575,
+      "num_supervised_tokens": 1514929,
+      "kl_from_init": 0.5188612766336513,
+      "kl_to_init": 0.18713487250051766,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9256133779571403,
+          "min_activation_freq": 0.8064021482194875
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 5055,
+          "dead_fraction": 0.45921148255813954,
+          "mean_activation_freq": 0.1511658177410632,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 1858,
+          "dead_fraction": 0.16878633720930233,
+          "mean_activation_freq": 0.16749141230189205,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.3977176362811776,
+          "min_activation_freq": 3.300484709184391e-06
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5615737279011824,
+          "min_activation_freq": 2.2443296022453856e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7183281976344098,
+          "min_activation_freq": 4.686688287041835e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8759584610593731,
+          "min_activation_freq": 0.10823213497134189
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.884208747029583,
+          "min_activation_freq": 0.06087744046090609
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9417991837382256,
+          "min_activation_freq": 0.11467006044507697
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9517144076151117,
+          "min_activation_freq": 0.264707454936832
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9754480788052167,
+          "min_activation_freq": 0.7162738319749639
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9856713432643293,
+          "min_activation_freq": 0.9387502648638979
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871846383502322,
+          "min_activation_freq": 0.9282098368966466
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812517573761842,
+          "min_activation_freq": 0.9182951808302567
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.983841835778354,
+          "min_activation_freq": 0.9135226799407761
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9813570069792165,
+          "min_activation_freq": 0.9290006330329672
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9805650250310295,
+          "min_activation_freq": 0.9233455825322506
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9800888750636744,
+          "min_activation_freq": 0.9279636207373415
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9808605675459585,
+          "min_activation_freq": 0.9362702806534168
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9786002924769619,
+          "min_activation_freq": 0.9382512315758692
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812243821821713,
+          "min_activation_freq": 0.9354748638385033
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.981786513733904,
+          "min_activation_freq": 0.9391040768247224
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9820345436606692,
+          "min_activation_freq": 0.9496194211081839
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9823808322673406,
+          "min_activation_freq": 0.9562019078121813
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9832029148279641,
+          "min_activation_freq": 0.9520340557214232
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9846808699618503,
+          "min_activation_freq": 0.9615394516838742
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9864278562753505,
+          "min_activation_freq": 0.9593624519696963
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9873578059800315,
+          "min_activation_freq": 0.9535661407234266
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9878787972057389,
+          "min_activation_freq": 0.18203625384423955
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9889880170788801,
+          "min_activation_freq": 0.9673885706854909
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.990510601733991,
+          "min_activation_freq": 0.4240568369870799
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9918047465540905,
+          "min_activation_freq": 0.9400671582628625
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9906236123932363,
+          "min_activation_freq": 0.8002817293747759
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.98981152914995,
+          "min_activation_freq": 0.8923243267506266
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9907364172519092,
+          "min_activation_freq": 0.8980698105323748
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9926590423611763,
+          "min_activation_freq": 0.25587337756422907
+        },
+        "_overall": {
+          "dead_count": 6913,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.01744438388242894
+        }
+      },
+      "size": 6534,
+      "size_pre_filter": 6534,
+      "skipped_long": 0
+    },
+    "negative": {
+      "loss": 0.6393954313615555,
+      "token_entropy": 0.3651623413164786,
+      "num_supervised_tokens": 8697482,
+      "kl_from_init": 0.4732466826848766,
+      "kl_to_init": 0.1807858280051673,
+      "dead_units": {
+        "layer_0": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9258173212253931,
+          "min_activation_freq": 0.8081663175617955
+        },
+        "layer_1": {
+          "intermediate_size": 11008,
+          "dead_count": 2387,
+          "dead_fraction": 0.2168422965116279,
+          "mean_activation_freq": 0.1509915535161799,
+          "min_activation_freq": 0.0
+        },
+        "layer_2": {
+          "intermediate_size": 11008,
+          "dead_count": 153,
+          "dead_fraction": 0.013898982558139535,
+          "mean_activation_freq": 0.16718317199023072,
+          "min_activation_freq": 0.0
+        },
+        "layer_3": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.39636586787667993,
+          "min_activation_freq": 4.484056420007538e-06
+        },
+        "layer_4": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.5625946465520035,
+          "min_activation_freq": 3.311303202467105e-05
+        },
+        "layer_5": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.7189981590453354,
+          "min_activation_freq": 7.611398333448692e-05
+        },
+        "layer_6": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8759823386503041,
+          "min_activation_freq": 0.10821775773723935
+        },
+        "layer_7": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.8855378263978292,
+          "min_activation_freq": 0.06546492421599723
+        },
+        "layer_8": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9420759621234407,
+          "min_activation_freq": 0.11098947948383221
+        },
+        "layer_9": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9521620073659228,
+          "min_activation_freq": 0.27647289180937656
+        },
+        "layer_10": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9754719940273158,
+          "min_activation_freq": 0.716647530860081
+        },
+        "layer_11": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9856111642648512,
+          "min_activation_freq": 0.938700994149801
+        },
+        "layer_12": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871649860105293,
+          "min_activation_freq": 0.9290807385401889
+        },
+        "layer_13": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9810947618230196,
+          "min_activation_freq": 0.9174816343396859
+        },
+        "layer_14": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9837185172488616,
+          "min_activation_freq": 0.9109905602564052
+        },
+        "layer_15": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9812454073996512,
+          "min_activation_freq": 0.9281214953937242
+        },
+        "layer_16": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9804508368363275,
+          "min_activation_freq": 0.9237324089891764
+        },
+        "layer_17": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.979975930169375,
+          "min_activation_freq": 0.9288738970658404
+        },
+        "layer_18": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9807445265722603,
+          "min_activation_freq": 0.9346408535251927
+        },
+        "layer_19": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9784932163429065,
+          "min_activation_freq": 0.9383518126280687
+        },
+        "layer_20": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9811151954719313,
+          "min_activation_freq": 0.93458658494493
+        },
+        "layer_21": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9816071578617123,
+          "min_activation_freq": 0.9385925719650814
+        },
+        "layer_22": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9817967775103766,
+          "min_activation_freq": 0.9490699722057487
+        },
+        "layer_23": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9821034697899806,
+          "min_activation_freq": 0.9565314420886413
+        },
+        "layer_24": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9829770109443712,
+          "min_activation_freq": 0.9517392505095152
+        },
+        "layer_25": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9844454273393137,
+          "min_activation_freq": 0.9619255320102991
+        },
+        "layer_26": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9862483633862531,
+          "min_activation_freq": 0.9590549310708547
+        },
+        "layer_27": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9871996814743703,
+          "min_activation_freq": 0.9511958748520548
+        },
+        "layer_28": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9877415687236519,
+          "min_activation_freq": 0.180534665090425
+        },
+        "layer_29": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9888704049539921,
+          "min_activation_freq": 0.9669618172248013
+        },
+        "layer_30": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9904233162517211,
+          "min_activation_freq": 0.4282007137238111
+        },
+        "layer_31": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9917674056878734,
+          "min_activation_freq": 0.9406729441923536
+        },
+        "layer_32": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9905758492990865,
+          "min_activation_freq": 0.7983945238403483
+        },
+        "layer_33": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.989712962186378,
+          "min_activation_freq": 0.8863684914783382
+        },
+        "layer_34": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.9906238345476625,
+          "min_activation_freq": 0.905647864519869
+        },
+        "layer_35": {
+          "intermediate_size": 11008,
+          "dead_count": 0,
+          "dead_fraction": 0.0,
+          "mean_activation_freq": 0.992641854825252,
+          "min_activation_freq": 0.2800108123247625
+        },
+        "_overall": {
+          "dead_count": 2540,
+          "intermediate_total": 396288,
+          "dead_fraction": 0.0064094799741602065
+        }
+      },
+      "size": 25210,
+      "size_pre_filter": 25210,
+      "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_hardk32_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_hardk32_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 sha256:0382cb1de6570551389d9b497effb1cc93d385336203198bfa4979be0c4e4782
+size 4975394480

rlrb_bs128_hardk32_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:c37c844a0f7fa81a24451580965fb3e66ecd0de33b1608a4d86396d3a39ec1ca
+size 1818862552

rlrb_bs128_hardk32_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-00002-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-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-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-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-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-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-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-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-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-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-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-00002-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-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-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-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-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-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-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-00002-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-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-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-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-00002-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-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-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-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-00002-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-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-00001-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-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-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-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-00002-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-00002-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-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-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-00002-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-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-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-00002-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-00002-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-00002-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-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-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-00001-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-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-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-00001-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-00002-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-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-00001-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-00002-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-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-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-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-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-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-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-00002-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-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-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-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-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-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-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00001-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-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-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-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-00001-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-00002-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-00001-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-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-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-00002-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-00002-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-00002-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-00002-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-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-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-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-00002-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-00001-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-00001-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-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-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-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-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-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-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-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-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-00002-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-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-00001-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-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-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-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-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-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-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-00001-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-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-00001-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_hardk32_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_hardk32_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_hardk32_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_hardk32_lam1p0/rollouts.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41649a391cada419343dbab02012c06490fef00712ab3ea857e506aa0c3ab5cf
+size 372847312