initial

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9690424cd10d30cc5bbbf31b5ba7149fe2d1b4d1c9b3e28378c37496dfddcc
+size 4982355512

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526f616bb5753775548b200b2d5afffa862bf3a17cf53c004b1ba8d702fb5890
+size 4982541984

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e8a19d8abfcd2f197de65252a587827278bcda8268f280b3b306d3b20cd0ad
+size 629445872

model.safetensors.index.json

@@ -0,0 +1,459 @@
+{
+  "metadata": {
+    "total_size": 10594293760
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.final_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.final_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.dense.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.dense.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.dense.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.dense.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "score.weight": "model-00003-of-00003.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3141cfe53ff93508ae18e5cfa5aff298fa69b9a04de873a70ddbe70aea93c1
+size 104546

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa85386c8d4b187f87b0e4132384e2fc7b6af5deff7544bcce16e885d86cad3e
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4436d514eceb4bbd13539f8ffdc444ba7664690927a11f3544198c6186935741
+size 1064

trainer_state.json

@@ -0,0 +1,957 @@
+{
+  "best_metric": 1.3127143383026123,
+  "best_model_checkpoint": "./results/checkpoint-12000",
+  "epoch": 2.9239766081871346,
+  "eval_steps": 1000,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 33.17779541015625,
+      "learning_rate": 7.711038961038962e-07,
+      "loss": 3.4711,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 37.28006362915039,
+      "learning_rate": 1.5827922077922078e-06,
+      "loss": 3.5437,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 36.98271942138672,
+      "learning_rate": 2.3944805194805195e-06,
+      "loss": 3.3504,
+      "step": 300
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 40.87253952026367,
+      "learning_rate": 3.2061688311688315e-06,
+      "loss": 3.0778,
+      "step": 400
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 38.7576904296875,
+      "learning_rate": 4.017857142857143e-06,
+      "loss": 2.7729,
+      "step": 500
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 32.913177490234375,
+      "learning_rate": 4.829545454545455e-06,
+      "loss": 2.4744,
+      "step": 600
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 25.826562881469727,
+      "learning_rate": 5.641233766233767e-06,
+      "loss": 2.0562,
+      "step": 700
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 18.770437240600586,
+      "learning_rate": 6.452922077922078e-06,
+      "loss": 1.8168,
+      "step": 800
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 25.943300247192383,
+      "learning_rate": 7.264610389610391e-06,
+      "loss": 1.6557,
+      "step": 900
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 19.324600219726562,
+      "learning_rate": 8.076298701298701e-06,
+      "loss": 1.6403,
+      "step": 1000
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 1.5921334028244019,
+      "eval_runtime": 26.2796,
+      "eval_samples_per_second": 138.815,
+      "eval_steps_per_second": 17.352,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 16.94064712524414,
+      "learning_rate": 8.887987012987014e-06,
+      "loss": 1.6253,
+      "step": 1100
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 30.26157569885254,
+      "learning_rate": 9.699675324675324e-06,
+      "loss": 1.5771,
+      "step": 1200
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 16.245685577392578,
+      "learning_rate": 9.999202318014557e-06,
+      "loss": 1.5458,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 26.97745132446289,
+      "learning_rate": 9.994661021925825e-06,
+      "loss": 1.5736,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 16.87709617614746,
+      "learning_rate": 9.986104618610859e-06,
+      "loss": 1.5701,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 17.941173553466797,
+      "learning_rate": 9.973539986389656e-06,
+      "loss": 1.624,
+      "step": 1600
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 19.09428596496582,
+      "learning_rate": 9.956977225716559e-06,
+      "loss": 1.574,
+      "step": 1700
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 20.125308990478516,
+      "learning_rate": 9.936429651060717e-06,
+      "loss": 1.4985,
+      "step": 1800
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 20.364625930786133,
+      "learning_rate": 9.911913780202837e-06,
+      "loss": 1.6142,
+      "step": 1900
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 41.57521438598633,
+      "learning_rate": 9.883449320956886e-06,
+      "loss": 1.5333,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 1.4966720342636108,
+      "eval_runtime": 26.2841,
+      "eval_samples_per_second": 138.791,
+      "eval_steps_per_second": 17.349,
+      "step": 2000
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 11.074485778808594,
+      "learning_rate": 9.851402406341606e-06,
+      "loss": 1.5664,
+      "step": 2100
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 20.685998916625977,
+      "learning_rate": 9.815151429615968e-06,
+      "loss": 1.5363,
+      "step": 2200
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 26.39971923828125,
+      "learning_rate": 9.775029649803677e-06,
+      "loss": 1.4989,
+      "step": 2300
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 20.003503799438477,
+      "learning_rate": 9.731069319994049e-06,
+      "loss": 1.4553,
+      "step": 2400
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 15.458146095275879,
+      "learning_rate": 9.683305779009301e-06,
+      "loss": 1.4732,
+      "step": 2500
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 13.668593406677246,
+      "learning_rate": 9.631777422996384e-06,
+      "loss": 1.4907,
+      "step": 2600
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 18.606111526489258,
+      "learning_rate": 9.576525674561088e-06,
+      "loss": 1.5343,
+      "step": 2700
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 23.913843154907227,
+      "learning_rate": 9.517594949469258e-06,
+      "loss": 1.4561,
+      "step": 2800
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 23.21706771850586,
+      "learning_rate": 9.45503262094184e-06,
+      "loss": 1.4558,
+      "step": 2900
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 18.72185516357422,
+      "learning_rate": 9.388888981572521e-06,
+      "loss": 1.4404,
+      "step": 3000
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 1.4381717443466187,
+      "eval_runtime": 26.2702,
+      "eval_samples_per_second": 138.865,
+      "eval_steps_per_second": 17.358,
+      "step": 3000
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 21.71692657470703,
+      "learning_rate": 9.319217202898511e-06,
+      "loss": 1.46,
+      "step": 3100
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 23.30307960510254,
+      "learning_rate": 9.246073292657036e-06,
+      "loss": 1.4993,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 17.032285690307617,
+      "learning_rate": 9.169516049761827e-06,
+      "loss": 1.426,
+      "step": 3300
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 25.84226417541504,
+      "learning_rate": 9.089607017035875e-06,
+      "loss": 1.45,
+      "step": 3400
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 15.991667747497559,
+      "learning_rate": 9.006410431738393e-06,
+      "loss": 1.4416,
+      "step": 3500
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 25.301294326782227,
+      "learning_rate": 8.919993173925775e-06,
+      "loss": 1.4338,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 21.2309513092041,
+      "learning_rate": 8.830424712688075e-06,
+      "loss": 1.4441,
+      "step": 3700
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 27.830860137939453,
+      "learning_rate": 8.737777050304201e-06,
+      "loss": 1.4336,
+      "step": 3800
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 13.40440845489502,
+      "learning_rate": 8.642124664360743e-06,
+      "loss": 1.4462,
+      "step": 3900
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 12.035055160522461,
+      "learning_rate": 8.543544447880932e-06,
+      "loss": 1.3731,
+      "step": 4000
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 1.4002097845077515,
+      "eval_runtime": 26.2861,
+      "eval_samples_per_second": 138.78,
+      "eval_steps_per_second": 17.348,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 26.902008056640625,
+      "learning_rate": 8.442115647511902e-06,
+      "loss": 1.3534,
+      "step": 4100
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 22.86239242553711,
+      "learning_rate": 8.338975181963125e-06,
+      "loss": 1.423,
+      "step": 4200
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 14.839469909667969,
+      "learning_rate": 8.232122458995769e-06,
+      "loss": 1.4046,
+      "step": 4300
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 11.413098335266113,
+      "learning_rate": 8.122671497992996e-06,
+      "loss": 1.4214,
+      "step": 4400
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 12.68773078918457,
+      "learning_rate": 8.010710284374138e-06,
+      "loss": 1.3689,
+      "step": 4500
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 26.15570640563965,
+      "learning_rate": 7.896328821499958e-06,
+      "loss": 1.4359,
+      "step": 4600
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 17.21908950805664,
+      "learning_rate": 7.779619058320773e-06,
+      "loss": 1.3365,
+      "step": 4700
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 13.629748344421387,
+      "learning_rate": 7.660674815460536e-06,
+      "loss": 1.4184,
+      "step": 4800
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 18.672447204589844,
+      "learning_rate": 7.539591709796332e-06,
+      "loss": 1.4249,
+      "step": 4900
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 19.526599884033203,
+      "learning_rate": 7.4164670775939064e-06,
+      "loss": 1.4118,
+      "step": 5000
+    },
+    {
+      "epoch": 1.22,
+      "eval_loss": 1.371161699295044,
+      "eval_runtime": 26.2776,
+      "eval_samples_per_second": 138.826,
+      "eval_steps_per_second": 17.353,
+      "step": 5000
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 21.340396881103516,
+      "learning_rate": 7.291399896260997e-06,
+      "loss": 1.4033,
+      "step": 5100
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 23.687089920043945,
+      "learning_rate": 7.164490704781396e-06,
+      "loss": 1.3883,
+      "step": 5200
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 24.734172821044922,
+      "learning_rate": 7.035841522893689e-06,
+      "loss": 1.4099,
+      "step": 5300
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 10.669279098510742,
+      "learning_rate": 6.90555576907965e-06,
+      "loss": 1.3431,
+      "step": 5400
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 14.781868934631348,
+      "learning_rate": 6.7737381774282e-06,
+      "loss": 1.3807,
+      "step": 5500
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 25.798255920410156,
+      "learning_rate": 6.640494713441796e-06,
+      "loss": 1.3509,
+      "step": 5600
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 24.66495704650879,
+      "learning_rate": 6.505932488852898e-06,
+      "loss": 1.3313,
+      "step": 5700
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 18.16162872314453,
+      "learning_rate": 6.370159675519001e-06,
+      "loss": 1.3439,
+      "step": 5800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 19.407123565673828,
+      "learning_rate": 6.233285418465477e-06,
+      "loss": 1.386,
+      "step": 5900
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 17.162641525268555,
+      "learning_rate": 6.095419748146076e-06,
+      "loss": 1.3701,
+      "step": 6000
+    },
+    {
+      "epoch": 1.46,
+      "eval_loss": 1.3507885932922363,
+      "eval_runtime": 26.3071,
+      "eval_samples_per_second": 138.67,
+      "eval_steps_per_second": 17.334,
+      "step": 6000
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 17.1251220703125,
+      "learning_rate": 5.9566734919916746e-06,
+      "loss": 1.3748,
+      "step": 6100
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 13.51869010925293,
+      "learning_rate": 5.817158185318335e-06,
+      "loss": 1.3594,
+      "step": 6200
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 13.84580135345459,
+      "learning_rate": 5.678390585745784e-06,
+      "loss": 1.3541,
+      "step": 6300
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 13.059226036071777,
+      "learning_rate": 5.537679049589568e-06,
+      "loss": 1.3485,
+      "step": 6400
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 15.174361228942871,
+      "learning_rate": 5.396535284093278e-06,
+      "loss": 1.3676,
+      "step": 6500
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 27.069568634033203,
+      "learning_rate": 5.255072751882363e-06,
+      "loss": 1.3789,
+      "step": 6600
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 18.00585174560547,
+      "learning_rate": 5.113405171832404e-06,
+      "loss": 1.3779,
+      "step": 6700
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 16.768413543701172,
+      "learning_rate": 4.971646427652806e-06,
+      "loss": 1.3338,
+      "step": 6800
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 24.71240234375,
+      "learning_rate": 4.829910476337972e-06,
+      "loss": 1.405,
+      "step": 6900
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 11.74875259399414,
+      "learning_rate": 4.688311256559587e-06,
+      "loss": 1.3563,
+      "step": 7000
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 1.3359144926071167,
+      "eval_runtime": 26.3043,
+      "eval_samples_per_second": 138.684,
+      "eval_steps_per_second": 17.336,
+      "step": 7000
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 20.35810661315918,
+      "learning_rate": 4.546962597073607e-06,
+      "loss": 1.3103,
+      "step": 7100
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 19.12173080444336,
+      "learning_rate": 4.405978125215627e-06,
+      "loss": 1.3983,
+      "step": 7200
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 24.56060218811035,
+      "learning_rate": 4.265471175558156e-06,
+      "loss": 1.3357,
+      "step": 7300
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 17.104286193847656,
+      "learning_rate": 4.125554698803241e-06,
+      "loss": 1.3546,
+      "step": 7400
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 18.4068603515625,
+      "learning_rate": 3.986341170983672e-06,
+      "loss": 1.3774,
+      "step": 7500
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 15.030558586120605,
+      "learning_rate": 3.847942503045776e-06,
+      "loss": 1.3573,
+      "step": 7600
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 25.187389373779297,
+      "learning_rate": 3.7104699508864606e-06,
+      "loss": 1.3029,
+      "step": 7700
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 14.766794204711914,
+      "learning_rate": 3.5740340259168383e-06,
+      "loss": 1.3441,
+      "step": 7800
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 15.01491928100586,
+      "learning_rate": 3.4387444062243453e-06,
+      "loss": 1.3704,
+      "step": 7900
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 14.977212905883789,
+      "learning_rate": 3.3047098484047314e-06,
+      "loss": 1.3027,
+      "step": 8000
+    },
+    {
+      "epoch": 1.95,
+      "eval_loss": 1.3263477087020874,
+      "eval_runtime": 26.2892,
+      "eval_samples_per_second": 138.764,
+      "eval_steps_per_second": 17.346,
+      "step": 8000
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 22.42038917541504,
+      "learning_rate": 3.172038100134823e-06,
+      "loss": 1.3301,
+      "step": 8100
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.849152565002441,
+      "learning_rate": 3.040835813556352e-06,
+      "loss": 1.3057,
+      "step": 8200
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 13.574536323547363,
+      "learning_rate": 2.911208459540442e-06,
+      "loss": 1.3523,
+      "step": 8300
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 21.791500091552734,
+      "learning_rate": 2.783260242901694e-06,
+      "loss": 1.3743,
+      "step": 8400
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 19.42542266845703,
+      "learning_rate": 2.6583465257615547e-06,
+      "loss": 1.3198,
+      "step": 8500
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 10.656351089477539,
+      "learning_rate": 2.5340443850538414e-06,
+      "loss": 1.3312,
+      "step": 8600
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 15.180091857910156,
+      "learning_rate": 2.4117245763133403e-06,
+      "loss": 1.3036,
+      "step": 8700
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 11.437941551208496,
+      "learning_rate": 2.2914854299664442e-06,
+      "loss": 1.3206,
+      "step": 8800
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 12.555315017700195,
+      "learning_rate": 2.173423603837027e-06,
+      "loss": 1.3197,
+      "step": 8900
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 11.639187812805176,
+      "learning_rate": 2.0576340054451755e-06,
+      "loss": 1.3416,
+      "step": 9000
+    },
+    {
+      "epoch": 2.19,
+      "eval_loss": 1.319271206855774,
+      "eval_runtime": 26.3038,
+      "eval_samples_per_second": 138.687,
+      "eval_steps_per_second": 17.336,
+      "step": 9000
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 23.691478729248047,
+      "learning_rate": 1.944209715712927e-06,
+      "loss": 1.3242,
+      "step": 9100
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 15.768092155456543,
+      "learning_rate": 1.8332419141384222e-06,
+      "loss": 1.3714,
+      "step": 9200
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 14.769400596618652,
+      "learning_rate": 1.7248198054985233e-06,
+      "loss": 1.3876,
+      "step": 9300
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 14.024765014648438,
+      "learning_rate": 1.6190305481389102e-06,
+      "loss": 1.3597,
+      "step": 9400
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 14.97281265258789,
+      "learning_rate": 1.5159591839092319e-06,
+      "loss": 1.3216,
+      "step": 9500
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 27.76974868774414,
+      "learning_rate": 1.415688569799686e-06,
+      "loss": 1.3462,
+      "step": 9600
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 23.970733642578125,
+      "learning_rate": 1.3182993113339553e-06,
+      "loss": 1.3334,
+      "step": 9700
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 15.778496742248535,
+      "learning_rate": 1.223869697772052e-06,
+      "loss": 1.3404,
+      "step": 9800
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 16.48326873779297,
+      "learning_rate": 1.1324756391751658e-06,
+      "loss": 1.3361,
+      "step": 9900
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 19.057518005371094,
+      "learning_rate": 1.0441906053830887e-06,
+      "loss": 1.2863,
+      "step": 10000
+    },
+    {
+      "epoch": 2.44,
+      "eval_loss": 1.315341830253601,
+      "eval_runtime": 26.3084,
+      "eval_samples_per_second": 138.663,
+      "eval_steps_per_second": 17.333,
+      "step": 10000
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 15.053688049316406,
+      "learning_rate": 9.590855669533e-07,
+      "loss": 1.3567,
+      "step": 10100
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 16.501331329345703,
+      "learning_rate": 8.77228938109167e-07,
+      "loss": 1.336,
+      "step": 10200
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 10.03864860534668,
+      "learning_rate": 7.986865217431261e-07,
+      "loss": 1.3121,
+      "step": 10300
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 14.122137069702148,
+      "learning_rate": 7.235214565190696e-07,
+      "loss": 1.3092,
+      "step": 10400
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 25.29042625427246,
+      "learning_rate": 6.517941661164445e-07,
+      "loss": 1.3221,
+      "step": 10500
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 17.808534622192383,
+      "learning_rate": 5.835623106568783e-07,
+      "loss": 1.3403,
+      "step": 10600
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 15.087233543395996,
+      "learning_rate": 5.188807403523721e-07,
+      "loss": 1.3124,
+      "step": 10700
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 15.44356918334961,
+      "learning_rate": 4.5780145141231526e-07,
+      "loss": 1.3397,
+      "step": 10800
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 18.34058952331543,
+      "learning_rate": 4.0037354424478926e-07,
+      "loss": 1.3471,
+      "step": 10900
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 13.286628723144531,
+      "learning_rate": 3.466431839857326e-07,
+      "loss": 1.329,
+      "step": 11000
+    },
+    {
+      "epoch": 2.68,
+      "eval_loss": 1.3130227327346802,
+      "eval_runtime": 26.3079,
+      "eval_samples_per_second": 138.665,
+      "eval_steps_per_second": 17.333,
+      "step": 11000
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 25.197416305541992,
+      "learning_rate": 2.9713480847324947e-07,
+      "loss": 1.3656,
+      "step": 11100
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 16.662456512451172,
+      "learning_rate": 2.508881149660197e-07,
+      "loss": 1.343,
+      "step": 11200
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 19.900924682617188,
+      "learning_rate": 2.0845913668792794e-07,
+      "loss": 1.3524,
+      "step": 11300
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 12.059335708618164,
+      "learning_rate": 1.698819814385927e-07,
+      "loss": 1.3436,
+      "step": 11400
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 20.73145294189453,
+      "learning_rate": 1.3518766061480726e-07,
+      "loss": 1.3223,
+      "step": 11500
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 13.213232040405273,
+      "learning_rate": 1.0440406428111116e-07,
+      "loss": 1.3015,
+      "step": 11600
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 17.85313606262207,
+      "learning_rate": 7.755593874952505e-08,
+      "loss": 1.2938,
+      "step": 11700
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 18.61409568786621,
+      "learning_rate": 5.4664866686491845e-08,
+      "loss": 1.3169,
+      "step": 11800
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 17.018802642822266,
+      "learning_rate": 3.574924976300742e-08,
+      "loss": 1.2538,
+      "step": 11900
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 22.11118507385254,
+      "learning_rate": 2.082429386188578e-08,
+      "loss": 1.3278,
+      "step": 12000
+    },
+    {
+      "epoch": 2.92,
+      "eval_loss": 1.3127143383026123,
+      "eval_runtime": 26.3216,
+      "eval_samples_per_second": 138.593,
+      "eval_steps_per_second": 17.324,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 12312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 3.087179791853568e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}