init

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.1",
+  "use_cache": false
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eb60ac2e66276f94acbab93fc85b1365ae78f2038e45ca1b4c77d289a2c596b
+size 4933725040

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d74156392da814c7b1eff277d056d7820415c6f2774ea00526b711bf03e7ec
+size 4915916176

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4276b1390b2c2a93ebfdb2d72e2f8921ea31249b199511cc14ce6daa6f94addd
+size 4999819336

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67260543f168df9ae9ef50cffae16f3ee5695223ad731cfb92f9b5e45635ebf5
+size 4915916184

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d1ebf27b2d6189647a1f7773110310d999715a54d71083161f698388dddfa7
+size 1913728736

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 21679054848
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e730af22820deaefb4cfb4abff6b64a88f32d22984d508de7fe9878d364a565c
+size 21679236242

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56a3891bcd17409b0ee8055f6a068ac9a2f6db543a92f46010932e0d91a2eb2
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1f1df46f5bbbe47211af84f7ec05e86f38a4e5651f5dc99de7d63e2b636b64
+size 750737

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,931 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.12734195771253845,
+  "eval_steps": 2,
+  "global_step": 18720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.896848787123102e-07,
+      "loss": 1.9119,
+      "step": 144
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.5625,
+      "learning_rate": 9.793697574246203e-07,
+      "loss": 1.9115,
+      "step": 288
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 5.96875,
+      "learning_rate": 1.4690546361369305e-06,
+      "loss": 1.9003,
+      "step": 432
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.359375,
+      "learning_rate": 1.9587395148492407e-06,
+      "loss": 1.9034,
+      "step": 576
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.390625,
+      "learning_rate": 2.4484243935615507e-06,
+      "loss": 1.9145,
+      "step": 720
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.5,
+      "learning_rate": 2.938109272273861e-06,
+      "loss": 1.8969,
+      "step": 864
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.234375,
+      "learning_rate": 3.427794150986171e-06,
+      "loss": 1.8644,
+      "step": 1008
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.328125,
+      "learning_rate": 3.917479029698481e-06,
+      "loss": 1.8823,
+      "step": 1152
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.421875,
+      "learning_rate": 4.4071639084107905e-06,
+      "loss": 1.8635,
+      "step": 1296
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.15625,
+      "learning_rate": 4.896848787123101e-06,
+      "loss": 1.8545,
+      "step": 1440
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.890625,
+      "learning_rate": 5.386533665835411e-06,
+      "loss": 1.871,
+      "step": 1584
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.046875,
+      "learning_rate": 5.876218544547722e-06,
+      "loss": 1.8609,
+      "step": 1728
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.40625,
+      "learning_rate": 6.365903423260031e-06,
+      "loss": 1.8788,
+      "step": 1872
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.140625,
+      "learning_rate": 6.855588301972342e-06,
+      "loss": 1.8672,
+      "step": 2016
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.03125,
+      "learning_rate": 7.345273180684652e-06,
+      "loss": 1.8723,
+      "step": 2160
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.078125,
+      "learning_rate": 7.834958059396963e-06,
+      "loss": 1.879,
+      "step": 2304
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.359375,
+      "learning_rate": 8.324642938109274e-06,
+      "loss": 1.8622,
+      "step": 2448
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.03125,
+      "learning_rate": 8.814327816821581e-06,
+      "loss": 1.8533,
+      "step": 2592
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.125,
+      "learning_rate": 9.304012695533892e-06,
+      "loss": 1.8503,
+      "step": 2736
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.1875,
+      "learning_rate": 9.793697574246203e-06,
+      "loss": 1.8314,
+      "step": 2880
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.0283382452958513e-05,
+      "loss": 1.835,
+      "step": 3024
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.0773067331670823e-05,
+      "loss": 1.8526,
+      "step": 3168
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.1262752210383133e-05,
+      "loss": 1.8434,
+      "step": 3312
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.03125,
+      "learning_rate": 1.1752437089095444e-05,
+      "loss": 1.8381,
+      "step": 3456
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.2242121967807753e-05,
+      "loss": 1.848,
+      "step": 3600
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.2731806846520062e-05,
+      "loss": 1.8476,
+      "step": 3744
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.3221491725232373e-05,
+      "loss": 1.8307,
+      "step": 3888
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.953125,
+      "learning_rate": 1.3711176603944684e-05,
+      "loss": 1.8328,
+      "step": 4032
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.875,
+      "learning_rate": 1.4200861482656995e-05,
+      "loss": 1.833,
+      "step": 4176
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.4690546361369304e-05,
+      "loss": 1.8559,
+      "step": 4320
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.4999994886948122e-05,
+      "loss": 1.8258,
+      "step": 4464
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.499992935844023e-05,
+      "loss": 1.8256,
+      "step": 4608
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 3.15625,
+      "learning_rate": 1.4999788341738499e-05,
+      "loss": 1.8315,
+      "step": 4752
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.796875,
+      "learning_rate": 1.4999571838262296e-05,
+      "loss": 1.8583,
+      "step": 4896
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.4999279850190762e-05,
+      "loss": 1.8287,
+      "step": 5040
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.953125,
+      "learning_rate": 1.4998912380462815e-05,
+      "loss": 1.8134,
+      "step": 5184
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.4998469432777108e-05,
+      "loss": 1.8111,
+      "step": 5328
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.015625,
+      "learning_rate": 1.4997951011591987e-05,
+      "loss": 1.8199,
+      "step": 5472
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.4997357122125465e-05,
+      "loss": 1.8188,
+      "step": 5616
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.625,
+      "learning_rate": 1.4996687770355145e-05,
+      "loss": 1.8023,
+      "step": 5760
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.015625,
+      "learning_rate": 1.4995942963018183e-05,
+      "loss": 1.8131,
+      "step": 5904
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.49951227076112e-05,
+      "loss": 1.8056,
+      "step": 6048
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.4994227012390224e-05,
+      "loss": 1.8034,
+      "step": 6192
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.4993255886370593e-05,
+      "loss": 1.8221,
+      "step": 6336
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.0,
+      "learning_rate": 1.4992209339326872e-05,
+      "loss": 1.7937,
+      "step": 6480
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.4991087381792756e-05,
+      "loss": 1.7936,
+      "step": 6624
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.4989890025060953e-05,
+      "loss": 1.804,
+      "step": 6768
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.4988617281183087e-05,
+      "loss": 1.779,
+      "step": 6912
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.4987269162969559e-05,
+      "loss": 1.7907,
+      "step": 7056
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.4985845683989435e-05,
+      "loss": 1.7945,
+      "step": 7200
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.4984346858570297e-05,
+      "loss": 1.7887,
+      "step": 7344
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.9375,
+      "learning_rate": 1.4982772701798105e-05,
+      "loss": 1.7657,
+      "step": 7488
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.4981123229517039e-05,
+      "loss": 1.7914,
+      "step": 7632
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.4979398458329347e-05,
+      "loss": 1.7716,
+      "step": 7776
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.4977598405595177e-05,
+      "loss": 1.7979,
+      "step": 7920
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.4975723089432394e-05,
+      "loss": 1.7751,
+      "step": 8064
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.4973772528716404e-05,
+      "loss": 1.7868,
+      "step": 8208
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.78125,
+      "learning_rate": 1.4971746743079972e-05,
+      "loss": 1.7974,
+      "step": 8352
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.4969645752913006e-05,
+      "loss": 1.7895,
+      "step": 8496
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.4967469579362364e-05,
+      "loss": 1.7919,
+      "step": 8640
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.4965218244331647e-05,
+      "loss": 1.7856,
+      "step": 8784
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.4962891770480958e-05,
+      "loss": 1.7777,
+      "step": 8928
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.5,
+      "learning_rate": 1.4960490181226693e-05,
+      "loss": 1.7796,
+      "step": 9072
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.49580135007413e-05,
+      "loss": 1.7769,
+      "step": 9216
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.495546175395303e-05,
+      "loss": 1.7843,
+      "step": 9360
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.495283496654569e-05,
+      "loss": 1.7763,
+      "step": 9504
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.4950133164958392e-05,
+      "loss": 1.7709,
+      "step": 9648
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.4947356376385275e-05,
+      "loss": 1.781,
+      "step": 9792
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.4944504628775233e-05,
+      "loss": 1.7831,
+      "step": 9936
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.4941577950831642e-05,
+      "loss": 1.7835,
+      "step": 10080
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.4938576372012062e-05,
+      "loss": 1.7648,
+      "step": 10224
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.4935499922527949e-05,
+      "loss": 1.774,
+      "step": 10368
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.4932348633344338e-05,
+      "loss": 1.7989,
+      "step": 10512
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.5,
+      "learning_rate": 1.492912253617955e-05,
+      "loss": 1.7624,
+      "step": 10656
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.4925821663504856e-05,
+      "loss": 1.7584,
+      "step": 10800
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.4922446048544157e-05,
+      "loss": 1.7719,
+      "step": 10944
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.4918995725273649e-05,
+      "loss": 1.7416,
+      "step": 11088
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.4915470728421481e-05,
+      "loss": 1.7587,
+      "step": 11232
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.4911871093467414e-05,
+      "loss": 1.7562,
+      "step": 11376
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.90625,
+      "learning_rate": 1.4908196856642441e-05,
+      "loss": 1.7579,
+      "step": 11520
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.625,
+      "learning_rate": 1.4904448054928444e-05,
+      "loss": 1.7734,
+      "step": 11664
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.4900624726057816e-05,
+      "loss": 1.7781,
+      "step": 11808
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.489672690851308e-05,
+      "loss": 1.7576,
+      "step": 11952
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.4892754641526498e-05,
+      "loss": 1.7561,
+      "step": 12096
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.375,
+      "learning_rate": 1.4888707965079682e-05,
+      "loss": 1.7602,
+      "step": 12240
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.4884586919903186e-05,
+      "loss": 1.7676,
+      "step": 12384
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.4880391547476106e-05,
+      "loss": 1.7546,
+      "step": 12528
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.234375,
+      "learning_rate": 1.4876121890025647e-05,
+      "loss": 1.7484,
+      "step": 12672
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.4871777990526713e-05,
+      "loss": 1.7425,
+      "step": 12816
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.4867359892701466e-05,
+      "loss": 1.7495,
+      "step": 12960
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.4862867641018887e-05,
+      "loss": 1.7478,
+      "step": 13104
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.4858301280694332e-05,
+      "loss": 1.7648,
+      "step": 13248
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.4853660857689073e-05,
+      "loss": 1.7779,
+      "step": 13392
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 6.0,
+      "learning_rate": 1.4848946418709838e-05,
+      "loss": 1.746,
+      "step": 13536
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 11.1875,
+      "learning_rate": 1.4844158011208336e-05,
+      "loss": 1.7482,
+      "step": 13680
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.4839295683380785e-05,
+      "loss": 1.7614,
+      "step": 13824
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.625,
+      "learning_rate": 1.4834359484167429e-05,
+      "loss": 1.7394,
+      "step": 13968
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.4829349463252034e-05,
+      "loss": 1.7529,
+      "step": 14112
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.48242656710614e-05,
+      "loss": 1.741,
+      "step": 14256
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.4819108158764847e-05,
+      "loss": 1.7496,
+      "step": 14400
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.4813876978273708e-05,
+      "loss": 1.7537,
+      "step": 14544
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.4808572182240786e-05,
+      "loss": 1.7435,
+      "step": 14688
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.4803193824059852e-05,
+      "loss": 1.7665,
+      "step": 14832
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.4797741957865087e-05,
+      "loss": 1.7547,
+      "step": 14976
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.4792216638530545e-05,
+      "loss": 1.7356,
+      "step": 15120
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.4786617921669603e-05,
+      "loss": 1.7397,
+      "step": 15264
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.478094586363439e-05,
+      "loss": 1.7239,
+      "step": 15408
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.4775200521515237e-05,
+      "loss": 1.7428,
+      "step": 15552
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.4769381953140084e-05,
+      "loss": 1.745,
+      "step": 15696
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.4763490217073917e-05,
+      "loss": 1.7382,
+      "step": 15840
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.5,
+      "learning_rate": 1.475752537261816e-05,
+      "loss": 1.7524,
+      "step": 15984
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.5,
+      "learning_rate": 1.475148747981009e-05,
+      "loss": 1.7288,
+      "step": 16128
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.4745376599422232e-05,
+      "loss": 1.7336,
+      "step": 16272
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.78125,
+      "learning_rate": 1.4739192792961736e-05,
+      "loss": 1.7313,
+      "step": 16416
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.4732936122669777e-05,
+      "loss": 1.7537,
+      "step": 16560
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.4726606651520911e-05,
+      "loss": 1.7428,
+      "step": 16704
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.90625,
+      "learning_rate": 1.4720204443222452e-05,
+      "loss": 1.7299,
+      "step": 16848
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.4713729562213825e-05,
+      "loss": 1.7276,
+      "step": 16992
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.5,
+      "learning_rate": 1.4707182073665921e-05,
+      "loss": 1.7312,
+      "step": 17136
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.470056204348044e-05,
+      "loss": 1.7477,
+      "step": 17280
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.4693869538289221e-05,
+      "loss": 1.7296,
+      "step": 17424
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.890625,
+      "learning_rate": 1.4687104625453587e-05,
+      "loss": 1.7353,
+      "step": 17568
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.4680267373063651e-05,
+      "loss": 1.7265,
+      "step": 17712
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.467335784993764e-05,
+      "loss": 1.7406,
+      "step": 17856
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.4666376125621198e-05,
+      "loss": 1.7313,
+      "step": 18000
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.4659322270386687e-05,
+      "loss": 1.7614,
+      "step": 18144
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.4652196355232481e-05,
+      "loss": 1.7313,
+      "step": 18288
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.5,
+      "learning_rate": 1.4644998451882254e-05,
+      "loss": 1.7307,
+      "step": 18432
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.463772863278425e-05,
+      "loss": 1.7291,
+      "step": 18576
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.4630386971110556e-05,
+      "loss": 1.7315,
+      "step": 18720
+    }
+  ],
+  "logging_steps": 144,
+  "max_steps": 147005,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1440,
+  "total_flos": 7.842747163103724e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898c6b5c29159b36432c702baa206aa7a2a7e678771271df38e494578308a1ba
+size 4984