First model version

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8280511067070df956f3bf9bd574d7d55ff09643e6a2e03ebda2a52531a6816
+size 9689093137

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48dfc013eef30de34a0c40c2089e0c57263a74bd1bfb99546153f1c3557a776
+size 9689093137

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c321676f360a75e78ae7b1b4045e9a17ce152faa02ee0609baf14c2ac55bf565
+size 9689093137

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb9726a29fcc90ab6d07d79a959b8fdf7c62bc8fdac5a127e850a66a5c5b380
+size 9689093137

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e956796ca12c4df3e9794efbcb85e1e4704ea639f2a8277361a78711f2f8dc
+size 9689093137

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b84131f56294a78d3ec16e607727effb8de56ae66f2fe9da281e798b273b8be
+size 9190067865

pytorch_model.bin.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 67488104448
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00007-of-00007.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.norm.weight": "pytorch_model-00007-of-00007.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "left",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_first": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.3625062153889583,
+    "train_runtime": 97159.7175,
+    "train_samples_per_second": 5.892,
+    "train_steps_per_second": 0.023
+}

trainer_state.json

@@ -0,0 +1,1366 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9991059454626732,
+  "eval_steps": 500,
+  "global_step": 2236,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9999012995785765e-05,
+      "loss": 0.5699,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.999605217797852e-05,
+      "loss": 0.5008,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9991118131046197e-05,
+      "loss": 0.4814,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.998421182897382e-05,
+      "loss": 0.4777,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9975334635071234e-05,
+      "loss": 0.4618,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9964488301704004e-05,
+      "loss": 0.4635,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9951674969947477e-05,
+      "loss": 0.4641,
+      "step": 70
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.993689716916414e-05,
+      "loss": 0.454,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.992015781650432e-05,
+      "loss": 0.4682,
+      "step": 90
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9901460216330344e-05,
+      "loss": 0.4651,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.988080805956425e-05,
+      "loss": 0.4528,
+      "step": 110
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9858205422959183e-05,
+      "loss": 0.4495,
+      "step": 120
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.983365676829466e-05,
+      "loss": 0.4425,
+      "step": 130
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9807166941495813e-05,
+      "loss": 0.46,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9778741171676766e-05,
+      "loss": 0.4544,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9748385070108444e-05,
+      "loss": 0.4361,
+      "step": 160
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9716104629110882e-05,
+      "loss": 0.4467,
+      "step": 170
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9681906220870345e-05,
+      "loss": 0.4426,
+      "step": 180
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9645796596181436e-05,
+      "loss": 0.4579,
+      "step": 190
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9607782883114507e-05,
+      "loss": 0.457,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.956787258560856e-05,
+      "loss": 0.4436,
+      "step": 210
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.952607358198996e-05,
+      "loss": 0.4478,
+      "step": 220
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9482394123417246e-05,
+      "loss": 0.4442,
+      "step": 230
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9436842832252363e-05,
+      "loss": 0.44,
+      "step": 240
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9389428700358575e-05,
+      "loss": 0.4482,
+      "step": 250
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9340161087325483e-05,
+      "loss": 0.4399,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9289049718621423e-05,
+      "loss": 0.4354,
+      "step": 270
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9236104683673656e-05,
+      "loss": 0.4495,
+      "step": 280
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9181336433876704e-05,
+      "loss": 0.4378,
+      "step": 290
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9124755780529243e-05,
+      "loss": 0.439,
+      "step": 300
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9066373892699933e-05,
+      "loss": 0.4472,
+      "step": 310
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9006202295022632e-05,
+      "loss": 0.4445,
+      "step": 320
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.894425286542144e-05,
+      "loss": 0.44,
+      "step": 330
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.8880537832765976e-05,
+      "loss": 0.4405,
+      "step": 340
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.8815069774457386e-05,
+      "loss": 0.4499,
+      "step": 350
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.874786161394556e-05,
+      "loss": 0.4314,
+      "step": 360
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8678926618178034e-05,
+      "loss": 0.4409,
+      "step": 370
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8608278394981068e-05,
+      "loss": 0.4378,
+      "step": 380
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8535930890373467e-05,
+      "loss": 0.4356,
+      "step": 390
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8461898385813622e-05,
+      "loss": 0.447,
+      "step": 400
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8386195495380324e-05,
+      "loss": 0.4323,
+      "step": 410
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8308837162887964e-05,
+      "loss": 0.4299,
+      "step": 420
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 0.4375,
+      "step": 430
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8149215577897397e-05,
+      "loss": 0.4494,
+      "step": 440
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8066983834834607e-05,
+      "loss": 0.4371,
+      "step": 450
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.7983159662363582e-05,
+      "loss": 0.4293,
+      "step": 460
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.7897759607446627e-05,
+      "loss": 0.4389,
+      "step": 470
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.7810800528126556e-05,
+      "loss": 0.4469,
+      "step": 480
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.772229959019892e-05,
+      "loss": 0.4352,
+      "step": 490
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.7632274263823458e-05,
+      "loss": 0.4411,
+      "step": 500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7540742320075476e-05,
+      "loss": 0.4339,
+      "step": 510
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.744772182743782e-05,
+      "loss": 0.4284,
+      "step": 520
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7353231148234134e-05,
+      "loss": 0.4226,
+      "step": 530
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.7257288935004134e-05,
+      "loss": 0.4348,
+      "step": 540
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.715991412682158e-05,
+      "loss": 0.428,
+      "step": 550
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.706112594555568e-05,
+      "loss": 0.448,
+      "step": 560
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.6960943892076672e-05,
+      "loss": 0.4362,
+      "step": 570
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.6859387742406358e-05,
+      "loss": 0.4293,
+      "step": 580
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.6756477543814276e-05,
+      "loss": 0.434,
+      "step": 590
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.6652233610860368e-05,
+      "loss": 0.4496,
+      "step": 600
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.6546676521384856e-05,
+      "loss": 0.431,
+      "step": 610
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.6439827112446177e-05,
+      "loss": 0.433,
+      "step": 620
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.6331706476207708e-05,
+      "loss": 0.4351,
+      "step": 630
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6222335955774178e-05,
+      "loss": 0.4408,
+      "step": 640
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.6111737140978495e-05,
+      "loss": 0.4159,
+      "step": 650
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.5999931864119923e-05,
+      "loss": 0.4304,
+      "step": 660
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.588694219565435e-05,
+      "loss": 0.4298,
+      "step": 670
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.5772790439837557e-05,
+      "loss": 0.4263,
+      "step": 680
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5657499130322366e-05,
+      "loss": 0.4255,
+      "step": 690
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5541091025710436e-05,
+      "loss": 0.4297,
+      "step": 700
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.542358910505974e-05,
+      "loss": 0.4261,
+      "step": 710
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5305016563348444e-05,
+      "loss": 0.4195,
+      "step": 720
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.5185396806896231e-05,
+      "loss": 0.4323,
+      "step": 730
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.5064753448743834e-05,
+      "loss": 0.4084,
+      "step": 740
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.4943110303991844e-05,
+      "loss": 0.4241,
+      "step": 750
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.4820491385099555e-05,
+      "loss": 0.4348,
+      "step": 760
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.4696920897144915e-05,
+      "loss": 0.4237,
+      "step": 770
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.4572423233046386e-05,
+      "loss": 0.423,
+      "step": 780
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4447022968747803e-05,
+      "loss": 0.4251,
+      "step": 790
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4320744858367026e-05,
+      "loss": 0.4404,
+      "step": 800
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.419361382930948e-05,
+      "loss": 0.4412,
+      "step": 810
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4065654977347452e-05,
+      "loss": 0.4263,
+      "step": 820
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.3936893561666171e-05,
+      "loss": 0.4282,
+      "step": 830
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.3807354999877615e-05,
+      "loss": 0.4147,
+      "step": 840
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.3677064863003069e-05,
+      "loss": 0.4091,
+      "step": 850
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 0.4261,
+      "step": 860
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.3414332884811847e-05,
+      "loss": 0.4143,
+      "step": 870
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3281942907009113e-05,
+      "loss": 0.4213,
+      "step": 880
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3148905070910363e-05,
+      "loss": 0.4314,
+      "step": 890
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3015245638296565e-05,
+      "loss": 0.4073,
+      "step": 900
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.2880990993652379e-05,
+      "loss": 0.4277,
+      "step": 910
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.2746167638957808e-05,
+      "loss": 0.4176,
+      "step": 920
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.2610802188456708e-05,
+      "loss": 0.4262,
+      "step": 930
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2474921363403096e-05,
+      "loss": 0.4248,
+      "step": 940
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2338551986786368e-05,
+      "loss": 0.4309,
+      "step": 950
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2201720978036411e-05,
+      "loss": 0.4248,
+      "step": 960
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2064455347709672e-05,
+      "loss": 0.4252,
+      "step": 970
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.1926782192157276e-05,
+      "loss": 0.4279,
+      "step": 980
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.1788728688176163e-05,
+      "loss": 0.4089,
+      "step": 990
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.165032208764438e-05,
+      "loss": 0.4057,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1511589712141527e-05,
+      "loss": 0.4326,
+      "step": 1010
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1372558947555457e-05,
+      "loss": 0.4131,
+      "step": 1020
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.123325723867628e-05,
+      "loss": 0.4313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1093712083778748e-05,
+      "loss": 0.4109,
+      "step": 1040
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.0953951029194039e-05,
+      "loss": 0.417,
+      "step": 1050
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0814001663872133e-05,
+      "loss": 0.4012,
+      "step": 1060
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.06738916139357e-05,
+      "loss": 0.4163,
+      "step": 1070
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0533648537226688e-05,
+      "loss": 0.4143,
+      "step": 1080
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0393300117846648e-05,
+      "loss": 0.4175,
+      "step": 1090
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0252874060691847e-05,
+      "loss": 0.4142,
+      "step": 1100
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0112398085984333e-05,
+      "loss": 0.4129,
+      "step": 1110
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.971899923799915e-06,
+      "loss": 0.4014,
+      "step": 1120
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.831407308594216e-06,
+      "loss": 0.3032,
+      "step": 1130
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.690947973727905e-06,
+      "loss": 0.2998,
+      "step": 1140
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.550549645992061e-06,
+      "loss": 0.2883,
+      "step": 1150
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.410240040134918e-06,
+      "loss": 0.2953,
+      "step": 1160
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.270046853390924e-06,
+      "loss": 0.2913,
+      "step": 1170
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.129997760013316e-06,
+      "loss": 0.2864,
+      "step": 1180
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 8.99012040581116e-06,
+      "loss": 0.2919,
+      "step": 1190
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.850442402692068e-06,
+      "loss": 0.2979,
+      "step": 1200
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.710991323211586e-06,
+      "loss": 0.2941,
+      "step": 1210
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.571794695130343e-06,
+      "loss": 0.2958,
+      "step": 1220
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.432879995980036e-06,
+      "loss": 0.3008,
+      "step": 1230
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.294274647639369e-06,
+      "loss": 0.2997,
+      "step": 1240
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.156006010920919e-06,
+      "loss": 0.286,
+      "step": 1250
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.018101380170123e-06,
+      "loss": 0.2928,
+      "step": 1260
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.88058797787732e-06,
+      "loss": 0.2895,
+      "step": 1270
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.743492949304023e-06,
+      "loss": 0.2956,
+      "step": 1280
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.606843357124426e-06,
+      "loss": 0.3037,
+      "step": 1290
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.470666176083193e-06,
+      "loss": 0.2887,
+      "step": 1300
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.334988287670648e-06,
+      "loss": 0.2961,
+      "step": 1310
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.199836474816313e-06,
+      "loss": 0.2971,
+      "step": 1320
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.0652374166019625e-06,
+      "loss": 0.2943,
+      "step": 1330
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.931217682995124e-06,
+      "loss": 0.295,
+      "step": 1340
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.797803729604183e-06,
+      "loss": 0.2804,
+      "step": 1350
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.665021892455978e-06,
+      "loss": 0.2914,
+      "step": 1360
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.532898382797082e-06,
+      "loss": 0.2911,
+      "step": 1370
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.401459281919656e-06,
+      "loss": 0.2905,
+      "step": 1380
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.270730536013e-06,
+      "loss": 0.2967,
+      "step": 1390
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.140737951041742e-06,
+      "loss": 0.2994,
+      "step": 1400
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.011507187651715e-06,
+      "loss": 0.2757,
+      "step": 1410
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.883063756104535e-06,
+      "loss": 0.2833,
+      "step": 1420
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.755433011241851e-06,
+      "loss": 0.2855,
+      "step": 1430
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.6286401474802675e-06,
+      "loss": 0.2988,
+      "step": 1440
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.502710193837959e-06,
+      "loss": 0.2888,
+      "step": 1450
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.377668008993921e-06,
+      "loss": 0.2933,
+      "step": 1460
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.2535382763808185e-06,
+      "loss": 0.2948,
+      "step": 1470
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.1303454993125075e-06,
+      "loss": 0.2921,
+      "step": 1480
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.008113996147006e-06,
+      "loss": 0.3003,
+      "step": 1490
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.886867895486065e-06,
+      "loss": 0.3004,
+      "step": 1500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.766631131412136e-06,
+      "loss": 0.2897,
+      "step": 1510
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.647427438763806e-06,
+      "loss": 0.3048,
+      "step": 1520
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.52928034845046e-06,
+      "loss": 0.2899,
+      "step": 1530
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.412213182807315e-06,
+      "loss": 0.2891,
+      "step": 1540
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.296249050991529e-06,
+      "loss": 0.286,
+      "step": 1550
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.181410844420473e-06,
+      "loss": 0.293,
+      "step": 1560
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.067721232252909e-06,
+      "loss": 0.2904,
+      "step": 1570
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.955202656914102e-06,
+      "loss": 0.2909,
+      "step": 1580
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.843877329665662e-06,
+      "loss": 0.2997,
+      "step": 1590
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.7337672262210155e-06,
+      "loss": 0.2808,
+      "step": 1600
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.6248940824073955e-06,
+      "loss": 0.2919,
+      "step": 1610
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.5172793898751446e-06,
+      "loss": 0.2887,
+      "step": 1620
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.410944391855279e-06,
+      "loss": 0.28,
+      "step": 1630
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.3059100789660215e-06,
+      "loss": 0.2828,
+      "step": 1640
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.202197185069279e-06,
+      "loss": 0.2822,
+      "step": 1650
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.09982618317771e-06,
+      "loss": 0.2871,
+      "step": 1660
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.9988172814133774e-06,
+      "loss": 0.2903,
+      "step": 1670
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.899190419018616e-06,
+      "loss": 0.2871,
+      "step": 1680
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.8009652624200436e-06,
+      "loss": 0.2926,
+      "step": 1690
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.7041612013463535e-06,
+      "loss": 0.2751,
+      "step": 1700
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.6087973450007953e-06,
+      "loss": 0.2815,
+      "step": 1710
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.514892518288988e-06,
+      "loss": 0.284,
+      "step": 1720
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.422465258102875e-06,
+      "loss": 0.2926,
+      "step": 1730
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.331533809661518e-06,
+      "loss": 0.2919,
+      "step": 1740
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.242116122909478e-06,
+      "loss": 0.2879,
+      "step": 1750
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.154229848973486e-06,
+      "loss": 0.2961,
+      "step": 1760
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.0678923366780934e-06,
+      "loss": 0.2901,
+      "step": 1770
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.983120629120998e-06,
+      "loss": 0.292,
+      "step": 1780
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.899931460308716e-06,
+      "loss": 0.2862,
+      "step": 1790
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.8183412518532907e-06,
+      "loss": 0.2859,
+      "step": 1800
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.738366109730638e-06,
+      "loss": 0.2837,
+      "step": 1810
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.660021821101222e-06,
+      "loss": 0.2793,
+      "step": 1820
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.5833238511936467e-06,
+      "loss": 0.2861,
+      "step": 1830
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.5082873402518172e-06,
+      "loss": 0.2963,
+      "step": 1840
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.4349271005462395e-06,
+      "loss": 0.2782,
+      "step": 1850
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.3632576134500653e-06,
+      "loss": 0.2865,
+      "step": 1860
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.2932930265804478e-06,
+      "loss": 0.2931,
+      "step": 1870
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.225047151005807e-06,
+      "loss": 0.2893,
+      "step": 1880
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.158533458519504e-06,
+      "loss": 0.282,
+      "step": 1890
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.0937650789804944e-06,
+      "loss": 0.2935,
+      "step": 1900
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0307547977214916e-06,
+      "loss": 0.2734,
+      "step": 1910
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 9.695150530251207e-07,
+      "loss": 0.2867,
+      "step": 1920
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.100579336686033e-07,
+      "loss": 0.2809,
+      "step": 1930
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.523951765374117e-07,
+      "loss": 0.293,
+      "step": 1940
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.965381643084069e-07,
+      "loss": 0.2901,
+      "step": 1950
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.424979232028784e-07,
+      "loss": 0.2823,
+      "step": 1960
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 6.902851208099704e-07,
+      "loss": 0.2775,
+      "step": 1970
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 6.399100639808819e-07,
+      "loss": 0.2886,
+      "step": 1980
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5.913826967942926e-07,
+      "loss": 0.2761,
+      "step": 1990
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.44712598593381e-07,
+      "loss": 0.2834,
+      "step": 2000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.9990898209487e-07,
+      "loss": 0.2767,
+      "step": 2010
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.5698069157042e-07,
+      "loss": 0.2769,
+      "step": 2020
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.159362011007606e-07,
+      "loss": 0.2755,
+      "step": 2030
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.76783612902909e-07,
+      "loss": 0.2863,
+      "step": 2040
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.395306557307698e-07,
+      "loss": 0.2767,
+      "step": 2050
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.041846833494888e-07,
+      "loss": 0.2901,
+      "step": 2060
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.7075267308380726e-07,
+      "loss": 0.282,
+      "step": 2070
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.392412244407294e-07,
+      "loss": 0.2734,
+      "step": 2080
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.0965655780677441e-07,
+      "loss": 0.2821,
+      "step": 2090
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8200451322007208e-07,
+      "loss": 0.2871,
+      "step": 2100
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.562905492175326e-07,
+      "loss": 0.2856,
+      "step": 2110
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.3251974175732097e-07,
+      "loss": 0.2851,
+      "step": 2120
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.1069678321686372e-07,
+      "loss": 0.2917,
+      "step": 2130
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 9.08259814665724e-08,
+      "loss": 0.2917,
+      "step": 2140
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 7.291125901946027e-08,
+      "loss": 0.2899,
+      "step": 2150
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.695615225683737e-08,
+      "loss": 0.288,
+      "step": 2160
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 4.296381073022549e-08,
+      "loss": 0.2858,
+      "step": 2170
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.0936996539636663e-08,
+      "loss": 0.2831,
+      "step": 2180
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.087808378832934e-08,
+      "loss": 0.286,
+      "step": 2190
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.2789058114156538e-08,
+      "loss": 0.2816,
+      "step": 2200
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.671516297606095e-09,
+      "loss": 0.2822,
+      "step": 2210
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.5266659465883468e-09,
+      "loss": 0.2888,
+      "step": 2220
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 3.553252580557054e-10,
+      "loss": 0.2791,
+      "step": 2230
+    },
+    {
+      "epoch": 2.0,
+      "step": 2236,
+      "total_flos": 3195475226787840.0,
+      "train_loss": 0.3625062153889583,
+      "train_runtime": 97159.7175,
+      "train_samples_per_second": 5.892,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2236,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 3195475226787840.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22067270070a3792a30ed1c29daf62116d344ebb06dbd6f8efb23af20a90039e
+size 6075