Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "justus27/qwen-math-long",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 300000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d217ed54ae4ac3f787a00b467dfe023664e892b0987e83e07258cb5b883fdba
+size 4548798728

model-00002-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed07a2af8708a9f98fb20eb365fa52a5472b81ef5a29cc7f9fc44ff329af2b7d
+size 4964101384

model-00003-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ee7baf3a3fdd4c229793d340fba401f52ba53f3c9f97d6a0d06fac339298ce
+size 4781637328

model-00004-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16588e452d913af2cdc65e6ef74388fb1cbea515bf4dd23219cd21b7c48256f3
+size 4781670320

model-00005-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd414f97c6f28ac6ad1e76b8afb28bdaf749b3ad19ad8fe385673fb3e304cc20
+size 4781670360

model-00006-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:425cae07cac23b67a63641b9505749d6700f6f6678b453280e29e3c74cf787a5
+size 4964101416

model-00007-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174fe3f9e1f22dc6c26f785ea3652f5ec26bcf17b0c72881e0122a040919fc8b
+size 4781637360

model-00008-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b2979ef1a9c60163c03acdacf611cdc6402eec4dd3dc86d4fe9af74e102265
+size 4781670360

model-00009-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d18518a6ae752019a33fbed891245f264692aa2a24d2038cb2d73f0bbbd326
+size 4781670360

model-00010-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e87cb624af17403a8d17e434925e453854d68c2ab003d9f50190f1de9fcc9eb
+size 4964101416

model-00011-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35889430045d8954e8423fd0da65cbf2ffc2d939e0e30b8e4e9d739d6e8ae51b
+size 4781637360

model-00012-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41510717458f90125eba91dc0a1893f09fe386400d53a53e3c498b1acd3e02d
+size 4781670360

model-00013-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152bbd2cf73001522b868756c6125ac5e2bd8bfc8d9b7c2975d2ff9853121bf5
+size 4781670360

model-00014-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0559f0b378ff0442afbf806425e3f5cb4c887c10094430a1110da41eb192c2fe
+size 4964101416

model-00015-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2ad65fe0663f522f329f1056431b87b7b2347502e355ac281272f4ea50021e
+size 4781637360

model-00016-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8487050b072d9359b5be7238f1fc12e718534a307cfa3c7b1962bbb744d785b7
+size 4781670360

model-00017-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6b94b7a539f06c4e34426d0cced427791fbecba826da3e57d66fbc54be9c84
+size 4781670360

model-00018-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071501422758d2da6ba93a693cb3f5974d206af66c9d79fa3dfc8f4ea83787ff
+size 4964101416

model-00019-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b607b99752afad68a95901d5cf328f35f5a05af43591771f4257821d59796a
+size 4781637360

model-00020-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ac32b8c447749089241af5c7a3fa99a1c2dece1e7b7fb51bdb639544c01a2f
+size 4781670360

model-00021-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097dbbc7e5797e5c98f52ef04f0f229313fe479dc823efa9bf26017b8f9c210f
+size 4781670360

model-00022-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d729f5bdcd034572f6556398e98a0d6d4f6f62584720e699adeae5547548bc2c
+size 4964101416

model-00023-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21874ecaccb89499d61e701b255c607486415bade0398b7d2371612ccb7914f
+size 4781637360

model-00024-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:607f97d7a74fcc6a908a5898e903b8e5d9993585d58d215598e9797abd451187
+size 4781670360

model-00025-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ac429d9da05a6fd2a8ddabf377320e9b388d2b8643776a8029966041087581
+size 4781670360

model-00026-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a5bd3ad8f50b541ae0c571bf0c67f6a636f0bea1b2768f2226c1b77db5a928
+size 4964101416

model-00027-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:195cd1d3a7adadeecefde081f2a7e7ba4482df41a47da19fe8ff7dcd4743a458
+size 4781637360

model-00028-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b342df5edf8850cd4b9f3004eb88af02e233fa90e050a3e63649c82fb0135621
+size 4781670360

model-00029-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b4aa47e25ba78fe40d97568b9921a177dd7cc0d684b8a44c63d556533c4158
+size 4781670360

model-00030-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3437b6f9882b1e453a48c37a7ccb6be22e5fe34aecc03828daeda06a8062274e
+size 3208747032

model-00031-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c4d3c5fb5fe2aaac8427125742248a1066e8961cb3023b98769c3cdfbcd6b4
+size 2491416704

model.safetensors.index.json

@@ -0,0 +1,970 @@
+{
+  "metadata": {
+    "total_size": 145412407296
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00031-of-00031.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00031.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00031.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00031.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00031.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00031.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00031.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00031.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00031.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00031.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00031.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00031.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00031.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00031.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00031.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00031.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00006-of-00031.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00006-of-00031.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00006-of-00031.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00031.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00031.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00031.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00031.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00031.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00007-of-00031.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00031.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00031.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00031.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00031.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00031.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00031.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00031.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00031.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00031.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00031.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00009-of-00031.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00009-of-00031.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00031.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00010-of-00031.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00010-of-00031.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00010-of-00031.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00010-of-00031.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00010-of-00031.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00031.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00010-of-00031.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00010-of-00031.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00010-of-00031.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00031.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00011-of-00031.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00031.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00011-of-00031.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00031.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00012-of-00031.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00012-of-00031.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00031.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00031.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00031.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00031.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00031.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00012-of-00031.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00013-of-00031.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00013-of-00031.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00013-of-00031.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00014-of-00031.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00014-of-00031.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00014-of-00031.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00014-of-00031.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00014-of-00031.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00014-of-00031.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00014-of-00031.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00014-of-00031.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00014-of-00031.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00031.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00015-of-00031.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00031.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00015-of-00031.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00031.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00016-of-00031.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00031.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00031.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00016-of-00031.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00016-of-00031.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00017-of-00031.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00017-of-00031.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00017-of-00031.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00018-of-00031.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00018-of-00031.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00018-of-00031.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00018-of-00031.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00018-of-00031.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00018-of-00031.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00018-of-00031.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00018-of-00031.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00018-of-00031.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00031.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00019-of-00031.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00019-of-00031.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00019-of-00031.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00031.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00031.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00031.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00020-of-00031.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00020-of-00031.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00020-of-00031.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00021-of-00031.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00021-of-00031.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00021-of-00031.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00022-of-00031.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00022-of-00031.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00022-of-00031.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00022-of-00031.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00022-of-00031.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00022-of-00031.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00022-of-00031.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00022-of-00031.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00022-of-00031.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00031.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00023-of-00031.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00023-of-00031.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00031.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00023-of-00031.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00031.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00024-of-00031.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00024-of-00031.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00024-of-00031.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00025-of-00031.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
+    "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00025-of-00031.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
+    "model.layers.65.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.65.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.65.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00025-of-00031.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
+    "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00026-of-00031.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
+    "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00026-of-00031.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
+    "model.layers.68.self_attn.k_proj.bias": "model-00026-of-00031.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.68.self_attn.q_proj.bias": "model-00026-of-00031.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.68.self_attn.v_proj.bias": "model-00026-of-00031.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00026-of-00031.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
+    "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00031.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00031.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00031.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00031.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00031.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00027-of-00031.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00027-of-00031.safetensors",
+    "model.layers.70.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00027-of-00031.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00031.safetensors",
+    "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00028-of-00031.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
+    "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00028-of-00031.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
+    "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00028-of-00031.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
+    "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00029-of-00031.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
+    "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00029-of-00031.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
+    "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00029-of-00031.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
+    "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00030-of-00031.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00030-of-00031.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00030-of-00031.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00030-of-00031.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00030-of-00031.safetensors",
+    "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00030-of-00031.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00030-of-00031.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00031.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00030-of-00031.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00031.safetensors",
+    "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00031.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00031.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00031.safetensors",
+    "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00031.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00031.safetensors",
+    "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00031.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00031.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00031.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00031.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
+    "model.norm.weight": "model-00030-of-00031.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60a1b40608e34bc801c8231f97b81c53b5290dfaed1b9cd0ccbeca29574a991
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad6a142a403eb9aafc4a3a9a856bca648fe31fd22d796867baca31fb13656aa
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bc23a138cc800b22881742c0f3f9a71731a9a7111c6058a0077e6274d21773
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a49cd8b86c1fc5494087e8b515f0355320aa65f04cf14865b6b9434292334eec
+size 1064

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1633 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3869625520110958,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006934812760055479,
+      "grad_norm": 61.60813903808594,
+      "learning_rate": 8.650519031141869e-07,
+      "loss": 2.7928,
+      "mean_token_accuracy": 0.6783367753028869,
+      "step": 5
+    },
+    {
+      "epoch": 0.013869625520110958,
+      "grad_norm": 35.546016693115234,
+      "learning_rate": 1.7301038062283738e-06,
+      "loss": 2.3942,
+      "mean_token_accuracy": 0.6943186521530151,
+      "step": 10
+    },
+    {
+      "epoch": 0.020804438280166437,
+      "grad_norm": 2.246945858001709,
+      "learning_rate": 2.5951557093425604e-06,
+      "loss": 1.202,
+      "mean_token_accuracy": 0.7397322177886962,
+      "step": 15
+    },
+    {
+      "epoch": 0.027739251040221916,
+      "grad_norm": 1.1429805755615234,
+      "learning_rate": 3.4602076124567477e-06,
+      "loss": 0.918,
+      "mean_token_accuracy": 0.7564186692237854,
+      "step": 20
+    },
+    {
+      "epoch": 0.03467406380027739,
+      "grad_norm": 0.9538511633872986,
+      "learning_rate": 4.325259515570934e-06,
+      "loss": 0.8104,
+      "mean_token_accuracy": 0.7724308490753173,
+      "step": 25
+    },
+    {
+      "epoch": 0.04160887656033287,
+      "grad_norm": 0.7069241404533386,
+      "learning_rate": 5.190311418685121e-06,
+      "loss": 0.7364,
+      "mean_token_accuracy": 0.7827559828758239,
+      "step": 30
+    },
+    {
+      "epoch": 0.04854368932038835,
+      "grad_norm": 0.4030636250972748,
+      "learning_rate": 6.055363321799308e-06,
+      "loss": 0.6835,
+      "mean_token_accuracy": 0.7935511350631714,
+      "step": 35
+    },
+    {
+      "epoch": 0.05547850208044383,
+      "grad_norm": 0.8142576217651367,
+      "learning_rate": 6.920415224913495e-06,
+      "loss": 0.6478,
+      "mean_token_accuracy": 0.8010085463523865,
+      "step": 40
+    },
+    {
+      "epoch": 0.06241331484049931,
+      "grad_norm": 0.2626665532588959,
+      "learning_rate": 7.785467128027681e-06,
+      "loss": 0.6267,
+      "mean_token_accuracy": 0.8053073883056641,
+      "step": 45
+    },
+    {
+      "epoch": 0.06934812760055478,
+      "grad_norm": 0.23942551016807556,
+      "learning_rate": 8.650519031141868e-06,
+      "loss": 0.6013,
+      "mean_token_accuracy": 0.8112802267074585,
+      "step": 50
+    },
+    {
+      "epoch": 0.07628294036061026,
+      "grad_norm": 0.20308136940002441,
+      "learning_rate": 9.515570934256055e-06,
+      "loss": 0.5769,
+      "mean_token_accuracy": 0.8168688178062439,
+      "step": 55
+    },
+    {
+      "epoch": 0.08321775312066575,
+      "grad_norm": 0.1854431927204132,
+      "learning_rate": 1.0380622837370241e-05,
+      "loss": 0.5805,
+      "mean_token_accuracy": 0.815436840057373,
+      "step": 60
+    },
+    {
+      "epoch": 0.09015256588072122,
+      "grad_norm": 0.1700541228055954,
+      "learning_rate": 1.124567474048443e-05,
+      "loss": 0.5652,
+      "mean_token_accuracy": 0.8188095331192017,
+      "step": 65
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "grad_norm": 0.18573108315467834,
+      "learning_rate": 1.2110726643598615e-05,
+      "loss": 0.5524,
+      "mean_token_accuracy": 0.8222507953643798,
+      "step": 70
+    },
+    {
+      "epoch": 0.10402219140083217,
+      "grad_norm": 0.18843185901641846,
+      "learning_rate": 1.2975778546712803e-05,
+      "loss": 0.542,
+      "mean_token_accuracy": 0.8249342203140259,
+      "step": 75
+    },
+    {
+      "epoch": 0.11095700416088766,
+      "grad_norm": 0.21635942161083221,
+      "learning_rate": 1.384083044982699e-05,
+      "loss": 0.5401,
+      "mean_token_accuracy": 0.8251730322837829,
+      "step": 80
+    },
+    {
+      "epoch": 0.11789181692094314,
+      "grad_norm": 0.21325534582138062,
+      "learning_rate": 1.4705882352941177e-05,
+      "loss": 0.5404,
+      "mean_token_accuracy": 0.8243620276451111,
+      "step": 85
+    },
+    {
+      "epoch": 0.12482662968099861,
+      "grad_norm": 0.22691610455513,
+      "learning_rate": 1.5570934256055363e-05,
+      "loss": 0.5278,
+      "mean_token_accuracy": 0.8283108592033386,
+      "step": 90
+    },
+    {
+      "epoch": 0.1317614424410541,
+      "grad_norm": 0.2375083714723587,
+      "learning_rate": 1.643598615916955e-05,
+      "loss": 0.5198,
+      "mean_token_accuracy": 0.8296842217445374,
+      "step": 95
+    },
+    {
+      "epoch": 0.13869625520110956,
+      "grad_norm": 0.27802157402038574,
+      "learning_rate": 1.7301038062283735e-05,
+      "loss": 0.5346,
+      "mean_token_accuracy": 0.825625765323639,
+      "step": 100
+    },
+    {
+      "epoch": 0.14563106796116504,
+      "grad_norm": 0.3691716194152832,
+      "learning_rate": 1.8166089965397926e-05,
+      "loss": 0.5249,
+      "mean_token_accuracy": 0.828523588180542,
+      "step": 105
+    },
+    {
+      "epoch": 0.15256588072122051,
+      "grad_norm": 0.30235254764556885,
+      "learning_rate": 1.903114186851211e-05,
+      "loss": 0.514,
+      "mean_token_accuracy": 0.8320501446723938,
+      "step": 110
+    },
+    {
+      "epoch": 0.15950069348127602,
+      "grad_norm": 0.3447076380252838,
+      "learning_rate": 1.98961937716263e-05,
+      "loss": 0.5203,
+      "mean_token_accuracy": 0.8298335313796997,
+      "step": 115
+    },
+    {
+      "epoch": 0.1664355062413315,
+      "grad_norm": 0.28185489773750305,
+      "learning_rate": 2.0761245674740483e-05,
+      "loss": 0.5305,
+      "mean_token_accuracy": 0.8264262914657593,
+      "step": 120
+    },
+    {
+      "epoch": 0.17337031900138697,
+      "grad_norm": 0.2629449963569641,
+      "learning_rate": 2.1626297577854674e-05,
+      "loss": 0.5167,
+      "mean_token_accuracy": 0.8303680658340454,
+      "step": 125
+    },
+    {
+      "epoch": 0.18030513176144244,
+      "grad_norm": 0.2788124680519104,
+      "learning_rate": 2.249134948096886e-05,
+      "loss": 0.5275,
+      "mean_token_accuracy": 0.8274267673492431,
+      "step": 130
+    },
+    {
+      "epoch": 0.18723994452149792,
+      "grad_norm": 0.24550440907478333,
+      "learning_rate": 2.3356401384083046e-05,
+      "loss": 0.5073,
+      "mean_token_accuracy": 0.8328269720077515,
+      "step": 135
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.7636565566062927,
+      "learning_rate": 2.422145328719723e-05,
+      "loss": 0.5138,
+      "mean_token_accuracy": 0.8308726906776428,
+      "step": 140
+    },
+    {
+      "epoch": 0.20110957004160887,
+      "grad_norm": 0.6163385510444641,
+      "learning_rate": 2.508650519031142e-05,
+      "loss": 0.5123,
+      "mean_token_accuracy": 0.8311893105506897,
+      "step": 145
+    },
+    {
+      "epoch": 0.20804438280166435,
+      "grad_norm": 0.3808706998825073,
+      "learning_rate": 2.5951557093425606e-05,
+      "loss": 0.5018,
+      "mean_token_accuracy": 0.8343647360801697,
+      "step": 150
+    },
+    {
+      "epoch": 0.21497919556171982,
+      "grad_norm": 0.2565021216869354,
+      "learning_rate": 2.6816608996539794e-05,
+      "loss": 0.4943,
+      "mean_token_accuracy": 0.8362817883491516,
+      "step": 155
+    },
+    {
+      "epoch": 0.22191400832177532,
+      "grad_norm": 0.3511087894439697,
+      "learning_rate": 2.768166089965398e-05,
+      "loss": 0.4933,
+      "mean_token_accuracy": 0.8366880297660828,
+      "step": 160
+    },
+    {
+      "epoch": 0.2288488210818308,
+      "grad_norm": 0.4006827175617218,
+      "learning_rate": 2.8546712802768166e-05,
+      "loss": 0.4906,
+      "mean_token_accuracy": 0.837351131439209,
+      "step": 165
+    },
+    {
+      "epoch": 0.23578363384188628,
+      "grad_norm": 0.4149070978164673,
+      "learning_rate": 2.9411764705882354e-05,
+      "loss": 0.4988,
+      "mean_token_accuracy": 0.8351827621459961,
+      "step": 170
+    },
+    {
+      "epoch": 0.24271844660194175,
+      "grad_norm": 0.32881560921669006,
+      "learning_rate": 3.0276816608996538e-05,
+      "loss": 0.5085,
+      "mean_token_accuracy": 0.831884253025055,
+      "step": 175
+    },
+    {
+      "epoch": 0.24965325936199723,
+      "grad_norm": 0.46366971731185913,
+      "learning_rate": 3.1141868512110726e-05,
+      "loss": 0.4964,
+      "mean_token_accuracy": 0.8355090618133545,
+      "step": 180
+    },
+    {
+      "epoch": 0.2565880721220527,
+      "grad_norm": 0.838777482509613,
+      "learning_rate": 3.200692041522492e-05,
+      "loss": 0.5078,
+      "mean_token_accuracy": 0.8320568442344666,
+      "step": 185
+    },
+    {
+      "epoch": 0.2635228848821082,
+      "grad_norm": 30.57767677307129,
+      "learning_rate": 3.28719723183391e-05,
+      "loss": 0.4978,
+      "mean_token_accuracy": 0.8360116839408874,
+      "step": 190
+    },
+    {
+      "epoch": 0.27045769764216365,
+      "grad_norm": 0.5885879993438721,
+      "learning_rate": 3.373702422145329e-05,
+      "loss": 0.497,
+      "mean_token_accuracy": 0.8356186389923096,
+      "step": 195
+    },
+    {
+      "epoch": 0.27739251040221913,
+      "grad_norm": 0.3610420525074005,
+      "learning_rate": 3.460207612456747e-05,
+      "loss": 0.4989,
+      "mean_token_accuracy": 0.8350513100624084,
+      "step": 200
+    },
+    {
+      "epoch": 0.2843273231622746,
+      "grad_norm": 0.3954995572566986,
+      "learning_rate": 3.546712802768166e-05,
+      "loss": 0.5011,
+      "mean_token_accuracy": 0.83415766954422,
+      "step": 205
+    },
+    {
+      "epoch": 0.2912621359223301,
+      "grad_norm": 0.3071337342262268,
+      "learning_rate": 3.633217993079585e-05,
+      "loss": 0.5255,
+      "mean_token_accuracy": 0.8285403490066529,
+      "step": 210
+    },
+    {
+      "epoch": 0.29819694868238555,
+      "grad_norm": 0.31758391857147217,
+      "learning_rate": 3.719723183391004e-05,
+      "loss": 0.4954,
+      "mean_token_accuracy": 0.835390031337738,
+      "step": 215
+    },
+    {
+      "epoch": 0.30513176144244103,
+      "grad_norm": 0.3296087086200714,
+      "learning_rate": 3.806228373702422e-05,
+      "loss": 0.4923,
+      "mean_token_accuracy": 0.8361375451087951,
+      "step": 220
+    },
+    {
+      "epoch": 0.3120665742024965,
+      "grad_norm": 0.2980894446372986,
+      "learning_rate": 3.892733564013841e-05,
+      "loss": 0.4996,
+      "mean_token_accuracy": 0.8341476917266846,
+      "step": 225
+    },
+    {
+      "epoch": 0.31900138696255204,
+      "grad_norm": 0.2892495095729828,
+      "learning_rate": 3.97923875432526e-05,
+      "loss": 0.4855,
+      "mean_token_accuracy": 0.8382086515426636,
+      "step": 230
+    },
+    {
+      "epoch": 0.3259361997226075,
+      "grad_norm": 0.29287102818489075,
+      "learning_rate": 4.065743944636679e-05,
+      "loss": 0.4944,
+      "mean_token_accuracy": 0.8353524923324585,
+      "step": 235
+    },
+    {
+      "epoch": 0.332871012482663,
+      "grad_norm": 0.28245487809181213,
+      "learning_rate": 4.1522491349480966e-05,
+      "loss": 0.4887,
+      "mean_token_accuracy": 0.8373544692993165,
+      "step": 240
+    },
+    {
+      "epoch": 0.33980582524271846,
+      "grad_norm": 0.23551802337169647,
+      "learning_rate": 4.238754325259516e-05,
+      "loss": 0.4925,
+      "mean_token_accuracy": 0.8361364006996155,
+      "step": 245
+    },
+    {
+      "epoch": 0.34674063800277394,
+      "grad_norm": 0.24266427755355835,
+      "learning_rate": 4.325259515570935e-05,
+      "loss": 0.4759,
+      "mean_token_accuracy": 0.8410738468170166,
+      "step": 250
+    },
+    {
+      "epoch": 0.3536754507628294,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 4.411764705882353e-05,
+      "loss": 0.4902,
+      "mean_token_accuracy": 0.8370885252952576,
+      "step": 255
+    },
+    {
+      "epoch": 0.3606102635228849,
+      "grad_norm": 0.5113539099693298,
+      "learning_rate": 4.498269896193772e-05,
+      "loss": 0.4918,
+      "mean_token_accuracy": 0.8364068984985351,
+      "step": 260
+    },
+    {
+      "epoch": 0.36754507628294036,
+      "grad_norm": 0.3733905851840973,
+      "learning_rate": 4.58477508650519e-05,
+      "loss": 0.49,
+      "mean_token_accuracy": 0.8370036244392395,
+      "step": 265
+    },
+    {
+      "epoch": 0.37447988904299584,
+      "grad_norm": 0.4112997353076935,
+      "learning_rate": 4.671280276816609e-05,
+      "loss": 0.4932,
+      "mean_token_accuracy": 0.8356328129768371,
+      "step": 270
+    },
+    {
+      "epoch": 0.3814147018030513,
+      "grad_norm": 0.5121487379074097,
+      "learning_rate": 4.7577854671280283e-05,
+      "loss": 0.479,
+      "mean_token_accuracy": 0.839626955986023,
+      "step": 275
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.36294957995414734,
+      "learning_rate": 4.844290657439446e-05,
+      "loss": 0.4829,
+      "mean_token_accuracy": 0.8391167283058166,
+      "step": 280
+    },
+    {
+      "epoch": 0.39528432732316227,
+      "grad_norm": 0.3162820339202881,
+      "learning_rate": 4.930795847750865e-05,
+      "loss": 0.4899,
+      "mean_token_accuracy": 0.8368083834648132,
+      "step": 285
+    },
+    {
+      "epoch": 0.40221914008321774,
+      "grad_norm": 0.3973437547683716,
+      "learning_rate": 4.9980732177263974e-05,
+      "loss": 0.4864,
+      "mean_token_accuracy": 0.8374906539916992,
+      "step": 290
+    },
+    {
+      "epoch": 0.4091539528432732,
+      "grad_norm": 0.5423433184623718,
+      "learning_rate": 4.9884393063583816e-05,
+      "loss": 0.4907,
+      "mean_token_accuracy": 0.8373413920402527,
+      "step": 295
+    },
+    {
+      "epoch": 0.4160887656033287,
+      "grad_norm": 0.39722123742103577,
+      "learning_rate": 4.9788053949903666e-05,
+      "loss": 0.4961,
+      "mean_token_accuracy": 0.8351489901542664,
+      "step": 300
+    },
+    {
+      "epoch": 0.42302357836338417,
+      "grad_norm": 0.34169071912765503,
+      "learning_rate": 4.969171483622351e-05,
+      "loss": 0.4891,
+      "mean_token_accuracy": 0.8370493412017822,
+      "step": 305
+    },
+    {
+      "epoch": 0.42995839112343964,
+      "grad_norm": 0.3429335951805115,
+      "learning_rate": 4.959537572254335e-05,
+      "loss": 0.4794,
+      "mean_token_accuracy": 0.8396916627883911,
+      "step": 310
+    },
+    {
+      "epoch": 0.4368932038834951,
+      "grad_norm": 0.3266272246837616,
+      "learning_rate": 4.94990366088632e-05,
+      "loss": 0.4757,
+      "mean_token_accuracy": 0.8405494570732117,
+      "step": 315
+    },
+    {
+      "epoch": 0.44382801664355065,
+      "grad_norm": 0.2874930202960968,
+      "learning_rate": 4.940269749518305e-05,
+      "loss": 0.4978,
+      "mean_token_accuracy": 0.8344841122627258,
+      "step": 320
+    },
+    {
+      "epoch": 0.4507628294036061,
+      "grad_norm": 0.2812349498271942,
+      "learning_rate": 4.930635838150289e-05,
+      "loss": 0.4839,
+      "mean_token_accuracy": 0.8383953332901001,
+      "step": 325
+    },
+    {
+      "epoch": 0.4576976421636616,
+      "grad_norm": 0.25296345353126526,
+      "learning_rate": 4.921001926782274e-05,
+      "loss": 0.4738,
+      "mean_token_accuracy": 0.8412886261940002,
+      "step": 330
+    },
+    {
+      "epoch": 0.4646324549237171,
+      "grad_norm": 0.22165291011333466,
+      "learning_rate": 4.9113680154142584e-05,
+      "loss": 0.4867,
+      "mean_token_accuracy": 0.8379201173782349,
+      "step": 335
+    },
+    {
+      "epoch": 0.47156726768377255,
+      "grad_norm": 0.2551758289337158,
+      "learning_rate": 4.9017341040462426e-05,
+      "loss": 0.4786,
+      "mean_token_accuracy": 0.8399594306945801,
+      "step": 340
+    },
+    {
+      "epoch": 0.478502080443828,
+      "grad_norm": 0.25708919763565063,
+      "learning_rate": 4.8921001926782276e-05,
+      "loss": 0.48,
+      "mean_token_accuracy": 0.8395551085472107,
+      "step": 345
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.1992408186197281,
+      "learning_rate": 4.8824662813102125e-05,
+      "loss": 0.4714,
+      "mean_token_accuracy": 0.8418668508529663,
+      "step": 350
+    },
+    {
+      "epoch": 0.492371705963939,
+      "grad_norm": 0.23445720970630646,
+      "learning_rate": 4.872832369942197e-05,
+      "loss": 0.471,
+      "mean_token_accuracy": 0.8421580553054809,
+      "step": 355
+    },
+    {
+      "epoch": 0.49930651872399445,
+      "grad_norm": 0.31462928652763367,
+      "learning_rate": 4.863198458574181e-05,
+      "loss": 0.4711,
+      "mean_token_accuracy": 0.842027747631073,
+      "step": 360
+    },
+    {
+      "epoch": 0.5062413314840499,
+      "grad_norm": 0.24767646193504333,
+      "learning_rate": 4.853564547206166e-05,
+      "loss": 0.4717,
+      "mean_token_accuracy": 0.8417503118515015,
+      "step": 365
+    },
+    {
+      "epoch": 0.5131761442441054,
+      "grad_norm": 0.2389938235282898,
+      "learning_rate": 4.84393063583815e-05,
+      "loss": 0.4677,
+      "mean_token_accuracy": 0.8431912064552307,
+      "step": 370
+    },
+    {
+      "epoch": 0.5201109570041609,
+      "grad_norm": 0.29998722672462463,
+      "learning_rate": 4.834296724470135e-05,
+      "loss": 0.4877,
+      "mean_token_accuracy": 0.8374402284622192,
+      "step": 375
+    },
+    {
+      "epoch": 0.5270457697642164,
+      "grad_norm": 0.2877121865749359,
+      "learning_rate": 4.82466281310212e-05,
+      "loss": 0.4863,
+      "mean_token_accuracy": 0.8380719065666199,
+      "step": 380
+    },
+    {
+      "epoch": 0.5339805825242718,
+      "grad_norm": 0.24628062546253204,
+      "learning_rate": 4.815028901734104e-05,
+      "loss": 0.4665,
+      "mean_token_accuracy": 0.8434135437011718,
+      "step": 385
+    },
+    {
+      "epoch": 0.5409153952843273,
+      "grad_norm": 0.24347947537899017,
+      "learning_rate": 4.8053949903660886e-05,
+      "loss": 0.476,
+      "mean_token_accuracy": 0.8404138565063477,
+      "step": 390
+    },
+    {
+      "epoch": 0.5478502080443828,
+      "grad_norm": 0.20724909007549286,
+      "learning_rate": 4.7957610789980735e-05,
+      "loss": 0.4881,
+      "mean_token_accuracy": 0.8372583389282227,
+      "step": 395
+    },
+    {
+      "epoch": 0.5547850208044383,
+      "grad_norm": 0.2162594497203827,
+      "learning_rate": 4.786127167630058e-05,
+      "loss": 0.4726,
+      "mean_token_accuracy": 0.842011570930481,
+      "step": 400
+    },
+    {
+      "epoch": 0.5617198335644937,
+      "grad_norm": 0.34494099020957947,
+      "learning_rate": 4.776493256262042e-05,
+      "loss": 0.4783,
+      "mean_token_accuracy": 0.8399308085441589,
+      "step": 405
+    },
+    {
+      "epoch": 0.5686546463245492,
+      "grad_norm": 0.24402566254138947,
+      "learning_rate": 4.7668593448940276e-05,
+      "loss": 0.4953,
+      "mean_token_accuracy": 0.8352864623069763,
+      "step": 410
+    },
+    {
+      "epoch": 0.5755894590846047,
+      "grad_norm": 0.2124612033367157,
+      "learning_rate": 4.757225433526012e-05,
+      "loss": 0.4849,
+      "mean_token_accuracy": 0.8380748987197876,
+      "step": 415
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.20577934384346008,
+      "learning_rate": 4.747591522157996e-05,
+      "loss": 0.4591,
+      "mean_token_accuracy": 0.845665693283081,
+      "step": 420
+    },
+    {
+      "epoch": 0.5894590846047156,
+      "grad_norm": 0.2838655710220337,
+      "learning_rate": 4.737957610789981e-05,
+      "loss": 0.4709,
+      "mean_token_accuracy": 0.8418583750724793,
+      "step": 425
+    },
+    {
+      "epoch": 0.5963938973647711,
+      "grad_norm": 0.2222902923822403,
+      "learning_rate": 4.7283236994219653e-05,
+      "loss": 0.4817,
+      "mean_token_accuracy": 0.8388337612152099,
+      "step": 430
+    },
+    {
+      "epoch": 0.6033287101248266,
+      "grad_norm": 0.25565460324287415,
+      "learning_rate": 4.7186897880539496e-05,
+      "loss": 0.4724,
+      "mean_token_accuracy": 0.8415215969085693,
+      "step": 435
+    },
+    {
+      "epoch": 0.6102635228848821,
+      "grad_norm": 0.680081844329834,
+      "learning_rate": 4.709055876685935e-05,
+      "loss": 0.4777,
+      "mean_token_accuracy": 0.8402902245521545,
+      "step": 440
+    },
+    {
+      "epoch": 0.6171983356449375,
+      "grad_norm": 0.3035682141780853,
+      "learning_rate": 4.6994219653179195e-05,
+      "loss": 0.4749,
+      "mean_token_accuracy": 0.8405117988586426,
+      "step": 445
+    },
+    {
+      "epoch": 0.624133148404993,
+      "grad_norm": 0.22393807768821716,
+      "learning_rate": 4.689788053949904e-05,
+      "loss": 0.4735,
+      "mean_token_accuracy": 0.8410566568374633,
+      "step": 450
+    },
+    {
+      "epoch": 0.6310679611650486,
+      "grad_norm": 0.23452860116958618,
+      "learning_rate": 4.6801541425818887e-05,
+      "loss": 0.4798,
+      "mean_token_accuracy": 0.8394344925880433,
+      "step": 455
+    },
+    {
+      "epoch": 0.6380027739251041,
+      "grad_norm": 0.21135355532169342,
+      "learning_rate": 4.670520231213873e-05,
+      "loss": 0.4783,
+      "mean_token_accuracy": 0.8398800015449523,
+      "step": 460
+    },
+    {
+      "epoch": 0.6449375866851595,
+      "grad_norm": 0.2495516985654831,
+      "learning_rate": 4.660886319845857e-05,
+      "loss": 0.4769,
+      "mean_token_accuracy": 0.8407980084419251,
+      "step": 465
+    },
+    {
+      "epoch": 0.651872399445215,
+      "grad_norm": 0.25724372267723083,
+      "learning_rate": 4.651252408477843e-05,
+      "loss": 0.4764,
+      "mean_token_accuracy": 0.8402070879936219,
+      "step": 470
+    },
+    {
+      "epoch": 0.6588072122052705,
+      "grad_norm": 0.28974995017051697,
+      "learning_rate": 4.641618497109827e-05,
+      "loss": 0.468,
+      "mean_token_accuracy": 0.8425545215606689,
+      "step": 475
+    },
+    {
+      "epoch": 0.665742024965326,
+      "grad_norm": 0.26298555731773376,
+      "learning_rate": 4.631984585741811e-05,
+      "loss": 0.4752,
+      "mean_token_accuracy": 0.8405273199081421,
+      "step": 480
+    },
+    {
+      "epoch": 0.6726768377253814,
+      "grad_norm": 0.3188522756099701,
+      "learning_rate": 4.622350674373796e-05,
+      "loss": 0.4683,
+      "mean_token_accuracy": 0.8426392555236817,
+      "step": 485
+    },
+    {
+      "epoch": 0.6796116504854369,
+      "grad_norm": 0.2528276741504669,
+      "learning_rate": 4.6127167630057805e-05,
+      "loss": 0.4753,
+      "mean_token_accuracy": 0.840662169456482,
+      "step": 490
+    },
+    {
+      "epoch": 0.6865464632454924,
+      "grad_norm": 0.3695737421512604,
+      "learning_rate": 4.603082851637765e-05,
+      "loss": 0.501,
+      "mean_token_accuracy": 0.8371694445610046,
+      "step": 495
+    },
+    {
+      "epoch": 0.6934812760055479,
+      "grad_norm": 0.31206727027893066,
+      "learning_rate": 4.59344894026975e-05,
+      "loss": 0.478,
+      "mean_token_accuracy": 0.8401562452316285,
+      "step": 500
+    },
+    {
+      "epoch": 0.7004160887656034,
+      "grad_norm": 3.478522539138794,
+      "learning_rate": 4.5838150289017346e-05,
+      "loss": 0.49,
+      "mean_token_accuracy": 0.8365014433860779,
+      "step": 505
+    },
+    {
+      "epoch": 0.7073509015256588,
+      "grad_norm": 0.4430016875267029,
+      "learning_rate": 4.574181117533719e-05,
+      "loss": 0.47,
+      "mean_token_accuracy": 0.8422938823699951,
+      "step": 510
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.28713470697402954,
+      "learning_rate": 4.564547206165704e-05,
+      "loss": 0.4786,
+      "mean_token_accuracy": 0.8401166200637817,
+      "step": 515
+    },
+    {
+      "epoch": 0.7212205270457698,
+      "grad_norm": 0.2158370316028595,
+      "learning_rate": 4.554913294797688e-05,
+      "loss": 0.4703,
+      "mean_token_accuracy": 0.8421276092529297,
+      "step": 520
+    },
+    {
+      "epoch": 0.7281553398058253,
+      "grad_norm": 0.2426484376192093,
+      "learning_rate": 4.545279383429672e-05,
+      "loss": 0.469,
+      "mean_token_accuracy": 0.8426563143730164,
+      "step": 525
+    },
+    {
+      "epoch": 0.7350901525658807,
+      "grad_norm": 0.27153995633125305,
+      "learning_rate": 4.535645472061657e-05,
+      "loss": 0.4754,
+      "mean_token_accuracy": 0.8406094431877136,
+      "step": 530
+    },
+    {
+      "epoch": 0.7420249653259362,
+      "grad_norm": 0.1991535872220993,
+      "learning_rate": 4.526011560693642e-05,
+      "loss": 0.4782,
+      "mean_token_accuracy": 0.8397158980369568,
+      "step": 535
+    },
+    {
+      "epoch": 0.7489597780859917,
+      "grad_norm": 0.15923242270946503,
+      "learning_rate": 4.5163776493256264e-05,
+      "loss": 0.4563,
+      "mean_token_accuracy": 0.8461790800094604,
+      "step": 540
+    },
+    {
+      "epoch": 0.7558945908460472,
+      "grad_norm": 0.18306083977222443,
+      "learning_rate": 4.5067437379576114e-05,
+      "loss": 0.4791,
+      "mean_token_accuracy": 0.8393635034561158,
+      "step": 545
+    },
+    {
+      "epoch": 0.7628294036061026,
+      "grad_norm": 0.24309256672859192,
+      "learning_rate": 4.4971098265895956e-05,
+      "loss": 0.4777,
+      "mean_token_accuracy": 0.8401144862174987,
+      "step": 550
+    },
+    {
+      "epoch": 0.7697642163661581,
+      "grad_norm": 0.20910784602165222,
+      "learning_rate": 4.48747591522158e-05,
+      "loss": 0.4728,
+      "mean_token_accuracy": 0.8417426466941833,
+      "step": 555
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.1896984726190567,
+      "learning_rate": 4.477842003853565e-05,
+      "loss": 0.4557,
+      "mean_token_accuracy": 0.8461586833000183,
+      "step": 560
+    },
+    {
+      "epoch": 0.7836338418862691,
+      "grad_norm": 0.18798613548278809,
+      "learning_rate": 4.46820809248555e-05,
+      "loss": 0.457,
+      "mean_token_accuracy": 0.8459754705429077,
+      "step": 565
+    },
+    {
+      "epoch": 0.7905686546463245,
+      "grad_norm": 0.18959036469459534,
+      "learning_rate": 4.458574181117534e-05,
+      "loss": 0.4633,
+      "mean_token_accuracy": 0.8437102913856507,
+      "step": 570
+    },
+    {
+      "epoch": 0.79750346740638,
+      "grad_norm": 0.16292130947113037,
+      "learning_rate": 4.448940269749519e-05,
+      "loss": 0.4749,
+      "mean_token_accuracy": 0.8404599308967591,
+      "step": 575
+    },
+    {
+      "epoch": 0.8044382801664355,
+      "grad_norm": 0.17686040699481964,
+      "learning_rate": 4.439306358381503e-05,
+      "loss": 0.4601,
+      "mean_token_accuracy": 0.844899308681488,
+      "step": 580
+    },
+    {
+      "epoch": 0.811373092926491,
+      "grad_norm": 0.1865614652633667,
+      "learning_rate": 4.4296724470134875e-05,
+      "loss": 0.4533,
+      "mean_token_accuracy": 0.846677553653717,
+      "step": 585
+    },
+    {
+      "epoch": 0.8183079056865464,
+      "grad_norm": 0.2037810981273651,
+      "learning_rate": 4.4200385356454724e-05,
+      "loss": 0.4575,
+      "mean_token_accuracy": 0.8457266449928283,
+      "step": 590
+    },
+    {
+      "epoch": 0.8252427184466019,
+      "grad_norm": 0.16701985895633698,
+      "learning_rate": 4.4104046242774566e-05,
+      "loss": 0.466,
+      "mean_token_accuracy": 0.8428797006607056,
+      "step": 595
+    },
+    {
+      "epoch": 0.8321775312066574,
+      "grad_norm": 0.19714096188545227,
+      "learning_rate": 4.4007707129094416e-05,
+      "loss": 0.4696,
+      "mean_token_accuracy": 0.8422728657722474,
+      "step": 600
+    },
+    {
+      "epoch": 0.8391123439667129,
+      "grad_norm": 0.20772860944271088,
+      "learning_rate": 4.391136801541426e-05,
+      "loss": 0.4635,
+      "mean_token_accuracy": 0.8438523054122925,
+      "step": 605
+    },
+    {
+      "epoch": 0.8460471567267683,
+      "grad_norm": 0.35546374320983887,
+      "learning_rate": 4.381502890173411e-05,
+      "loss": 0.4665,
+      "mean_token_accuracy": 0.8430918097496033,
+      "step": 610
+    },
+    {
+      "epoch": 0.8529819694868238,
+      "grad_norm": 0.19986563920974731,
+      "learning_rate": 4.371868978805395e-05,
+      "loss": 0.4742,
+      "mean_token_accuracy": 0.8409379243850708,
+      "step": 615
+    },
+    {
+      "epoch": 0.8599167822468793,
+      "grad_norm": 0.4013294279575348,
+      "learning_rate": 4.36223506743738e-05,
+      "loss": 0.4673,
+      "mean_token_accuracy": 0.8426662087440491,
+      "step": 620
+    },
+    {
+      "epoch": 0.8668515950069348,
+      "grad_norm": 0.29566317796707153,
+      "learning_rate": 4.352601156069364e-05,
+      "loss": 0.4837,
+      "mean_token_accuracy": 0.8380556702613831,
+      "step": 625
+    },
+    {
+      "epoch": 0.8737864077669902,
+      "grad_norm": 0.24461045861244202,
+      "learning_rate": 4.342967244701349e-05,
+      "loss": 0.4648,
+      "mean_token_accuracy": 0.8434231281280518,
+      "step": 630
+    },
+    {
+      "epoch": 0.8807212205270458,
+      "grad_norm": 0.2197730541229248,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.4585,
+      "mean_token_accuracy": 0.8448979973793029,
+      "step": 635
+    },
+    {
+      "epoch": 0.8876560332871013,
+      "grad_norm": 0.22158759832382202,
+      "learning_rate": 4.3236994219653183e-05,
+      "loss": 0.4678,
+      "mean_token_accuracy": 0.8427410125732422,
+      "step": 640
+    },
+    {
+      "epoch": 0.8945908460471568,
+      "grad_norm": 0.17014814913272858,
+      "learning_rate": 4.3140655105973026e-05,
+      "loss": 0.4706,
+      "mean_token_accuracy": 0.8416074395179749,
+      "step": 645
+    },
+    {
+      "epoch": 0.9015256588072122,
+      "grad_norm": 0.22929687798023224,
+      "learning_rate": 4.304431599229287e-05,
+      "loss": 0.4753,
+      "mean_token_accuracy": 0.8403880834579468,
+      "step": 650
+    },
+    {
+      "epoch": 0.9084604715672677,
+      "grad_norm": 0.20894835889339447,
+      "learning_rate": 4.294797687861272e-05,
+      "loss": 0.4734,
+      "mean_token_accuracy": 0.8410162568092346,
+      "step": 655
+    },
+    {
+      "epoch": 0.9153952843273232,
+      "grad_norm": 0.18031327426433563,
+      "learning_rate": 4.285163776493257e-05,
+      "loss": 0.4536,
+      "mean_token_accuracy": 0.8469532251358032,
+      "step": 660
+    },
+    {
+      "epoch": 0.9223300970873787,
+      "grad_norm": 0.17288991808891296,
+      "learning_rate": 4.275529865125241e-05,
+      "loss": 0.4611,
+      "mean_token_accuracy": 0.8443895936012268,
+      "step": 665
+    },
+    {
+      "epoch": 0.9292649098474342,
+      "grad_norm": 0.1980760544538498,
+      "learning_rate": 4.265895953757226e-05,
+      "loss": 0.484,
+      "mean_token_accuracy": 0.8379009962081909,
+      "step": 670
+    },
+    {
+      "epoch": 0.9361997226074896,
+      "grad_norm": 0.20848602056503296,
+      "learning_rate": 4.25626204238921e-05,
+      "loss": 0.4771,
+      "mean_token_accuracy": 0.8398370265960693,
+      "step": 675
+    },
+    {
+      "epoch": 0.9431345353675451,
+      "grad_norm": 0.1636408418416977,
+      "learning_rate": 4.2466281310211944e-05,
+      "loss": 0.4578,
+      "mean_token_accuracy": 0.845670223236084,
+      "step": 680
+    },
+    {
+      "epoch": 0.9500693481276006,
+      "grad_norm": 0.22376923263072968,
+      "learning_rate": 4.2369942196531794e-05,
+      "loss": 0.4652,
+      "mean_token_accuracy": 0.8431706428527832,
+      "step": 685
+    },
+    {
+      "epoch": 0.957004160887656,
+      "grad_norm": 0.21399416029453278,
+      "learning_rate": 4.2273603082851636e-05,
+      "loss": 0.4537,
+      "mean_token_accuracy": 0.8464810252189636,
+      "step": 690
+    },
+    {
+      "epoch": 0.9639389736477115,
+      "grad_norm": 2.5790159702301025,
+      "learning_rate": 4.2177263969171485e-05,
+      "loss": 0.4754,
+      "mean_token_accuracy": 0.8421392440795898,
+      "step": 695
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.2648729085922241,
+      "learning_rate": 4.2080924855491335e-05,
+      "loss": 0.469,
+      "mean_token_accuracy": 0.8423485517501831,
+      "step": 700
+    },
+    {
+      "epoch": 0.9778085991678225,
+      "grad_norm": 0.20691435039043427,
+      "learning_rate": 4.198458574181118e-05,
+      "loss": 0.4534,
+      "mean_token_accuracy": 0.8466127276420593,
+      "step": 705
+    },
+    {
+      "epoch": 0.984743411927878,
+      "grad_norm": 0.2122969925403595,
+      "learning_rate": 4.188824662813102e-05,
+      "loss": 0.4744,
+      "mean_token_accuracy": 0.843373692035675,
+      "step": 710
+    },
+    {
+      "epoch": 0.9916782246879334,
+      "grad_norm": 0.18356889486312866,
+      "learning_rate": 4.179190751445087e-05,
+      "loss": 0.4735,
+      "mean_token_accuracy": 0.840711236000061,
+      "step": 715
+    },
+    {
+      "epoch": 0.9986130374479889,
+      "grad_norm": 0.2710322141647339,
+      "learning_rate": 4.169556840077071e-05,
+      "loss": 0.4893,
+      "mean_token_accuracy": 0.8400939464569092,
+      "step": 720
+    },
+    {
+      "epoch": 1.0055478502080444,
+      "grad_norm": 0.28685542941093445,
+      "learning_rate": 4.159922928709056e-05,
+      "loss": 0.4413,
+      "mean_token_accuracy": 0.8504527807235718,
+      "step": 725
+    },
+    {
+      "epoch": 1.0124826629680999,
+      "grad_norm": 0.24674533307552338,
+      "learning_rate": 4.150289017341041e-05,
+      "loss": 0.4098,
+      "mean_token_accuracy": 0.8587909460067749,
+      "step": 730
+    },
+    {
+      "epoch": 1.0194174757281553,
+      "grad_norm": 0.21753250062465668,
+      "learning_rate": 4.140655105973025e-05,
+      "loss": 0.3935,
+      "mean_token_accuracy": 0.8634741544723511,
+      "step": 735
+    },
+    {
+      "epoch": 1.0263522884882108,
+      "grad_norm": 0.20492789149284363,
+      "learning_rate": 4.1310211946050096e-05,
+      "loss": 0.4068,
+      "mean_token_accuracy": 0.8603113770484925,
+      "step": 740
+    },
+    {
+      "epoch": 1.0332871012482663,
+      "grad_norm": 0.16923396289348602,
+      "learning_rate": 4.1213872832369945e-05,
+      "loss": 0.4185,
+      "mean_token_accuracy": 0.8562816023826599,
+      "step": 745
+    },
+    {
+      "epoch": 1.0402219140083218,
+      "grad_norm": 0.18504321575164795,
+      "learning_rate": 4.111753371868979e-05,
+      "loss": 0.4083,
+      "mean_token_accuracy": 0.8588919401168823,
+      "step": 750
+    },
+    {
+      "epoch": 1.0471567267683772,
+      "grad_norm": 0.15754340589046478,
+      "learning_rate": 4.102119460500964e-05,
+      "loss": 0.4001,
+      "mean_token_accuracy": 0.8617303729057312,
+      "step": 755
+    },
+    {
+      "epoch": 1.0540915395284327,
+      "grad_norm": 0.16705656051635742,
+      "learning_rate": 4.0924855491329486e-05,
+      "loss": 0.4124,
+      "mean_token_accuracy": 0.8577338337898255,
+      "step": 760
+    },
+    {
+      "epoch": 1.0610263522884882,
+      "grad_norm": 0.1913621723651886,
+      "learning_rate": 4.082851637764933e-05,
+      "loss": 0.4027,
+      "mean_token_accuracy": 0.860604989528656,
+      "step": 765
+    },
+    {
+      "epoch": 1.0679611650485437,
+      "grad_norm": 0.1807246059179306,
+      "learning_rate": 4.073217726396917e-05,
+      "loss": 0.4154,
+      "mean_token_accuracy": 0.8569133520126343,
+      "step": 770
+    },
+    {
+      "epoch": 1.0748959778085991,
+      "grad_norm": 0.16904115676879883,
+      "learning_rate": 4.063583815028902e-05,
+      "loss": 0.4043,
+      "mean_token_accuracy": 0.8603330969810485,
+      "step": 775
+    },
+    {
+      "epoch": 1.0818307905686546,
+      "grad_norm": 0.13820037245750427,
+      "learning_rate": 4.053949903660886e-05,
+      "loss": 0.4032,
+      "mean_token_accuracy": 0.8607820630073547,
+      "step": 780
+    },
+    {
+      "epoch": 1.08876560332871,
+      "grad_norm": 0.15458045899868011,
+      "learning_rate": 4.0443159922928706e-05,
+      "loss": 0.4126,
+      "mean_token_accuracy": 0.8577965140342713,
+      "step": 785
+    },
+    {
+      "epoch": 1.0957004160887656,
+      "grad_norm": 0.14621621370315552,
+      "learning_rate": 4.034682080924856e-05,
+      "loss": 0.4164,
+      "mean_token_accuracy": 0.8568703651428222,
+      "step": 790
+    },
+    {
+      "epoch": 1.102635228848821,
+      "grad_norm": 0.22418245673179626,
+      "learning_rate": 4.0250481695568404e-05,
+      "loss": 0.4151,
+      "mean_token_accuracy": 0.8572113513946533,
+      "step": 795
+    },
+    {
+      "epoch": 1.1095700416088765,
+      "grad_norm": 0.18166805803775787,
+      "learning_rate": 4.015414258188825e-05,
+      "loss": 0.4236,
+      "mean_token_accuracy": 0.8545473575592041,
+      "step": 800
+    },
+    {
+      "epoch": 1.116504854368932,
+      "grad_norm": 0.19410911202430725,
+      "learning_rate": 4.0057803468208096e-05,
+      "loss": 0.4081,
+      "mean_token_accuracy": 0.8594057202339173,
+      "step": 805
+    },
+    {
+      "epoch": 1.1234396671289875,
+      "grad_norm": 0.15663549304008484,
+      "learning_rate": 3.996146435452794e-05,
+      "loss": 0.41,
+      "mean_token_accuracy": 0.8585174441337585,
+      "step": 810
+    },
+    {
+      "epoch": 1.130374479889043,
+      "grad_norm": 0.2926901578903198,
+      "learning_rate": 3.986512524084778e-05,
+      "loss": 0.4088,
+      "mean_token_accuracy": 0.8590117692947388,
+      "step": 815
+    },
+    {
+      "epoch": 1.1373092926490984,
+      "grad_norm": 0.14440152049064636,
+      "learning_rate": 3.976878612716764e-05,
+      "loss": 0.4029,
+      "mean_token_accuracy": 0.8609296917915344,
+      "step": 820
+    },
+    {
+      "epoch": 1.1442441054091539,
+      "grad_norm": 0.18435537815093994,
+      "learning_rate": 3.967244701348748e-05,
+      "loss": 0.406,
+      "mean_token_accuracy": 0.8599510669708252,
+      "step": 825
+    },
+    {
+      "epoch": 1.1511789181692094,
+      "grad_norm": 0.16614344716072083,
+      "learning_rate": 3.957610789980732e-05,
+      "loss": 0.4165,
+      "mean_token_accuracy": 0.8565038800239563,
+      "step": 830
+    },
+    {
+      "epoch": 1.1581137309292648,
+      "grad_norm": 0.180514857172966,
+      "learning_rate": 3.947976878612717e-05,
+      "loss": 0.4233,
+      "mean_token_accuracy": 0.854881489276886,
+      "step": 835
+    },
+    {
+      "epoch": 1.1650485436893203,
+      "grad_norm": 0.17873796820640564,
+      "learning_rate": 3.9383429672447015e-05,
+      "loss": 0.4142,
+      "mean_token_accuracy": 0.8575613379478455,
+      "step": 840
+    },
+    {
+      "epoch": 1.1719833564493758,
+      "grad_norm": 0.17171607911586761,
+      "learning_rate": 3.928709055876686e-05,
+      "loss": 0.4199,
+      "mean_token_accuracy": 0.8555831432342529,
+      "step": 845
+    },
+    {
+      "epoch": 1.1789181692094313,
+      "grad_norm": 0.2052180916070938,
+      "learning_rate": 3.9190751445086707e-05,
+      "loss": 0.4084,
+      "mean_token_accuracy": 0.8590785980224609,
+      "step": 850
+    },
+    {
+      "epoch": 1.1858529819694867,
+      "grad_norm": 0.16104774177074432,
+      "learning_rate": 3.9094412331406556e-05,
+      "loss": 0.4064,
+      "mean_token_accuracy": 0.8598842978477478,
+      "step": 855
+    },
+    {
+      "epoch": 1.1927877947295422,
+      "grad_norm": 0.16743043065071106,
+      "learning_rate": 3.89980732177264e-05,
+      "loss": 0.4136,
+      "mean_token_accuracy": 0.857661247253418,
+      "step": 860
+    },
+    {
+      "epoch": 1.1997226074895977,
+      "grad_norm": 0.15085460245609283,
+      "learning_rate": 3.890173410404625e-05,
+      "loss": 0.4143,
+      "mean_token_accuracy": 0.8573906064033509,
+      "step": 865
+    },
+    {
+      "epoch": 1.2066574202496532,
+      "grad_norm": 0.14390355348587036,
+      "learning_rate": 3.880539499036609e-05,
+      "loss": 0.4221,
+      "mean_token_accuracy": 0.8549758553504944,
+      "step": 870
+    },
+    {
+      "epoch": 1.2135922330097086,
+      "grad_norm": 0.170955091714859,
+      "learning_rate": 3.870905587668593e-05,
+      "loss": 0.417,
+      "mean_token_accuracy": 0.8564952373504638,
+      "step": 875
+    },
+    {
+      "epoch": 1.2205270457697641,
+      "grad_norm": 0.17432747781276703,
+      "learning_rate": 3.861271676300578e-05,
+      "loss": 0.4065,
+      "mean_token_accuracy": 0.8594078302383423,
+      "step": 880
+    },
+    {
+      "epoch": 1.2274618585298196,
+      "grad_norm": 0.15886807441711426,
+      "learning_rate": 3.851637764932563e-05,
+      "loss": 0.4191,
+      "mean_token_accuracy": 0.8560209155082703,
+      "step": 885
+    },
+    {
+      "epoch": 1.234396671289875,
+      "grad_norm": 0.22739961743354797,
+      "learning_rate": 3.8420038535645474e-05,
+      "loss": 0.4136,
+      "mean_token_accuracy": 0.8580429792404175,
+      "step": 890
+    },
+    {
+      "epoch": 1.2413314840499305,
+      "grad_norm": 0.1761876940727234,
+      "learning_rate": 3.832369942196532e-05,
+      "loss": 0.4058,
+      "mean_token_accuracy": 0.8598258137702942,
+      "step": 895
+    },
+    {
+      "epoch": 1.248266296809986,
+      "grad_norm": 0.8043875098228455,
+      "learning_rate": 3.8227360308285166e-05,
+      "loss": 0.4146,
+      "mean_token_accuracy": 0.8571544885635376,
+      "step": 900
+    },
+    {
+      "epoch": 1.2552011095700415,
+      "grad_norm": 0.18043817579746246,
+      "learning_rate": 3.813102119460501e-05,
+      "loss": 0.4032,
+      "mean_token_accuracy": 0.8605299115180969,
+      "step": 905
+    },
+    {
+      "epoch": 1.262135922330097,
+      "grad_norm": 0.16484476625919342,
+      "learning_rate": 3.803468208092486e-05,
+      "loss": 0.3987,
+      "mean_token_accuracy": 0.8620869636535644,
+      "step": 910
+    },
+    {
+      "epoch": 1.2690707350901524,
+      "grad_norm": 0.15530748665332794,
+      "learning_rate": 3.793834296724471e-05,
+      "loss": 0.4019,
+      "mean_token_accuracy": 0.8608452916145325,
+      "step": 915
+    },
+    {
+      "epoch": 1.276005547850208,
+      "grad_norm": 0.16284696757793427,
+      "learning_rate": 3.784200385356455e-05,
+      "loss": 0.4056,
+      "mean_token_accuracy": 0.8598546504974365,
+      "step": 920
+    },
+    {
+      "epoch": 1.2829403606102634,
+      "grad_norm": 0.15156075358390808,
+      "learning_rate": 3.774566473988439e-05,
+      "loss": 0.4148,
+      "mean_token_accuracy": 0.8573850750923157,
+      "step": 925
+    },
+    {
+      "epoch": 1.2898751733703189,
+      "grad_norm": 0.18044961988925934,
+      "learning_rate": 3.764932562620424e-05,
+      "loss": 0.4165,
+      "mean_token_accuracy": 0.8561815977096557,
+      "step": 930
+    },
+    {
+      "epoch": 1.2968099861303743,
+      "grad_norm": 0.1658436506986618,
+      "learning_rate": 3.7552986512524084e-05,
+      "loss": 0.4056,
+      "mean_token_accuracy": 0.8600709080696106,
+      "step": 935
+    },
+    {
+      "epoch": 1.3037447988904298,
+      "grad_norm": 0.16520382463932037,
+      "learning_rate": 3.7456647398843934e-05,
+      "loss": 0.4148,
+      "mean_token_accuracy": 0.8568984508514405,
+      "step": 940
+    },
+    {
+      "epoch": 1.3106796116504853,
+      "grad_norm": 0.1799880713224411,
+      "learning_rate": 3.736030828516378e-05,
+      "loss": 0.4188,
+      "mean_token_accuracy": 0.856162166595459,
+      "step": 945
+    },
+    {
+      "epoch": 1.317614424410541,
+      "grad_norm": 0.16812920570373535,
+      "learning_rate": 3.7263969171483626e-05,
+      "loss": 0.4111,
+      "mean_token_accuracy": 0.8584610104560852,
+      "step": 950
+    },
+    {
+      "epoch": 1.3245492371705965,
+      "grad_norm": 0.15165302157402039,
+      "learning_rate": 3.716763005780347e-05,
+      "loss": 0.404,
+      "mean_token_accuracy": 0.860293960571289,
+      "step": 955
+    },
+    {
+      "epoch": 1.331484049930652,
+      "grad_norm": 0.13624367117881775,
+      "learning_rate": 3.707129094412332e-05,
+      "loss": 0.4136,
+      "mean_token_accuracy": 0.8572997689247132,
+      "step": 960
+    },
+    {
+      "epoch": 1.3384188626907074,
+      "grad_norm": 0.6036350131034851,
+      "learning_rate": 3.697495183044316e-05,
+      "loss": 0.4139,
+      "mean_token_accuracy": 0.8579724669456482,
+      "step": 965
+    },
+    {
+      "epoch": 1.345353675450763,
+      "grad_norm": 0.16172119975090027,
+      "learning_rate": 3.6878612716763e-05,
+      "loss": 0.4194,
+      "mean_token_accuracy": 0.8556413412094116,
+      "step": 970
+    },
+    {
+      "epoch": 1.3522884882108184,
+      "grad_norm": 0.13519282639026642,
+      "learning_rate": 3.678227360308285e-05,
+      "loss": 0.4053,
+      "mean_token_accuracy": 0.8597145199775695,
+      "step": 975
+    },
+    {
+      "epoch": 1.3592233009708738,
+      "grad_norm": 0.14305779337882996,
+      "learning_rate": 3.66859344894027e-05,
+      "loss": 0.4066,
+      "mean_token_accuracy": 0.8596665501594544,
+      "step": 980
+    },
+    {
+      "epoch": 1.3661581137309293,
+      "grad_norm": 0.18043436110019684,
+      "learning_rate": 3.6589595375722544e-05,
+      "loss": 0.4061,
+      "mean_token_accuracy": 0.8598026871681214,
+      "step": 985
+    },
+    {
+      "epoch": 1.3730929264909848,
+      "grad_norm": 0.12696458399295807,
+      "learning_rate": 3.649325626204239e-05,
+      "loss": 0.4035,
+      "mean_token_accuracy": 0.860295832157135,
+      "step": 990
+    },
+    {
+      "epoch": 1.3800277392510403,
+      "grad_norm": 0.15299014747142792,
+      "learning_rate": 3.6396917148362236e-05,
+      "loss": 0.4045,
+      "mean_token_accuracy": 0.8601055145263672,
+      "step": 995
+    },
+    {
+      "epoch": 1.3869625520110958,
+      "grad_norm": 0.14797343313694,
+      "learning_rate": 3.630057803468208e-05,
+      "loss": 0.4064,
+      "mean_token_accuracy": 0.8599012613296508,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2884,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2953357891076096e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}