Add files using upload-large-folder tool

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 +1,28 @@
+{
+  "_name_or_path": "/inspire/hdd/project/ai4education/public/Models/Qwen/Qwen2___5-32B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.41.2"
+}

latest

@@ -0,0 +1 @@
+global_step232

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8b57240617d73e830dc86d73d91a00dc944afd84a68cbcff61a84ed3a9e8e0
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:accc6df65cdda2e05385826693e49dca20d0c9eac3a83da4d220955f1569db62
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56ccbdf8dad02055774cff4d4c0a455fbacf2cefb69133a576d617602c07ef4
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1830fc7af9cd63ce2c8bf7f022a80edee8c3a3446517206e4a985c4f15c7e797
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce912f94de5243916d01d54495770ec59fecd020df2c348b25442bc9547cd5d
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a43deae5e97ccbeab0935658a3e36806ccd1431c6e729747ee8420cc239df1
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310e1a81a17aa49794c39156d239db850c71dd4c7a381057fe25a3df2f6f6381
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf47593f7b25c9ba598bbcfc7475dfbd0e42327825f12620257456bfec280083
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f49158bf86ae5cdbd922ee2dd888564cfb29f04c02ab80ec5b45f6026216c0
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e767ad4730efdbc10fd37cbb94ed75ff2ac71d196292fdda102b721ac3faa435
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d13ce49a6341f0f840aa60e9aea86e2479f7fd502b41ececaf8db3d9d169200
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65d8da4af29a95bb443bb55b6ca6263e3d020927f0ec4638d47c02b43eb1e58
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec382033f644def53fb7c8e54a124516579cadb242b70694e2d81f49039bc528
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6905011af01d574a99180c9cee70eed7cd477a2b0adf2bc92625655e25468293
+size 2123397800

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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        {{- 'You are InnoSpark, created by Lab of AI Education. You are from East China Normal University(华东师范大学), and your Chinese Name is 启创. You are a helpful assistant. ' }}\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\\nYou are InnoSpark, created by Lab of AI Education. You are from East China Normal University(华东师范大学), and your Chinese Name is 启创. You are a helpful assistant. <|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": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1657 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 232,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017241379310344827,
+      "grad_norm": 80.31050581181768,
+      "learning_rate": 0.0,
+      "loss": 1.4516,
+      "step": 1
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 90.66593902894294,
+      "learning_rate": 1.892789260714372e-05,
+      "loss": 1.0609,
+      "step": 2
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "grad_norm": 90.6412108346005,
+      "learning_rate": 3e-05,
+      "loss": 1.0468,
+      "step": 3
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 21.696996187368597,
+      "learning_rate": 2.9999128304883237e-05,
+      "loss": 0.6824,
+      "step": 4
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 46.08411710784286,
+      "learning_rate": 2.9996513323979987e-05,
+      "loss": 0.9277,
+      "step": 5
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 93.57974123040734,
+      "learning_rate": 2.9992155370618938e-05,
+      "loss": 0.7584,
+      "step": 6
+    },
+    {
+      "epoch": 0.1206896551724138,
+      "grad_norm": 22.43113716035459,
+      "learning_rate": 2.998605496697282e-05,
+      "loss": 0.7961,
+      "step": 7
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 22.006831408953662,
+      "learning_rate": 2.9978212843995877e-05,
+      "loss": 0.7105,
+      "step": 8
+    },
+    {
+      "epoch": 0.15517241379310345,
+      "grad_norm": 29.144093292262927,
+      "learning_rate": 2.9968629941336248e-05,
+      "loss": 0.4781,
+      "step": 9
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 8.93340415736729,
+      "learning_rate": 2.9957307407223423e-05,
+      "loss": 0.3585,
+      "step": 10
+    },
+    {
+      "epoch": 0.1896551724137931,
+      "grad_norm": 20.807302748224,
+      "learning_rate": 2.994424659833062e-05,
+      "loss": 0.4682,
+      "step": 11
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 14.72957736049307,
+      "learning_rate": 2.9929449079612246e-05,
+      "loss": 0.3505,
+      "step": 12
+    },
+    {
+      "epoch": 0.22413793103448276,
+      "grad_norm": 10.43577077098154,
+      "learning_rate": 2.9912916624116393e-05,
+      "loss": 0.3434,
+      "step": 13
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 7.3058963530148775,
+      "learning_rate": 2.9894651212772355e-05,
+      "loss": 0.2807,
+      "step": 14
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 7.108438082150919,
+      "learning_rate": 2.9874655034153328e-05,
+      "loss": 0.2738,
+      "step": 15
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 7.091797143951386,
+      "learning_rate": 2.9852930484214108e-05,
+      "loss": 0.2701,
+      "step": 16
+    },
+    {
+      "epoch": 0.29310344827586204,
+      "grad_norm": 6.676854296806337,
+      "learning_rate": 2.9829480166004073e-05,
+      "loss": 0.2782,
+      "step": 17
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 6.626812093253219,
+      "learning_rate": 2.9804306889355218e-05,
+      "loss": 0.2277,
+      "step": 18
+    },
+    {
+      "epoch": 0.3275862068965517,
+      "grad_norm": 6.379963457248036,
+      "learning_rate": 2.977741367054553e-05,
+      "loss": 0.2053,
+      "step": 19
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 7.29866479655697,
+      "learning_rate": 2.9748803731937552e-05,
+      "loss": 0.2003,
+      "step": 20
+    },
+    {
+      "epoch": 0.3620689655172414,
+      "grad_norm": 6.104965140378312,
+      "learning_rate": 2.9718480501592293e-05,
+      "loss": 0.1867,
+      "step": 21
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 5.557912756675425,
+      "learning_rate": 2.9686447612858447e-05,
+      "loss": 0.1619,
+      "step": 22
+    },
+    {
+      "epoch": 0.39655172413793105,
+      "grad_norm": 4.990529819409756,
+      "learning_rate": 2.9652708903937075e-05,
+      "loss": 0.146,
+      "step": 23
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 4.237040564012678,
+      "learning_rate": 2.9617268417421686e-05,
+      "loss": 0.1229,
+      "step": 24
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 3.4133177060524518,
+      "learning_rate": 2.9580130399813866e-05,
+      "loss": 0.1094,
+      "step": 25
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 2.5718331983652485,
+      "learning_rate": 2.9541299301014464e-05,
+      "loss": 0.1064,
+      "step": 26
+    },
+    {
+      "epoch": 0.46551724137931033,
+      "grad_norm": 2.0498892451815505,
+      "learning_rate": 2.9500779773790364e-05,
+      "loss": 0.0974,
+      "step": 27
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 1.1191261916369943,
+      "learning_rate": 2.9458576673217044e-05,
+      "loss": 0.0953,
+      "step": 28
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.768069035765961,
+      "learning_rate": 2.941469505609679e-05,
+      "loss": 0.1037,
+      "step": 29
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 2.8220934541450293,
+      "learning_rate": 2.9369140180352812e-05,
+      "loss": 0.114,
+      "step": 30
+    },
+    {
+      "epoch": 0.5344827586206896,
+      "grad_norm": 1.361115623756419,
+      "learning_rate": 2.9321917504399238e-05,
+      "loss": 0.0888,
+      "step": 31
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 2.313779528494868,
+      "learning_rate": 2.927303268648707e-05,
+      "loss": 0.1034,
+      "step": 32
+    },
+    {
+      "epoch": 0.5689655172413793,
+      "grad_norm": 1.1190616919358272,
+      "learning_rate": 2.9222491584026204e-05,
+      "loss": 0.0925,
+      "step": 33
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 1.289503080041172,
+      "learning_rate": 2.9170300252883615e-05,
+      "loss": 0.0844,
+      "step": 34
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 1.4272762455921733,
+      "learning_rate": 2.911646494665772e-05,
+      "loss": 0.0916,
+      "step": 35
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 1.6575040568076267,
+      "learning_rate": 2.906099211592908e-05,
+      "loss": 0.0825,
+      "step": 36
+    },
+    {
+      "epoch": 0.6379310344827587,
+      "grad_norm": 0.8814394578120118,
+      "learning_rate": 2.900388840748747e-05,
+      "loss": 0.0737,
+      "step": 37
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.6144518523012089,
+      "learning_rate": 2.894516066353548e-05,
+      "loss": 0.0666,
+      "step": 38
+    },
+    {
+      "epoch": 0.6724137931034483,
+      "grad_norm": 1.8032222595958134,
+      "learning_rate": 2.8884815920868656e-05,
+      "loss": 0.0931,
+      "step": 39
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 1.7506305376078992,
+      "learning_rate": 2.8822861410032354e-05,
+      "loss": 0.0972,
+      "step": 40
+    },
+    {
+      "epoch": 0.7068965517241379,
+      "grad_norm": 0.8060213163884279,
+      "learning_rate": 2.875930455445539e-05,
+      "loss": 0.0823,
+      "step": 41
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.6129565989359341,
+      "learning_rate": 2.8694152969560528e-05,
+      "loss": 0.089,
+      "step": 42
+    },
+    {
+      "epoch": 0.7413793103448276,
+      "grad_norm": 1.0743731023695133,
+      "learning_rate": 2.8627414461852014e-05,
+      "loss": 0.0875,
+      "step": 43
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 1.5600930557862254,
+      "learning_rate": 2.8559097027980196e-05,
+      "loss": 0.088,
+      "step": 44
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 1.9343946859562833,
+      "learning_rate": 2.848920885378336e-05,
+      "loss": 0.075,
+      "step": 45
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 1.4560674593881502,
+      "learning_rate": 2.841775831330688e-05,
+      "loss": 0.0779,
+      "step": 46
+    },
+    {
+      "epoch": 0.8103448275862069,
+      "grad_norm": 0.7158126102048735,
+      "learning_rate": 2.8344753967799867e-05,
+      "loss": 0.0722,
+      "step": 47
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 1.3230016736130281,
+      "learning_rate": 2.827020456468933e-05,
+      "loss": 0.0771,
+      "step": 48
+    },
+    {
+      "epoch": 0.8448275862068966,
+      "grad_norm": 0.8538765569691402,
+      "learning_rate": 2.8194119036532047e-05,
+      "loss": 0.0725,
+      "step": 49
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 1.4515258028875562,
+      "learning_rate": 2.8116506499944298e-05,
+      "loss": 0.0732,
+      "step": 50
+    },
+    {
+      "epoch": 0.8793103448275862,
+      "grad_norm": 0.7743302404539248,
+      "learning_rate": 2.8037376254509465e-05,
+      "loss": 0.0634,
+      "step": 51
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 1.1017487821596053,
+      "learning_rate": 2.7956737781663777e-05,
+      "loss": 0.0692,
+      "step": 52
+    },
+    {
+      "epoch": 0.9137931034482759,
+      "grad_norm": 0.7522946857683028,
+      "learning_rate": 2.7874600743560218e-05,
+      "loss": 0.0605,
+      "step": 53
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.3786133489443896,
+      "learning_rate": 2.7790974981910826e-05,
+      "loss": 0.0587,
+      "step": 54
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 0.8005253080409681,
+      "learning_rate": 2.770587051680743e-05,
+      "loss": 0.066,
+      "step": 55
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.44224502404984106,
+      "learning_rate": 2.761929754552104e-05,
+      "loss": 0.0628,
+      "step": 56
+    },
+    {
+      "epoch": 0.9827586206896551,
+      "grad_norm": 0.9366156857815378,
+      "learning_rate": 2.7531266441280017e-05,
+      "loss": 0.0597,
+      "step": 57
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.45468661449123293,
+      "learning_rate": 2.7441787752027143e-05,
+      "loss": 0.0553,
+      "step": 58
+    },
+    {
+      "epoch": 1.0172413793103448,
+      "grad_norm": 0.5132332441156243,
+      "learning_rate": 2.7350872199155745e-05,
+      "loss": 0.0661,
+      "step": 59
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.8814793538528105,
+      "learning_rate": 2.7258530676225056e-05,
+      "loss": 0.0674,
+      "step": 60
+    },
+    {
+      "epoch": 1.0517241379310345,
+      "grad_norm": 0.648861068817073,
+      "learning_rate": 2.7164774247654965e-05,
+      "loss": 0.0579,
+      "step": 61
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.8442749227291019,
+      "learning_rate": 2.706961414740024e-05,
+      "loss": 0.0545,
+      "step": 62
+    },
+    {
+      "epoch": 1.0862068965517242,
+      "grad_norm": 0.41623096534234333,
+      "learning_rate": 2.6973061777604476e-05,
+      "loss": 0.0538,
+      "step": 63
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.48790289906928386,
+      "learning_rate": 2.68751287072339e-05,
+      "loss": 0.0556,
+      "step": 64
+    },
+    {
+      "epoch": 1.1206896551724137,
+      "grad_norm": 0.45178796557883827,
+      "learning_rate": 2.677582667069115e-05,
+      "loss": 0.0541,
+      "step": 65
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.6897870300753144,
+      "learning_rate": 2.6675167566409273e-05,
+      "loss": 0.0636,
+      "step": 66
+    },
+    {
+      "epoch": 1.1551724137931034,
+      "grad_norm": 0.49099958965668944,
+      "learning_rate": 2.6573163455426008e-05,
+      "loss": 0.0525,
+      "step": 67
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.5015650633274068,
+      "learning_rate": 2.6469826559938675e-05,
+      "loss": 0.0595,
+      "step": 68
+    },
+    {
+      "epoch": 1.1896551724137931,
+      "grad_norm": 1.2796243263087093,
+      "learning_rate": 2.6365169261839658e-05,
+      "loss": 0.0792,
+      "step": 69
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.6662453174247587,
+      "learning_rate": 2.6259204101232846e-05,
+      "loss": 0.0663,
+      "step": 70
+    },
+    {
+      "epoch": 1.2241379310344827,
+      "grad_norm": 1.212387398279308,
+      "learning_rate": 2.6151943774931023e-05,
+      "loss": 0.0613,
+      "step": 71
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 1.0479426277741841,
+      "learning_rate": 2.604340113493456e-05,
+      "loss": 0.0596,
+      "step": 72
+    },
+    {
+      "epoch": 1.2586206896551724,
+      "grad_norm": 0.7987586926269339,
+      "learning_rate": 2.5933589186891452e-05,
+      "loss": 0.0487,
+      "step": 73
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.38709021558416046,
+      "learning_rate": 2.582252108853901e-05,
+      "loss": 0.0571,
+      "step": 74
+    },
+    {
+      "epoch": 1.293103448275862,
+      "grad_norm": 0.46735277155079546,
+      "learning_rate": 2.5710210148127256e-05,
+      "loss": 0.0444,
+      "step": 75
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.597066850436939,
+      "learning_rate": 2.5596669822824356e-05,
+      "loss": 0.0493,
+      "step": 76
+    },
+    {
+      "epoch": 1.3275862068965516,
+      "grad_norm": 0.5692997392561687,
+      "learning_rate": 2.548191371710413e-05,
+      "loss": 0.0559,
+      "step": 77
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.7937487069066846,
+      "learning_rate": 2.5365955581115994e-05,
+      "loss": 0.0681,
+      "step": 78
+    },
+    {
+      "epoch": 1.3620689655172413,
+      "grad_norm": 0.6239501957901394,
+      "learning_rate": 2.5248809309037388e-05,
+      "loss": 0.0639,
+      "step": 79
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.323843186951961,
+      "learning_rate": 2.5130488937408974e-05,
+      "loss": 0.0566,
+      "step": 80
+    },
+    {
+      "epoch": 1.396551724137931,
+      "grad_norm": 0.7601978866920112,
+      "learning_rate": 2.5011008643452776e-05,
+      "loss": 0.0735,
+      "step": 81
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.740263241328343,
+      "learning_rate": 2.489038274337343e-05,
+      "loss": 0.0492,
+      "step": 82
+    },
+    {
+      "epoch": 1.4310344827586206,
+      "grad_norm": 0.46537529182886017,
+      "learning_rate": 2.476862569064284e-05,
+      "loss": 0.0625,
+      "step": 83
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.4150072870993542,
+      "learning_rate": 2.4645752074268322e-05,
+      "loss": 0.0505,
+      "step": 84
+    },
+    {
+      "epoch": 1.4655172413793103,
+      "grad_norm": 0.44405921451606856,
+      "learning_rate": 2.4521776617044573e-05,
+      "loss": 0.0513,
+      "step": 85
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.9108315447108887,
+      "learning_rate": 2.439671417378956e-05,
+      "loss": 0.07,
+      "step": 86
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.4962764163397105,
+      "learning_rate": 2.4270579729564582e-05,
+      "loss": 0.0599,
+      "step": 87
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.41476406186934317,
+      "learning_rate": 2.4143388397878813e-05,
+      "loss": 0.0583,
+      "step": 88
+    },
+    {
+      "epoch": 1.5344827586206895,
+      "grad_norm": 0.8057667799695798,
+      "learning_rate": 2.4015155418878315e-05,
+      "loss": 0.0686,
+      "step": 89
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.4617166561072775,
+      "learning_rate": 2.3885896157520017e-05,
+      "loss": 0.0487,
+      "step": 90
+    },
+    {
+      "epoch": 1.5689655172413794,
+      "grad_norm": 0.6780078347240123,
+      "learning_rate": 2.3755626101730647e-05,
+      "loss": 0.06,
+      "step": 91
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.7034994823546088,
+      "learning_rate": 2.362436086055095e-05,
+      "loss": 0.055,
+      "step": 92
+    },
+    {
+      "epoch": 1.603448275862069,
+      "grad_norm": 0.220042937651117,
+      "learning_rate": 2.3492116162265433e-05,
+      "loss": 0.0521,
+      "step": 93
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.5416790306685376,
+      "learning_rate": 2.3358907852517767e-05,
+      "loss": 0.0559,
+      "step": 94
+    },
+    {
+      "epoch": 1.6379310344827587,
+      "grad_norm": 0.5739325763948568,
+      "learning_rate": 2.3224751892412166e-05,
+      "loss": 0.0478,
+      "step": 95
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.9746158270918538,
+      "learning_rate": 2.3089664356600896e-05,
+      "loss": 0.0483,
+      "step": 96
+    },
+    {
+      "epoch": 1.6724137931034484,
+      "grad_norm": 0.8870891520027294,
+      "learning_rate": 2.295366143135823e-05,
+      "loss": 0.0548,
+      "step": 97
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.6701707516695699,
+      "learning_rate": 2.2816759412640983e-05,
+      "loss": 0.0619,
+      "step": 98
+    },
+    {
+      "epoch": 1.706896551724138,
+      "grad_norm": 0.4649690411116379,
+      "learning_rate": 2.2678974704135914e-05,
+      "loss": 0.0544,
+      "step": 99
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.5666448156500851,
+      "learning_rate": 2.2540323815294228e-05,
+      "loss": 0.0556,
+      "step": 100
+    },
+    {
+      "epoch": 1.7413793103448276,
+      "grad_norm": 0.5747839293651054,
+      "learning_rate": 2.2400823359353427e-05,
+      "loss": 0.0518,
+      "step": 101
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.5035038013712511,
+      "learning_rate": 2.2260490051346664e-05,
+      "loss": 0.0502,
+      "step": 102
+    },
+    {
+      "epoch": 1.7758620689655173,
+      "grad_norm": 0.4353431259303049,
+      "learning_rate": 2.211934070609996e-05,
+      "loss": 0.0518,
+      "step": 103
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 0.7282410377739317,
+      "learning_rate": 2.1977392236217437e-05,
+      "loss": 0.0547,
+      "step": 104
+    },
+    {
+      "epoch": 1.8103448275862069,
+      "grad_norm": 0.2269975333174313,
+      "learning_rate": 2.1834661650054842e-05,
+      "loss": 0.0465,
+      "step": 105
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.6795575686384344,
+      "learning_rate": 2.1691166049681583e-05,
+      "loss": 0.0563,
+      "step": 106
+    },
+    {
+      "epoch": 1.8448275862068966,
+      "grad_norm": 0.4185343329339508,
+      "learning_rate": 2.1546922628831557e-05,
+      "loss": 0.0474,
+      "step": 107
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 0.29021178988123264,
+      "learning_rate": 2.1401948670842993e-05,
+      "loss": 0.0551,
+      "step": 108
+    },
+    {
+      "epoch": 1.8793103448275863,
+      "grad_norm": 0.4104860523876863,
+      "learning_rate": 2.1256261546587544e-05,
+      "loss": 0.048,
+      "step": 109
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.48654750487264353,
+      "learning_rate": 2.1109878712388884e-05,
+      "loss": 0.0486,
+      "step": 110
+    },
+    {
+      "epoch": 1.9137931034482758,
+      "grad_norm": 0.29782223166209676,
+      "learning_rate": 2.0962817707931105e-05,
+      "loss": 0.0515,
+      "step": 111
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.3784591160214946,
+      "learning_rate": 2.081509615415708e-05,
+      "loss": 0.0644,
+      "step": 112
+    },
+    {
+      "epoch": 1.9482758620689655,
+      "grad_norm": 0.427685460468331,
+      "learning_rate": 2.066673175115714e-05,
+      "loss": 0.0518,
+      "step": 113
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.6180035471613788,
+      "learning_rate": 2.0517742276048204e-05,
+      "loss": 0.0443,
+      "step": 114
+    },
+    {
+      "epoch": 1.9827586206896552,
+      "grad_norm": 0.2153109585578122,
+      "learning_rate": 2.0368145580843715e-05,
+      "loss": 0.0556,
+      "step": 115
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2786578624422437,
+      "learning_rate": 2.0217959590314645e-05,
+      "loss": 0.0513,
+      "step": 116
+    },
+    {
+      "epoch": 2.0172413793103448,
+      "grad_norm": 0.22457752001893297,
+      "learning_rate": 2.0067202299841676e-05,
+      "loss": 0.0402,
+      "step": 117
+    },
+    {
+      "epoch": 2.0344827586206895,
+      "grad_norm": 0.40115360043809567,
+      "learning_rate": 1.9915891773259033e-05,
+      "loss": 0.0469,
+      "step": 118
+    },
+    {
+      "epoch": 2.0517241379310347,
+      "grad_norm": 0.3848178266559636,
+      "learning_rate": 1.9764046140690026e-05,
+      "loss": 0.0447,
+      "step": 119
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.34564228923454376,
+      "learning_rate": 1.9611683596374723e-05,
+      "loss": 0.0373,
+      "step": 120
+    },
+    {
+      "epoch": 2.086206896551724,
+      "grad_norm": 0.8318106488703036,
+      "learning_rate": 1.9458822396489862e-05,
+      "loss": 0.0401,
+      "step": 121
+    },
+    {
+      "epoch": 2.103448275862069,
+      "grad_norm": 0.514176269742461,
+      "learning_rate": 1.9305480856961432e-05,
+      "loss": 0.0471,
+      "step": 122
+    },
+    {
+      "epoch": 2.1206896551724137,
+      "grad_norm": 0.6560806101214318,
+      "learning_rate": 1.9151677351269996e-05,
+      "loss": 0.0424,
+      "step": 123
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 0.6241496977729802,
+      "learning_rate": 1.899743030824922e-05,
+      "loss": 0.044,
+      "step": 124
+    },
+    {
+      "epoch": 2.1551724137931036,
+      "grad_norm": 0.7064617244721939,
+      "learning_rate": 1.8842758209877685e-05,
+      "loss": 0.0433,
+      "step": 125
+    },
+    {
+      "epoch": 2.1724137931034484,
+      "grad_norm": 0.5397965781860613,
+      "learning_rate": 1.8687679589064374e-05,
+      "loss": 0.0529,
+      "step": 126
+    },
+    {
+      "epoch": 2.189655172413793,
+      "grad_norm": 0.4114471647300015,
+      "learning_rate": 1.853221302742805e-05,
+      "loss": 0.043,
+      "step": 127
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 0.6619594933212386,
+      "learning_rate": 1.837637715307078e-05,
+      "loss": 0.0431,
+      "step": 128
+    },
+    {
+      "epoch": 2.2241379310344827,
+      "grad_norm": 0.6788037792348437,
+      "learning_rate": 1.8220190638345925e-05,
+      "loss": 0.0421,
+      "step": 129
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.44437222175427143,
+      "learning_rate": 1.8063672197620804e-05,
+      "loss": 0.0446,
+      "step": 130
+    },
+    {
+      "epoch": 2.2586206896551726,
+      "grad_norm": 0.21556298635731527,
+      "learning_rate": 1.7906840585034305e-05,
+      "loss": 0.0397,
+      "step": 131
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.4888413230768935,
+      "learning_rate": 1.7749714592249782e-05,
+      "loss": 0.0391,
+      "step": 132
+    },
+    {
+      "epoch": 2.293103448275862,
+      "grad_norm": 0.5684832408467927,
+      "learning_rate": 1.75923130462034e-05,
+      "loss": 0.0485,
+      "step": 133
+    },
+    {
+      "epoch": 2.310344827586207,
+      "grad_norm": 0.5532199357884209,
+      "learning_rate": 1.7434654806848293e-05,
+      "loss": 0.0487,
+      "step": 134
+    },
+    {
+      "epoch": 2.3275862068965516,
+      "grad_norm": 0.44377530119856,
+      "learning_rate": 1.727675876489475e-05,
+      "loss": 0.0349,
+      "step": 135
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 0.4375182897286949,
+      "learning_rate": 1.711864383954673e-05,
+      "loss": 0.046,
+      "step": 136
+    },
+    {
+      "epoch": 2.3620689655172415,
+      "grad_norm": 0.27063975232289045,
+      "learning_rate": 1.696032897623492e-05,
+      "loss": 0.0408,
+      "step": 137
+    },
+    {
+      "epoch": 2.3793103448275863,
+      "grad_norm": 0.3090699541525638,
+      "learning_rate": 1.6801833144346706e-05,
+      "loss": 0.0409,
+      "step": 138
+    },
+    {
+      "epoch": 2.396551724137931,
+      "grad_norm": 0.3790621682501314,
+      "learning_rate": 1.6643175334953248e-05,
+      "loss": 0.036,
+      "step": 139
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.4048549467693139,
+      "learning_rate": 1.6484374558533966e-05,
+      "loss": 0.0432,
+      "step": 140
+    },
+    {
+      "epoch": 2.4310344827586206,
+      "grad_norm": 0.4287299844946669,
+      "learning_rate": 1.632544984269866e-05,
+      "loss": 0.0518,
+      "step": 141
+    },
+    {
+      "epoch": 2.4482758620689653,
+      "grad_norm": 0.45024313848499997,
+      "learning_rate": 1.616642022990764e-05,
+      "loss": 0.0361,
+      "step": 142
+    },
+    {
+      "epoch": 2.4655172413793105,
+      "grad_norm": 0.4484803973425137,
+      "learning_rate": 1.6007304775190018e-05,
+      "loss": 0.0378,
+      "step": 143
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 0.32950999105006323,
+      "learning_rate": 1.5848122543860562e-05,
+      "loss": 0.0442,
+      "step": 144
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.1977755311044798,
+      "learning_rate": 1.568889260923525e-05,
+      "loss": 0.0403,
+      "step": 145
+    },
+    {
+      "epoch": 2.5172413793103448,
+      "grad_norm": 0.2718588763969704,
+      "learning_rate": 1.5529634050345898e-05,
+      "loss": 0.0422,
+      "step": 146
+    },
+    {
+      "epoch": 2.5344827586206895,
+      "grad_norm": 0.31806067044898856,
+      "learning_rate": 1.5370365949654098e-05,
+      "loss": 0.0451,
+      "step": 147
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 0.29463586138392256,
+      "learning_rate": 1.5211107390764749e-05,
+      "loss": 0.0415,
+      "step": 148
+    },
+    {
+      "epoch": 2.5689655172413794,
+      "grad_norm": 0.2244206257417315,
+      "learning_rate": 1.5051877456139439e-05,
+      "loss": 0.0376,
+      "step": 149
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.5863234456871204,
+      "learning_rate": 1.4892695224809986e-05,
+      "loss": 0.0406,
+      "step": 150
+    },
+    {
+      "epoch": 2.603448275862069,
+      "grad_norm": 0.17400182660455388,
+      "learning_rate": 1.4733579770092367e-05,
+      "loss": 0.0416,
+      "step": 151
+    },
+    {
+      "epoch": 2.6206896551724137,
+      "grad_norm": 0.358095878096067,
+      "learning_rate": 1.457455015730134e-05,
+      "loss": 0.0339,
+      "step": 152
+    },
+    {
+      "epoch": 2.637931034482759,
+      "grad_norm": 0.6408337276302095,
+      "learning_rate": 1.4415625441466033e-05,
+      "loss": 0.0481,
+      "step": 153
+    },
+    {
+      "epoch": 2.655172413793103,
+      "grad_norm": 0.5033929265450956,
+      "learning_rate": 1.4256824665046749e-05,
+      "loss": 0.0433,
+      "step": 154
+    },
+    {
+      "epoch": 2.6724137931034484,
+      "grad_norm": 0.4224811543826838,
+      "learning_rate": 1.40981668556533e-05,
+      "loss": 0.0358,
+      "step": 155
+    },
+    {
+      "epoch": 2.689655172413793,
+      "grad_norm": 0.6210472281444889,
+      "learning_rate": 1.3939671023765087e-05,
+      "loss": 0.0403,
+      "step": 156
+    },
+    {
+      "epoch": 2.706896551724138,
+      "grad_norm": 0.7509429884450859,
+      "learning_rate": 1.3781356160453275e-05,
+      "loss": 0.0339,
+      "step": 157
+    },
+    {
+      "epoch": 2.7241379310344827,
+      "grad_norm": 0.47959730934417544,
+      "learning_rate": 1.362324123510525e-05,
+      "loss": 0.0371,
+      "step": 158
+    },
+    {
+      "epoch": 2.7413793103448274,
+      "grad_norm": 0.3282804801964574,
+      "learning_rate": 1.3465345193151709e-05,
+      "loss": 0.0401,
+      "step": 159
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.28076426629279005,
+      "learning_rate": 1.3307686953796603e-05,
+      "loss": 0.0265,
+      "step": 160
+    },
+    {
+      "epoch": 2.7758620689655173,
+      "grad_norm": 0.3945531178070007,
+      "learning_rate": 1.3150285407750218e-05,
+      "loss": 0.0437,
+      "step": 161
+    },
+    {
+      "epoch": 2.793103448275862,
+      "grad_norm": 0.18910480215177314,
+      "learning_rate": 1.299315941496569e-05,
+      "loss": 0.028,
+      "step": 162
+    },
+    {
+      "epoch": 2.810344827586207,
+      "grad_norm": 0.36962844264053035,
+      "learning_rate": 1.2836327802379196e-05,
+      "loss": 0.0303,
+      "step": 163
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.5711119809352289,
+      "learning_rate": 1.2679809361654076e-05,
+      "loss": 0.0331,
+      "step": 164
+    },
+    {
+      "epoch": 2.844827586206897,
+      "grad_norm": 0.3003204085055974,
+      "learning_rate": 1.2523622846929226e-05,
+      "loss": 0.0362,
+      "step": 165
+    },
+    {
+      "epoch": 2.862068965517241,
+      "grad_norm": 0.31404544632192555,
+      "learning_rate": 1.2367786972571957e-05,
+      "loss": 0.0339,
+      "step": 166
+    },
+    {
+      "epoch": 2.8793103448275863,
+      "grad_norm": 0.26321708168896896,
+      "learning_rate": 1.2212320410935632e-05,
+      "loss": 0.0354,
+      "step": 167
+    },
+    {
+      "epoch": 2.896551724137931,
+      "grad_norm": 0.42819450398971026,
+      "learning_rate": 1.2057241790122319e-05,
+      "loss": 0.0346,
+      "step": 168
+    },
+    {
+      "epoch": 2.913793103448276,
+      "grad_norm": 0.476993975190435,
+      "learning_rate": 1.1902569691750782e-05,
+      "loss": 0.037,
+      "step": 169
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 0.5227017712120989,
+      "learning_rate": 1.1748322648730002e-05,
+      "loss": 0.0367,
+      "step": 170
+    },
+    {
+      "epoch": 2.9482758620689653,
+      "grad_norm": 0.573643532517419,
+      "learning_rate": 1.1594519143038573e-05,
+      "loss": 0.0321,
+      "step": 171
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 0.2565210391844935,
+      "learning_rate": 1.1441177603510138e-05,
+      "loss": 0.0387,
+      "step": 172
+    },
+    {
+      "epoch": 2.9827586206896552,
+      "grad_norm": 0.2996752083478276,
+      "learning_rate": 1.1288316403625276e-05,
+      "loss": 0.0411,
+      "step": 173
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3269862100138925,
+      "learning_rate": 1.1135953859309974e-05,
+      "loss": 0.038,
+      "step": 174
+    },
+    {
+      "epoch": 3.0172413793103448,
+      "grad_norm": 0.41839666832578426,
+      "learning_rate": 1.0984108226740968e-05,
+      "loss": 0.0344,
+      "step": 175
+    },
+    {
+      "epoch": 3.0344827586206895,
+      "grad_norm": 0.33310564902822715,
+      "learning_rate": 1.0832797700158324e-05,
+      "loss": 0.0278,
+      "step": 176
+    },
+    {
+      "epoch": 3.0517241379310347,
+      "grad_norm": 0.30304190489746813,
+      "learning_rate": 1.0682040409685357e-05,
+      "loss": 0.036,
+      "step": 177
+    },
+    {
+      "epoch": 3.0689655172413794,
+      "grad_norm": 0.19063903842888325,
+      "learning_rate": 1.0531854419156286e-05,
+      "loss": 0.0249,
+      "step": 178
+    },
+    {
+      "epoch": 3.086206896551724,
+      "grad_norm": 0.26112379231134863,
+      "learning_rate": 1.0382257723951802e-05,
+      "loss": 0.0256,
+      "step": 179
+    },
+    {
+      "epoch": 3.103448275862069,
+      "grad_norm": 0.26023947727649255,
+      "learning_rate": 1.0233268248842857e-05,
+      "loss": 0.0284,
+      "step": 180
+    },
+    {
+      "epoch": 3.1206896551724137,
+      "grad_norm": 0.5175700924807861,
+      "learning_rate": 1.0084903845842919e-05,
+      "loss": 0.026,
+      "step": 181
+    },
+    {
+      "epoch": 3.1379310344827585,
+      "grad_norm": 0.3240038492767359,
+      "learning_rate": 9.937182292068898e-06,
+      "loss": 0.0298,
+      "step": 182
+    },
+    {
+      "epoch": 3.1551724137931036,
+      "grad_norm": 0.3720902965715703,
+      "learning_rate": 9.790121287611119e-06,
+      "loss": 0.0202,
+      "step": 183
+    },
+    {
+      "epoch": 3.1724137931034484,
+      "grad_norm": 0.2768496692729557,
+      "learning_rate": 9.64373845341246e-06,
+      "loss": 0.0201,
+      "step": 184
+    },
+    {
+      "epoch": 3.189655172413793,
+      "grad_norm": 0.24807187202234196,
+      "learning_rate": 9.498051329157004e-06,
+      "loss": 0.0206,
+      "step": 185
+    },
+    {
+      "epoch": 3.206896551724138,
+      "grad_norm": 0.2860347071859339,
+      "learning_rate": 9.353077371168444e-06,
+      "loss": 0.0232,
+      "step": 186
+    },
+    {
+      "epoch": 3.2241379310344827,
+      "grad_norm": 0.3828846221247785,
+      "learning_rate": 9.208833950318425e-06,
+      "loss": 0.0314,
+      "step": 187
+    },
+    {
+      "epoch": 3.2413793103448274,
+      "grad_norm": 0.3738366798689589,
+      "learning_rate": 9.065338349945159e-06,
+      "loss": 0.0284,
+      "step": 188
+    },
+    {
+      "epoch": 3.2586206896551726,
+      "grad_norm": 0.3189800741077174,
+      "learning_rate": 8.922607763782567e-06,
+      "loss": 0.0304,
+      "step": 189
+    },
+    {
+      "epoch": 3.2758620689655173,
+      "grad_norm": 0.8535829775006718,
+      "learning_rate": 8.78065929390004e-06,
+      "loss": 0.0244,
+      "step": 190
+    },
+    {
+      "epoch": 3.293103448275862,
+      "grad_norm": 0.2412509344507808,
+      "learning_rate": 8.639509948653339e-06,
+      "loss": 0.0196,
+      "step": 191
+    },
+    {
+      "epoch": 3.310344827586207,
+      "grad_norm": 0.2438682333590634,
+      "learning_rate": 8.499176640646574e-06,
+      "loss": 0.0193,
+      "step": 192
+    },
+    {
+      "epoch": 3.3275862068965516,
+      "grad_norm": 0.515406851427045,
+      "learning_rate": 8.359676184705773e-06,
+      "loss": 0.0317,
+      "step": 193
+    },
+    {
+      "epoch": 3.344827586206897,
+      "grad_norm": 0.26674244550270093,
+      "learning_rate": 8.22102529586409e-06,
+      "loss": 0.0219,
+      "step": 194
+    },
+    {
+      "epoch": 3.3620689655172415,
+      "grad_norm": 0.3562088482495647,
+      "learning_rate": 8.083240587359024e-06,
+      "loss": 0.0145,
+      "step": 195
+    },
+    {
+      "epoch": 3.3793103448275863,
+      "grad_norm": 0.2853586706468104,
+      "learning_rate": 7.946338568641774e-06,
+      "loss": 0.0233,
+      "step": 196
+    },
+    {
+      "epoch": 3.396551724137931,
+      "grad_norm": 0.22309988564377628,
+      "learning_rate": 7.810335643399106e-06,
+      "loss": 0.0249,
+      "step": 197
+    },
+    {
+      "epoch": 3.413793103448276,
+      "grad_norm": 0.21904384937696103,
+      "learning_rate": 7.67524810758784e-06,
+      "loss": 0.0274,
+      "step": 198
+    },
+    {
+      "epoch": 3.4310344827586206,
+      "grad_norm": 0.231369464855975,
+      "learning_rate": 7.541092147482234e-06,
+      "loss": 0.0205,
+      "step": 199
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 0.31673400292650616,
+      "learning_rate": 7.407883837734573e-06,
+      "loss": 0.0227,
+      "step": 200
+    },
+    {
+      "epoch": 3.4655172413793105,
+      "grad_norm": 0.23560651052719475,
+      "learning_rate": 7.2756391394490495e-06,
+      "loss": 0.019,
+      "step": 201
+    },
+    {
+      "epoch": 3.4827586206896552,
+      "grad_norm": 0.355736746737518,
+      "learning_rate": 7.144373898269359e-06,
+      "loss": 0.02,
+      "step": 202
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.13952720154573706,
+      "learning_rate": 7.014103842479983e-06,
+      "loss": 0.02,
+      "step": 203
+    },
+    {
+      "epoch": 3.5172413793103448,
+      "grad_norm": 0.24605295812008457,
+      "learning_rate": 6.884844581121684e-06,
+      "loss": 0.0221,
+      "step": 204
+    },
+    {
+      "epoch": 3.5344827586206895,
+      "grad_norm": 0.1804914629461453,
+      "learning_rate": 6.756611602121192e-06,
+      "loss": 0.0141,
+      "step": 205
+    },
+    {
+      "epoch": 3.5517241379310347,
+      "grad_norm": 0.29158022854253035,
+      "learning_rate": 6.629420270435416e-06,
+      "loss": 0.0167,
+      "step": 206
+    },
+    {
+      "epoch": 3.5689655172413794,
+      "grad_norm": 0.18846167866340074,
+      "learning_rate": 6.503285826210448e-06,
+      "loss": 0.0222,
+      "step": 207
+    },
+    {
+      "epoch": 3.586206896551724,
+      "grad_norm": 0.1583714943206511,
+      "learning_rate": 6.378223382955428e-06,
+      "loss": 0.0174,
+      "step": 208
+    },
+    {
+      "epoch": 3.603448275862069,
+      "grad_norm": 0.3967321777174731,
+      "learning_rate": 6.2542479257316834e-06,
+      "loss": 0.0248,
+      "step": 209
+    },
+    {
+      "epoch": 3.6206896551724137,
+      "grad_norm": 0.31844884399258744,
+      "learning_rate": 6.131374309357168e-06,
+      "loss": 0.0176,
+      "step": 210
+    },
+    {
+      "epoch": 3.637931034482759,
+      "grad_norm": 0.33630177242876536,
+      "learning_rate": 6.009617256626572e-06,
+      "loss": 0.014,
+      "step": 211
+    },
+    {
+      "epoch": 3.655172413793103,
+      "grad_norm": 0.266018799974313,
+      "learning_rate": 5.888991356547223e-06,
+      "loss": 0.022,
+      "step": 212
+    },
+    {
+      "epoch": 3.6724137931034484,
+      "grad_norm": 0.34989553067481094,
+      "learning_rate": 5.769511062591021e-06,
+      "loss": 0.017,
+      "step": 213
+    },
+    {
+      "epoch": 3.689655172413793,
+      "grad_norm": 0.3525004273269985,
+      "learning_rate": 5.651190690962615e-06,
+      "loss": 0.0236,
+      "step": 214
+    },
+    {
+      "epoch": 3.706896551724138,
+      "grad_norm": 0.20730528599041878,
+      "learning_rate": 5.5340444188840075e-06,
+      "loss": 0.0159,
+      "step": 215
+    },
+    {
+      "epoch": 3.7241379310344827,
+      "grad_norm": 0.302121656003982,
+      "learning_rate": 5.4180862828958736e-06,
+      "loss": 0.0213,
+      "step": 216
+    },
+    {
+      "epoch": 3.7413793103448274,
+      "grad_norm": 0.22206626492504716,
+      "learning_rate": 5.303330177175645e-06,
+      "loss": 0.0154,
+      "step": 217
+    },
+    {
+      "epoch": 3.7586206896551726,
+      "grad_norm": 0.23122272169473673,
+      "learning_rate": 5.189789851872745e-06,
+      "loss": 0.0111,
+      "step": 218
+    },
+    {
+      "epoch": 3.7758620689655173,
+      "grad_norm": 0.2036574153500964,
+      "learning_rate": 5.077478911460993e-06,
+      "loss": 0.0141,
+      "step": 219
+    },
+    {
+      "epoch": 3.793103448275862,
+      "grad_norm": 0.3082821516245183,
+      "learning_rate": 4.9664108131085495e-06,
+      "loss": 0.0191,
+      "step": 220
+    },
+    {
+      "epoch": 3.810344827586207,
+      "grad_norm": 0.2037428116846801,
+      "learning_rate": 4.856598865065446e-06,
+      "loss": 0.0137,
+      "step": 221
+    },
+    {
+      "epoch": 3.8275862068965516,
+      "grad_norm": 0.155124875139698,
+      "learning_rate": 4.748056225068973e-06,
+      "loss": 0.0182,
+      "step": 222
+    },
+    {
+      "epoch": 3.844827586206897,
+      "grad_norm": 0.2707756039030258,
+      "learning_rate": 4.640795898767154e-06,
+      "loss": 0.0162,
+      "step": 223
+    },
+    {
+      "epoch": 3.862068965517241,
+      "grad_norm": 0.3691019310426078,
+      "learning_rate": 4.53483073816034e-06,
+      "loss": 0.0196,
+      "step": 224
+    },
+    {
+      "epoch": 3.8793103448275863,
+      "grad_norm": 0.2560322010400225,
+      "learning_rate": 4.4301734400613326e-06,
+      "loss": 0.0203,
+      "step": 225
+    },
+    {
+      "epoch": 3.896551724137931,
+      "grad_norm": 0.1865861797161085,
+      "learning_rate": 4.3268365445739955e-06,
+      "loss": 0.0119,
+      "step": 226
+    },
+    {
+      "epoch": 3.913793103448276,
+      "grad_norm": 0.24921046694680007,
+      "learning_rate": 4.224832433590729e-06,
+      "loss": 0.0171,
+      "step": 227
+    },
+    {
+      "epoch": 3.9310344827586206,
+      "grad_norm": 0.2623082113135812,
+      "learning_rate": 4.12417332930885e-06,
+      "loss": 0.0146,
+      "step": 228
+    },
+    {
+      "epoch": 3.9482758620689653,
+      "grad_norm": 0.19305679459444855,
+      "learning_rate": 4.0248712927661005e-06,
+      "loss": 0.0169,
+      "step": 229
+    },
+    {
+      "epoch": 3.9655172413793105,
+      "grad_norm": 0.41239919008625026,
+      "learning_rate": 3.926938222395527e-06,
+      "loss": 0.0218,
+      "step": 230
+    },
+    {
+      "epoch": 3.9827586206896552,
+      "grad_norm": 0.16179670491340867,
+      "learning_rate": 3.830385852599764e-06,
+      "loss": 0.0136,
+      "step": 231
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.21889193221870137,
+      "learning_rate": 3.735225752345039e-06,
+      "loss": 0.0162,
+      "step": 232
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 290,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 4.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3266421681291264.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0edfb088877cf335b998373471d40e7e198d126aa16657a993c6b68c7c5b49b
+size 7032