Add files using upload-large-folder tool

.gitattributes

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

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.3"
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce64fdf5a5a34abc6ada781c39612beb35b3c829a126d69ae51b17c3815095b
+size 4498420872

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:904afb3e09d3eafef55b2962772c4ae4c48f362a96c5961264c7af423244be10
+size 4718804768

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ea1adc449da66909787e46ada1c90106e580205d4770248bf27512e0494cdf
+size 4467075880

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8ed2fdc54ca33ac3b2abcd9e2622138dbef15ab1343a6e3314cf06731f7b63
+size 4467075880

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198f6ba8fd03caf17bb4633eed4096f17f256a5ecb6467f5d4c9e8df4706169d
+size 4718804760

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ab7fb10ef800b7c7e4c567208328d710117cb18aaf0f9d058b02f3f515c961
+size 4467075904

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:904bff60904fff8b2f535b619185d8262db9fddcc5f7d2afad805cff67ba8a87
+size 4467075904

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78f2497f4090ed5325b994811666dd16c0353d55eb51c49d3d94e6ea3ea741b
+size 4718804800

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836df23ed527bf96117e2b4dba42b7ecf0c562c6ca8b9f757715a88cb91c69d2
+size 4467075904

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b8b016a66bc59ae0da6b79b329dc7cc8124dca2067ff104b714dbb051806f6
+size 4467075904

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a2a70bcb0caf793c453a2eb2cc144f677c15a7514867cec6d2739c7e6fc26d
+size 4718804800

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a343aabb1d4a05e947ba0a6442b79904e3e2f6e98bc47114218cc1133720871
+size 4467075904

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a36475006a71224df113ffcdaa3acc0b9e1dba574cd3a70463b115f48c1f05
+size 4467075904

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ba5d72a7ac3fed59282e81c3d487b7353876f9cf2772bfc9338cbf55db787b
+size 4718804800

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd61a71cbfe1e411ff6a211cc43cdfcc22d42f45b8fbcf53c2d2529da995813
+size 4467075904

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b668dcaac62a7a47beec96008b05ed6fa1ff22af4d5abc623754b0b0bb6863
+size 4467075904

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1cd7cc05898534c1fdf32361bf8f908422d113825a528038727645fa03bdf7
+size 4718804800

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6cc9c7d7d8a3232ee23efcaeda5fe6513feb047112170b925d6df7afa54829f
+size 4467075904

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bcbd930ae8177fed7234462a9b4d6ee18ca3198a9584051d260a13f648e8f3d
+size 4467075904

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168f84ee45c8812d5bab3c931025fce030ce374105777340846ee24b1170bc11
+size 4718804800

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2f2b52251f69bc7c279a731911f2a6fbd718f4291923ab15b246a94eefcdda
+size 4467075904

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258d7c6573e9ccab6de03b41add4c2eb2644c374ad07118461b95d2810ba9426
+size 4467075904

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1606e6ba75591e99280c797fecf09dff7a75335b49029b782faee6231689552
+size 4718804800

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b698764015bf83c25a07712aca741d65c4f74c7dcf32bf5315ae976ee0d1539
+size 4467075904

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf5e412762da21f0bd196e789a041723081bb8665ac5034272f82a3c1d1dce4
+size 4467075904

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106ee42f9f9cd13aaa8761ef1b4ffad047041040ca0d3289e4edf894be80cda7
+size 4718804800

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8450a83a75ea7804955cccffdee8f3b7c8eb279883769f1a796c14563b3c38cc
+size 4467075904

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc1db130dad06ef3f5be5d14f472c6a271fab7dba5429920c1593e8536c8664
+size 4467075904

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2f46325cde590f189b7ed0d271a9319c095f6026512bdc0d0d9066e209c00a
+size 3680563768

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 131055505408
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00029-of-00029.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.norm.weight": "model-00029-of-00029.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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. 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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2553 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 315,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015873015873015872,
+      "grad_norm": 7.645266056060791,
+      "learning_rate": 6.25e-07,
+      "loss": 1.366,
+      "mean_token_accuracy": 0.6359601020812988,
+      "step": 1
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 8.354494094848633,
+      "learning_rate": 1.25e-06,
+      "loss": 1.4918,
+      "mean_token_accuracy": 0.648927628993988,
+      "step": 2
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 7.670858383178711,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.4791,
+      "mean_token_accuracy": 0.610198974609375,
+      "step": 3
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 8.558603286743164,
+      "learning_rate": 2.5e-06,
+      "loss": 1.507,
+      "mean_token_accuracy": 0.6174368262290955,
+      "step": 4
+    },
+    {
+      "epoch": 0.07936507936507936,
+      "grad_norm": 7.195960521697998,
+      "learning_rate": 3.125e-06,
+      "loss": 1.4965,
+      "mean_token_accuracy": 0.6209526658058167,
+      "step": 5
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 6.573232173919678,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.3766,
+      "mean_token_accuracy": 0.62288898229599,
+      "step": 6
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 4.44756555557251,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 1.2835,
+      "mean_token_accuracy": 0.6413974761962891,
+      "step": 7
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 4.386582851409912,
+      "learning_rate": 5e-06,
+      "loss": 1.274,
+      "mean_token_accuracy": 0.6449005007743835,
+      "step": 8
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 2.9588849544525146,
+      "learning_rate": 5.625e-06,
+      "loss": 1.2105,
+      "mean_token_accuracy": 0.6454917192459106,
+      "step": 9
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 2.780573844909668,
+      "learning_rate": 6.25e-06,
+      "loss": 1.2936,
+      "mean_token_accuracy": 0.626201868057251,
+      "step": 10
+    },
+    {
+      "epoch": 0.1746031746031746,
+      "grad_norm": 2.3944156169891357,
+      "learning_rate": 6.875e-06,
+      "loss": 1.1906,
+      "mean_token_accuracy": 0.6416702270507812,
+      "step": 11
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 2.4857006072998047,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.1477,
+      "mean_token_accuracy": 0.6536551713943481,
+      "step": 12
+    },
+    {
+      "epoch": 0.20634920634920634,
+      "grad_norm": 3.2947516441345215,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 1.0916,
+      "mean_token_accuracy": 0.674787700176239,
+      "step": 13
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 3.138019561767578,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.181,
+      "mean_token_accuracy": 0.6426388025283813,
+      "step": 14
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 3.0852348804473877,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 1.1424,
+      "mean_token_accuracy": 0.6612462997436523,
+      "step": 15
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 2.2055983543395996,
+      "learning_rate": 1e-05,
+      "loss": 1.0388,
+      "mean_token_accuracy": 0.6682813167572021,
+      "step": 16
+    },
+    {
+      "epoch": 0.2698412698412698,
+      "grad_norm": 2.2655630111694336,
+      "learning_rate": 9.999724009977419e-06,
+      "loss": 1.116,
+      "mean_token_accuracy": 0.668512761592865,
+      "step": 17
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 3.348353862762451,
+      "learning_rate": 9.998896070377873e-06,
+      "loss": 1.0509,
+      "mean_token_accuracy": 0.6763769388198853,
+      "step": 18
+    },
+    {
+      "epoch": 0.30158730158730157,
+      "grad_norm": 2.178619861602783,
+      "learning_rate": 9.99751627260259e-06,
+      "loss": 1.0227,
+      "mean_token_accuracy": 0.6901260018348694,
+      "step": 19
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 2.036501884460449,
+      "learning_rate": 9.995584768975735e-06,
+      "loss": 1.0818,
+      "mean_token_accuracy": 0.6697351932525635,
+      "step": 20
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.8429316282272339,
+      "learning_rate": 9.993101772727602e-06,
+      "loss": 1.081,
+      "mean_token_accuracy": 0.6770170331001282,
+      "step": 21
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 1.9818006753921509,
+      "learning_rate": 9.990067557971068e-06,
+      "loss": 1.0054,
+      "mean_token_accuracy": 0.6853318810462952,
+      "step": 22
+    },
+    {
+      "epoch": 0.36507936507936506,
+      "grad_norm": 1.9771008491516113,
+      "learning_rate": 9.986482459671332e-06,
+      "loss": 0.9637,
+      "mean_token_accuracy": 0.6931653618812561,
+      "step": 23
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.9616119861602783,
+      "learning_rate": 9.982346873608936e-06,
+      "loss": 1.0484,
+      "mean_token_accuracy": 0.6677199006080627,
+      "step": 24
+    },
+    {
+      "epoch": 0.3968253968253968,
+      "grad_norm": 1.6112979650497437,
+      "learning_rate": 9.977661256336081e-06,
+      "loss": 0.9638,
+      "mean_token_accuracy": 0.6957253813743591,
+      "step": 25
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 1.9327082633972168,
+      "learning_rate": 9.972426125126208e-06,
+      "loss": 0.9339,
+      "mean_token_accuracy": 0.702426016330719,
+      "step": 26
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 1.7104556560516357,
+      "learning_rate": 9.966642057916915e-06,
+      "loss": 1.0022,
+      "mean_token_accuracy": 0.6801244616508484,
+      "step": 27
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.5087337493896484,
+      "learning_rate": 9.960309693246135e-06,
+      "loss": 0.9673,
+      "mean_token_accuracy": 0.7036176323890686,
+      "step": 28
+    },
+    {
+      "epoch": 0.4603174603174603,
+      "grad_norm": 1.4818483591079712,
+      "learning_rate": 9.953429730181653e-06,
+      "loss": 1.0496,
+      "mean_token_accuracy": 0.6714926958084106,
+      "step": 29
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.4883416891098022,
+      "learning_rate": 9.94600292824394e-06,
+      "loss": 1.0853,
+      "mean_token_accuracy": 0.6756605505943298,
+      "step": 30
+    },
+    {
+      "epoch": 0.49206349206349204,
+      "grad_norm": 1.6064577102661133,
+      "learning_rate": 9.938030107322284e-06,
+      "loss": 1.0108,
+      "mean_token_accuracy": 0.6843318939208984,
+      "step": 31
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 1.2882405519485474,
+      "learning_rate": 9.929512147584297e-06,
+      "loss": 1.0017,
+      "mean_token_accuracy": 0.6932390928268433,
+      "step": 32
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 1.462615966796875,
+      "learning_rate": 9.920449989378741e-06,
+      "loss": 1.0853,
+      "mean_token_accuracy": 0.6662924289703369,
+      "step": 33
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 1.3395570516586304,
+      "learning_rate": 9.910844633131712e-06,
+      "loss": 0.991,
+      "mean_token_accuracy": 0.6973869800567627,
+      "step": 34
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 1.4672247171401978,
+      "learning_rate": 9.90069713923621e-06,
+      "loss": 0.9711,
+      "mean_token_accuracy": 0.6921698451042175,
+      "step": 35
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.459593415260315,
+      "learning_rate": 9.890008627935057e-06,
+      "loss": 0.9867,
+      "mean_token_accuracy": 0.6826137900352478,
+      "step": 36
+    },
+    {
+      "epoch": 0.5873015873015873,
+      "grad_norm": 1.4538332223892212,
+      "learning_rate": 9.878780279197246e-06,
+      "loss": 0.9639,
+      "mean_token_accuracy": 0.6869688630104065,
+      "step": 37
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 1.4662752151489258,
+      "learning_rate": 9.867013332587667e-06,
+      "loss": 0.9144,
+      "mean_token_accuracy": 0.7195159196853638,
+      "step": 38
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 1.5825181007385254,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.9851,
+      "mean_token_accuracy": 0.697943389415741,
+      "step": 39
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 1.6793732643127441,
+      "learning_rate": 9.841868901164621e-06,
+      "loss": 1.0489,
+      "mean_token_accuracy": 0.6596137285232544,
+      "step": 40
+    },
+    {
+      "epoch": 0.6507936507936508,
+      "grad_norm": 1.4431298971176147,
+      "learning_rate": 9.828494192196037e-06,
+      "loss": 0.9437,
+      "mean_token_accuracy": 0.6924724578857422,
+      "step": 41
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.5359476804733276,
+      "learning_rate": 9.814586436738998e-06,
+      "loss": 0.9627,
+      "mean_token_accuracy": 0.6844196319580078,
+      "step": 42
+    },
+    {
+      "epoch": 0.6825396825396826,
+      "grad_norm": 1.5142978429794312,
+      "learning_rate": 9.8001471701542e-06,
+      "loss": 0.9122,
+      "mean_token_accuracy": 0.7117491364479065,
+      "step": 43
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 1.6079134941101074,
+      "learning_rate": 9.785177986479049e-06,
+      "loss": 0.9616,
+      "mean_token_accuracy": 0.6850039958953857,
+      "step": 44
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.4364824295043945,
+      "learning_rate": 9.76968053825168e-06,
+      "loss": 0.9412,
+      "mean_token_accuracy": 0.6876325607299805,
+      "step": 45
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 1.6108063459396362,
+      "learning_rate": 9.753656536328529e-06,
+      "loss": 0.8542,
+      "mean_token_accuracy": 0.7127025723457336,
+      "step": 46
+    },
+    {
+      "epoch": 0.746031746031746,
+      "grad_norm": 1.4979714155197144,
+      "learning_rate": 9.737107749695456e-06,
+      "loss": 1.0857,
+      "mean_token_accuracy": 0.6746847033500671,
+      "step": 47
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.492646336555481,
+      "learning_rate": 9.72003600527246e-06,
+      "loss": 0.9565,
+      "mean_token_accuracy": 0.678888738155365,
+      "step": 48
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 1.5077250003814697,
+      "learning_rate": 9.702443187711991e-06,
+      "loss": 0.856,
+      "mean_token_accuracy": 0.7180086374282837,
+      "step": 49
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 1.5432298183441162,
+      "learning_rate": 9.6843312391909e-06,
+      "loss": 0.9436,
+      "mean_token_accuracy": 0.7022880911827087,
+      "step": 50
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 1.5827702283859253,
+      "learning_rate": 9.665702159196014e-06,
+      "loss": 0.9587,
+      "mean_token_accuracy": 0.6920652389526367,
+      "step": 51
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 1.5026133060455322,
+      "learning_rate": 9.646558004303419e-06,
+      "loss": 1.0145,
+      "mean_token_accuracy": 0.6848466396331787,
+      "step": 52
+    },
+    {
+      "epoch": 0.8412698412698413,
+      "grad_norm": 1.6121655702590942,
+      "learning_rate": 9.62690088795141e-06,
+      "loss": 0.9505,
+      "mean_token_accuracy": 0.6841768026351929,
+      "step": 53
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.4861469268798828,
+      "learning_rate": 9.606732980207186e-06,
+      "loss": 0.9782,
+      "mean_token_accuracy": 0.6907793879508972,
+      "step": 54
+    },
+    {
+      "epoch": 0.873015873015873,
+      "grad_norm": 1.3851877450942993,
+      "learning_rate": 9.586056507527266e-06,
+      "loss": 1.012,
+      "mean_token_accuracy": 0.6789924502372742,
+      "step": 55
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.5138801336288452,
+      "learning_rate": 9.564873752511719e-06,
+      "loss": 0.9156,
+      "mean_token_accuracy": 0.7050096988677979,
+      "step": 56
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 1.4586461782455444,
+      "learning_rate": 9.543187053652156e-06,
+      "loss": 0.8683,
+      "mean_token_accuracy": 0.7179403305053711,
+      "step": 57
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 1.3151836395263672,
+      "learning_rate": 9.520998805073583e-06,
+      "loss": 0.9126,
+      "mean_token_accuracy": 0.7062746286392212,
+      "step": 58
+    },
+    {
+      "epoch": 0.9365079365079365,
+      "grad_norm": 1.466514229774475,
+      "learning_rate": 9.498311456270091e-06,
+      "loss": 0.9754,
+      "mean_token_accuracy": 0.6828599572181702,
+      "step": 59
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.4227975606918335,
+      "learning_rate": 9.475127511834438e-06,
+      "loss": 0.9465,
+      "mean_token_accuracy": 0.7063090801239014,
+      "step": 60
+    },
+    {
+      "epoch": 0.9682539682539683,
+      "grad_norm": 1.4949185848236084,
+      "learning_rate": 9.451449531181571e-06,
+      "loss": 0.9415,
+      "mean_token_accuracy": 0.6885518431663513,
+      "step": 61
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 1.498402714729309,
+      "learning_rate": 9.427280128266049e-06,
+      "loss": 0.8661,
+      "mean_token_accuracy": 0.715215802192688,
+      "step": 62
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3733229637145996,
+      "learning_rate": 9.4026219712935e-06,
+      "loss": 0.9046,
+      "mean_token_accuracy": 0.6959970593452454,
+      "step": 63
+    },
+    {
+      "epoch": 1.0158730158730158,
+      "grad_norm": 1.6193804740905762,
+      "learning_rate": 9.377477782426041e-06,
+      "loss": 0.789,
+      "mean_token_accuracy": 0.7177256345748901,
+      "step": 64
+    },
+    {
+      "epoch": 1.0317460317460316,
+      "grad_norm": 1.4630059003829956,
+      "learning_rate": 9.351850337481774e-06,
+      "loss": 0.7264,
+      "mean_token_accuracy": 0.7328070402145386,
+      "step": 65
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 1.2606074810028076,
+      "learning_rate": 9.325742465628342e-06,
+      "loss": 0.7628,
+      "mean_token_accuracy": 0.7213523387908936,
+      "step": 66
+    },
+    {
+      "epoch": 1.0634920634920635,
+      "grad_norm": 1.392194151878357,
+      "learning_rate": 9.299157049070604e-06,
+      "loss": 0.7474,
+      "mean_token_accuracy": 0.7312816977500916,
+      "step": 67
+    },
+    {
+      "epoch": 1.0793650793650793,
+      "grad_norm": 1.448189616203308,
+      "learning_rate": 9.272097022732444e-06,
+      "loss": 0.6216,
+      "mean_token_accuracy": 0.7725050449371338,
+      "step": 68
+    },
+    {
+      "epoch": 1.0952380952380953,
+      "grad_norm": 1.363480567932129,
+      "learning_rate": 9.244565373932775e-06,
+      "loss": 0.6251,
+      "mean_token_accuracy": 0.7715384364128113,
+      "step": 69
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.3022717237472534,
+      "learning_rate": 9.216565142055745e-06,
+      "loss": 0.8162,
+      "mean_token_accuracy": 0.739141583442688,
+      "step": 70
+    },
+    {
+      "epoch": 1.126984126984127,
+      "grad_norm": 1.2808637619018555,
+      "learning_rate": 9.188099418215208e-06,
+      "loss": 0.7196,
+      "mean_token_accuracy": 0.7466751337051392,
+      "step": 71
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.3880754709243774,
+      "learning_rate": 9.159171344913469e-06,
+      "loss": 0.7558,
+      "mean_token_accuracy": 0.7294354438781738,
+      "step": 72
+    },
+    {
+      "epoch": 1.1587301587301586,
+      "grad_norm": 1.4471501111984253,
+      "learning_rate": 9.129784115694368e-06,
+      "loss": 0.634,
+      "mean_token_accuracy": 0.7721849679946899,
+      "step": 73
+    },
+    {
+      "epoch": 1.1746031746031746,
+      "grad_norm": 1.5563479661941528,
+      "learning_rate": 9.09994097479073e-06,
+      "loss": 0.7126,
+      "mean_token_accuracy": 0.7434053421020508,
+      "step": 74
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 1.3956546783447266,
+      "learning_rate": 9.069645216766207e-06,
+      "loss": 0.7222,
+      "mean_token_accuracy": 0.7285550236701965,
+      "step": 75
+    },
+    {
+      "epoch": 1.2063492063492063,
+      "grad_norm": 1.2886793613433838,
+      "learning_rate": 9.038900186151574e-06,
+      "loss": 0.6632,
+      "mean_token_accuracy": 0.7603873014450073,
+      "step": 76
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 1.3814256191253662,
+      "learning_rate": 9.007709277075512e-06,
+      "loss": 0.7433,
+      "mean_token_accuracy": 0.738385021686554,
+      "step": 77
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 1.2273836135864258,
+      "learning_rate": 8.976075932889896e-06,
+      "loss": 0.7643,
+      "mean_token_accuracy": 0.7412843704223633,
+      "step": 78
+    },
+    {
+      "epoch": 1.253968253968254,
+      "grad_norm": 1.3541786670684814,
+      "learning_rate": 8.944003645789678e-06,
+      "loss": 0.702,
+      "mean_token_accuracy": 0.7366657257080078,
+      "step": 79
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 1.5467926263809204,
+      "learning_rate": 8.911495956427358e-06,
+      "loss": 0.6916,
+      "mean_token_accuracy": 0.740810215473175,
+      "step": 80
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 1.2560186386108398,
+      "learning_rate": 8.8785564535221e-06,
+      "loss": 0.6826,
+      "mean_token_accuracy": 0.7509929537773132,
+      "step": 81
+    },
+    {
+      "epoch": 1.3015873015873016,
+      "grad_norm": 1.2027472257614136,
+      "learning_rate": 8.845188773463567e-06,
+      "loss": 0.7904,
+      "mean_token_accuracy": 0.7260932326316833,
+      "step": 82
+    },
+    {
+      "epoch": 1.3174603174603174,
+      "grad_norm": 1.4221609830856323,
+      "learning_rate": 8.811396599910467e-06,
+      "loss": 0.7492,
+      "mean_token_accuracy": 0.7119400501251221,
+      "step": 83
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.3599181175231934,
+      "learning_rate": 8.777183663383897e-06,
+      "loss": 0.7523,
+      "mean_token_accuracy": 0.7216988801956177,
+      "step": 84
+    },
+    {
+      "epoch": 1.3492063492063493,
+      "grad_norm": 1.3047292232513428,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.7349,
+      "mean_token_accuracy": 0.7551175951957703,
+      "step": 85
+    },
+    {
+      "epoch": 1.3650793650793651,
+      "grad_norm": 1.4084362983703613,
+      "learning_rate": 8.707510655330536e-06,
+      "loss": 0.6225,
+      "mean_token_accuracy": 0.7565320134162903,
+      "step": 86
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 1.5446528196334839,
+      "learning_rate": 8.672058275425773e-06,
+      "loss": 0.7056,
+      "mean_token_accuracy": 0.7259581089019775,
+      "step": 87
+    },
+    {
+      "epoch": 1.3968253968253967,
+      "grad_norm": 1.1988624334335327,
+      "learning_rate": 8.636200514942466e-06,
+      "loss": 0.6895,
+      "mean_token_accuracy": 0.7405627965927124,
+      "step": 88
+    },
+    {
+      "epoch": 1.4126984126984126,
+      "grad_norm": 1.3339022397994995,
+      "learning_rate": 8.59994133243427e-06,
+      "loss": 0.6864,
+      "mean_token_accuracy": 0.752083420753479,
+      "step": 89
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.3587596416473389,
+      "learning_rate": 8.563284730770222e-06,
+      "loss": 0.6124,
+      "mean_token_accuracy": 0.7803294658660889,
+      "step": 90
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 1.2187806367874146,
+      "learning_rate": 8.52623475669285e-06,
+      "loss": 0.7382,
+      "mean_token_accuracy": 0.7305276393890381,
+      "step": 91
+    },
+    {
+      "epoch": 1.4603174603174602,
+      "grad_norm": 1.2334811687469482,
+      "learning_rate": 8.488795500371427e-06,
+      "loss": 0.7677,
+      "mean_token_accuracy": 0.7154316306114197,
+      "step": 92
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 1.3801590204238892,
+      "learning_rate": 8.450971094950433e-06,
+      "loss": 0.6484,
+      "mean_token_accuracy": 0.7606028318405151,
+      "step": 93
+    },
+    {
+      "epoch": 1.492063492063492,
+      "grad_norm": 1.3321889638900757,
+      "learning_rate": 8.412765716093273e-06,
+      "loss": 0.6363,
+      "mean_token_accuracy": 0.7536671161651611,
+      "step": 94
+    },
+    {
+      "epoch": 1.507936507936508,
+      "grad_norm": 1.2593462467193604,
+      "learning_rate": 8.374183581521288e-06,
+      "loss": 0.7035,
+      "mean_token_accuracy": 0.7448620200157166,
+      "step": 95
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 1.2974730730056763,
+      "learning_rate": 8.335228950548164e-06,
+      "loss": 0.7209,
+      "mean_token_accuracy": 0.7377753853797913,
+      "step": 96
+    },
+    {
+      "epoch": 1.5396825396825395,
+      "grad_norm": 1.3005163669586182,
+      "learning_rate": 8.29590612360969e-06,
+      "loss": 0.7118,
+      "mean_token_accuracy": 0.7413659691810608,
+      "step": 97
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 1.2531510591506958,
+      "learning_rate": 8.256219441789023e-06,
+      "loss": 0.6691,
+      "mean_token_accuracy": 0.7775458097457886,
+      "step": 98
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 1.2969629764556885,
+      "learning_rate": 8.216173286337449e-06,
+      "loss": 0.7427,
+      "mean_token_accuracy": 0.7308691740036011,
+      "step": 99
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 1.2509957551956177,
+      "learning_rate": 8.175772078190706e-06,
+      "loss": 0.614,
+      "mean_token_accuracy": 0.7691511511802673,
+      "step": 100
+    },
+    {
+      "epoch": 1.6031746031746033,
+      "grad_norm": 1.285543441772461,
+      "learning_rate": 8.135020277480933e-06,
+      "loss": 0.6741,
+      "mean_token_accuracy": 0.7384034395217896,
+      "step": 101
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 1.4988497495651245,
+      "learning_rate": 8.093922383044293e-06,
+      "loss": 0.7753,
+      "mean_token_accuracy": 0.729863703250885,
+      "step": 102
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "grad_norm": 1.2798858880996704,
+      "learning_rate": 8.052482931924307e-06,
+      "loss": 0.7676,
+      "mean_token_accuracy": 0.7343738675117493,
+      "step": 103
+    },
+    {
+      "epoch": 1.6507936507936507,
+      "grad_norm": 1.3362586498260498,
+      "learning_rate": 8.010706498870997e-06,
+      "loss": 0.6517,
+      "mean_token_accuracy": 0.762486457824707,
+      "step": 104
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.354143738746643,
+      "learning_rate": 7.968597695835845e-06,
+      "loss": 0.6297,
+      "mean_token_accuracy": 0.7620171308517456,
+      "step": 105
+    },
+    {
+      "epoch": 1.6825396825396826,
+      "grad_norm": 1.2046130895614624,
+      "learning_rate": 7.926161171462647e-06,
+      "loss": 0.6443,
+      "mean_token_accuracy": 0.7690253257751465,
+      "step": 106
+    },
+    {
+      "epoch": 1.6984126984126984,
+      "grad_norm": 1.241445541381836,
+      "learning_rate": 7.883401610574338e-06,
+      "loss": 0.6668,
+      "mean_token_accuracy": 0.7507138252258301,
+      "step": 107
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 1.3440011739730835,
+      "learning_rate": 7.84032373365578e-06,
+      "loss": 0.6325,
+      "mean_token_accuracy": 0.7514282464981079,
+      "step": 108
+    },
+    {
+      "epoch": 1.7301587301587302,
+      "grad_norm": 1.4172037839889526,
+      "learning_rate": 7.796932296332666e-06,
+      "loss": 0.6898,
+      "mean_token_accuracy": 0.7555402517318726,
+      "step": 109
+    },
+    {
+      "epoch": 1.746031746031746,
+      "grad_norm": 1.1736810207366943,
+      "learning_rate": 7.753232088846505e-06,
+      "loss": 0.778,
+      "mean_token_accuracy": 0.737077534198761,
+      "step": 110
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 1.1764577627182007,
+      "learning_rate": 7.709227935525796e-06,
+      "loss": 0.724,
+      "mean_token_accuracy": 0.734950065612793,
+      "step": 111
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 1.228583574295044,
+      "learning_rate": 7.664924694253444e-06,
+      "loss": 0.7141,
+      "mean_token_accuracy": 0.7455480098724365,
+      "step": 112
+    },
+    {
+      "epoch": 1.7936507936507935,
+      "grad_norm": 1.3196018934249878,
+      "learning_rate": 7.620327255930475e-06,
+      "loss": 0.7775,
+      "mean_token_accuracy": 0.7201443910598755,
+      "step": 113
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 1.3832653760910034,
+      "learning_rate": 7.575440543936092e-06,
+      "loss": 0.7439,
+      "mean_token_accuracy": 0.7421494126319885,
+      "step": 114
+    },
+    {
+      "epoch": 1.8253968253968254,
+      "grad_norm": 1.3130351305007935,
+      "learning_rate": 7.530269513584158e-06,
+      "loss": 0.5983,
+      "mean_token_accuracy": 0.7735153436660767,
+      "step": 115
+    },
+    {
+      "epoch": 1.8412698412698414,
+      "grad_norm": 1.2631326913833618,
+      "learning_rate": 7.484819151576148e-06,
+      "loss": 0.8277,
+      "mean_token_accuracy": 0.7191202640533447,
+      "step": 116
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 1.2389181852340698,
+      "learning_rate": 7.439094475450638e-06,
+      "loss": 0.75,
+      "mean_token_accuracy": 0.7433958649635315,
+      "step": 117
+    },
+    {
+      "epoch": 1.873015873015873,
+      "grad_norm": 1.1765884160995483,
+      "learning_rate": 7.393100533029383e-06,
+      "loss": 0.7157,
+      "mean_token_accuracy": 0.757839024066925,
+      "step": 118
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 1.1635072231292725,
+      "learning_rate": 7.346842401860069e-06,
+      "loss": 0.7568,
+      "mean_token_accuracy": 0.7247301340103149,
+      "step": 119
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 1.2166038751602173,
+      "learning_rate": 7.300325188655762e-06,
+      "loss": 0.7275,
+      "mean_token_accuracy": 0.7342228889465332,
+      "step": 120
+    },
+    {
+      "epoch": 1.9206349206349205,
+      "grad_norm": 1.2700014114379883,
+      "learning_rate": 7.253554028731149e-06,
+      "loss": 0.7394,
+      "mean_token_accuracy": 0.7326907515525818,
+      "step": 121
+    },
+    {
+      "epoch": 1.9365079365079365,
+      "grad_norm": 1.2303329706192017,
+      "learning_rate": 7.206534085435626e-06,
+      "loss": 0.6532,
+      "mean_token_accuracy": 0.7559145092964172,
+      "step": 122
+    },
+    {
+      "epoch": 1.9523809523809523,
+      "grad_norm": 1.426224946975708,
+      "learning_rate": 7.159270549583278e-06,
+      "loss": 0.6547,
+      "mean_token_accuracy": 0.7708938121795654,
+      "step": 123
+    },
+    {
+      "epoch": 1.9682539682539684,
+      "grad_norm": 1.2642630338668823,
+      "learning_rate": 7.111768638879834e-06,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.7534304261207581,
+      "step": 124
+    },
+    {
+      "epoch": 1.9841269841269842,
+      "grad_norm": 1.2871243953704834,
+      "learning_rate": 7.064033597346658e-06,
+      "loss": 0.6769,
+      "mean_token_accuracy": 0.7718325257301331,
+      "step": 125
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1990370750427246,
+      "learning_rate": 7.016070694741824e-06,
+      "loss": 0.6836,
+      "mean_token_accuracy": 0.7100950479507446,
+      "step": 126
+    },
+    {
+      "epoch": 2.015873015873016,
+      "grad_norm": 1.434239387512207,
+      "learning_rate": 6.967885225978366e-06,
+      "loss": 0.5373,
+      "mean_token_accuracy": 0.80208820104599,
+      "step": 127
+    },
+    {
+      "epoch": 2.0317460317460316,
+      "grad_norm": 1.1308351755142212,
+      "learning_rate": 6.919482510539723e-06,
+      "loss": 0.5622,
+      "mean_token_accuracy": 0.7496302723884583,
+      "step": 128
+    },
+    {
+      "epoch": 2.0476190476190474,
+      "grad_norm": 1.0369759798049927,
+      "learning_rate": 6.870867891892511e-06,
+      "loss": 0.5444,
+      "mean_token_accuracy": 0.7851538062095642,
+      "step": 129
+    },
+    {
+      "epoch": 2.0634920634920633,
+      "grad_norm": 1.218014121055603,
+      "learning_rate": 6.822046736896607e-06,
+      "loss": 0.5651,
+      "mean_token_accuracy": 0.7711318135261536,
+      "step": 130
+    },
+    {
+      "epoch": 2.0793650793650795,
+      "grad_norm": 1.5595968961715698,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.4641,
+      "mean_token_accuracy": 0.8099368810653687,
+      "step": 131
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 1.4578797817230225,
+      "learning_rate": 6.723806398707186e-06,
+      "loss": 0.3923,
+      "mean_token_accuracy": 0.8459458351135254,
+      "step": 132
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 1.259845495223999,
+      "learning_rate": 6.674398060854931e-06,
+      "loss": 0.5929,
+      "mean_token_accuracy": 0.7611780762672424,
+      "step": 133
+    },
+    {
+      "epoch": 2.126984126984127,
+      "grad_norm": 1.182294249534607,
+      "learning_rate": 6.624804876139227e-06,
+      "loss": 0.5286,
+      "mean_token_accuracy": 0.7840155959129333,
+      "step": 134
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 1.1326159238815308,
+      "learning_rate": 6.57503231944974e-06,
+      "loss": 0.4789,
+      "mean_token_accuracy": 0.8139358758926392,
+      "step": 135
+    },
+    {
+      "epoch": 2.1587301587301586,
+      "grad_norm": 1.1104531288146973,
+      "learning_rate": 6.525085885478088e-06,
+      "loss": 0.4598,
+      "mean_token_accuracy": 0.8077739477157593,
+      "step": 136
+    },
+    {
+      "epoch": 2.1746031746031744,
+      "grad_norm": 1.4372111558914185,
+      "learning_rate": 6.4749710881112485e-06,
+      "loss": 0.4121,
+      "mean_token_accuracy": 0.8421859741210938,
+      "step": 137
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 1.2716678380966187,
+      "learning_rate": 6.424693459822843e-06,
+      "loss": 0.4572,
+      "mean_token_accuracy": 0.8043623566627502,
+      "step": 138
+    },
+    {
+      "epoch": 2.2063492063492065,
+      "grad_norm": 1.077424168586731,
+      "learning_rate": 6.374258551062377e-06,
+      "loss": 0.4492,
+      "mean_token_accuracy": 0.8146030306816101,
+      "step": 139
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 1.1364110708236694,
+      "learning_rate": 6.3236719296424985e-06,
+      "loss": 0.5233,
+      "mean_token_accuracy": 0.7739091515541077,
+      "step": 140
+    },
+    {
+      "epoch": 2.238095238095238,
+      "grad_norm": 1.0795546770095825,
+      "learning_rate": 6.272939180124316e-06,
+      "loss": 0.39,
+      "mean_token_accuracy": 0.8451641201972961,
+      "step": 141
+    },
+    {
+      "epoch": 2.253968253968254,
+      "grad_norm": 1.2171779870986938,
+      "learning_rate": 6.222065903200909e-06,
+      "loss": 0.5816,
+      "mean_token_accuracy": 0.7803935408592224,
+      "step": 142
+    },
+    {
+      "epoch": 2.2698412698412698,
+      "grad_norm": 1.146126627922058,
+      "learning_rate": 6.171057715079012e-06,
+      "loss": 0.4214,
+      "mean_token_accuracy": 0.7971423864364624,
+      "step": 143
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 1.1783219575881958,
+      "learning_rate": 6.119920246859025e-06,
+      "loss": 0.5536,
+      "mean_token_accuracy": 0.7960186004638672,
+      "step": 144
+    },
+    {
+      "epoch": 2.3015873015873014,
+      "grad_norm": 1.18180513381958,
+      "learning_rate": 6.068659143913349e-06,
+      "loss": 0.4735,
+      "mean_token_accuracy": 0.8162056803703308,
+      "step": 145
+    },
+    {
+      "epoch": 2.317460317460317,
+      "grad_norm": 1.0765876770019531,
+      "learning_rate": 6.0172800652631706e-06,
+      "loss": 0.4516,
+      "mean_token_accuracy": 0.8035807609558105,
+      "step": 146
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 1.2142268419265747,
+      "learning_rate": 5.965788682953717e-06,
+      "loss": 0.4891,
+      "mean_token_accuracy": 0.8061010241508484,
+      "step": 147
+    },
+    {
+      "epoch": 2.3492063492063493,
+      "grad_norm": 1.0830104351043701,
+      "learning_rate": 5.914190681428098e-06,
+      "loss": 0.5592,
+      "mean_token_accuracy": 0.7947844862937927,
+      "step": 148
+    },
+    {
+      "epoch": 2.365079365079365,
+      "grad_norm": 1.1901891231536865,
+      "learning_rate": 5.862491756899753e-06,
+      "loss": 0.4102,
+      "mean_token_accuracy": 0.8136416077613831,
+      "step": 149
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 1.2062454223632812,
+      "learning_rate": 5.8106976167236236e-06,
+      "loss": 0.3502,
+      "mean_token_accuracy": 0.857958197593689,
+      "step": 150
+    },
+    {
+      "epoch": 2.3968253968253967,
+      "grad_norm": 1.0489780902862549,
+      "learning_rate": 5.758813978766077e-06,
+      "loss": 0.4885,
+      "mean_token_accuracy": 0.7897634506225586,
+      "step": 151
+    },
+    {
+      "epoch": 2.4126984126984126,
+      "grad_norm": 1.1065855026245117,
+      "learning_rate": 5.706846570773677e-06,
+      "loss": 0.5357,
+      "mean_token_accuracy": 0.7911423444747925,
+      "step": 152
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 1.1048340797424316,
+      "learning_rate": 5.654801129740863e-06,
+      "loss": 0.5444,
+      "mean_token_accuracy": 0.7757133841514587,
+      "step": 153
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 1.065033197402954,
+      "learning_rate": 5.6026834012766155e-06,
+      "loss": 0.4551,
+      "mean_token_accuracy": 0.8179129362106323,
+      "step": 154
+    },
+    {
+      "epoch": 2.4603174603174605,
+      "grad_norm": 1.134699821472168,
+      "learning_rate": 5.550499138970158e-06,
+      "loss": 0.3377,
+      "mean_token_accuracy": 0.87542325258255,
+      "step": 155
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 1.147384524345398,
+      "learning_rate": 5.4982541037557825e-06,
+      "loss": 0.4467,
+      "mean_token_accuracy": 0.825996994972229,
+      "step": 156
+    },
+    {
+      "epoch": 2.492063492063492,
+      "grad_norm": 1.2173268795013428,
+      "learning_rate": 5.44595406327687e-06,
+      "loss": 0.5541,
+      "mean_token_accuracy": 0.7744438648223877,
+      "step": 157
+    },
+    {
+      "epoch": 2.507936507936508,
+      "grad_norm": 1.0811070203781128,
+      "learning_rate": 5.393604791249158e-06,
+      "loss": 0.3923,
+      "mean_token_accuracy": 0.8318279981613159,
+      "step": 158
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "grad_norm": 1.0606483221054077,
+      "learning_rate": 5.341212066823356e-06,
+      "loss": 0.3868,
+      "mean_token_accuracy": 0.8136443495750427,
+      "step": 159
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "grad_norm": 1.167754888534546,
+      "learning_rate": 5.288781673947143e-06,
+      "loss": 0.4686,
+      "mean_token_accuracy": 0.7608866095542908,
+      "step": 160
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 1.2630232572555542,
+      "learning_rate": 5.2363194007266435e-06,
+      "loss": 0.4706,
+      "mean_token_accuracy": 0.8080599308013916,
+      "step": 161
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.0766682624816895,
+      "learning_rate": 5.183831038787449e-06,
+      "loss": 0.541,
+      "mean_token_accuracy": 0.7889450788497925,
+      "step": 162
+    },
+    {
+      "epoch": 2.5873015873015874,
+      "grad_norm": 1.18930983543396,
+      "learning_rate": 5.131322382635236e-06,
+      "loss": 0.4729,
+      "mean_token_accuracy": 0.807502031326294,
+      "step": 163
+    },
+    {
+      "epoch": 2.6031746031746033,
+      "grad_norm": 1.173232078552246,
+      "learning_rate": 5.078799229016083e-06,
+      "loss": 0.4129,
+      "mean_token_accuracy": 0.8101903796195984,
+      "step": 164
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 1.0739233493804932,
+      "learning_rate": 5.0262673762765316e-06,
+      "loss": 0.4577,
+      "mean_token_accuracy": 0.8131040930747986,
+      "step": 165
+    },
+    {
+      "epoch": 2.634920634920635,
+      "grad_norm": 1.0806288719177246,
+      "learning_rate": 4.973732623723471e-06,
+      "loss": 0.5123,
+      "mean_token_accuracy": 0.7756950855255127,
+      "step": 166
+    },
+    {
+      "epoch": 2.6507936507936507,
+      "grad_norm": 1.1319019794464111,
+      "learning_rate": 4.921200770983919e-06,
+      "loss": 0.5075,
+      "mean_token_accuracy": 0.7682743668556213,
+      "step": 167
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.1852954626083374,
+      "learning_rate": 4.8686776173647655e-06,
+      "loss": 0.4145,
+      "mean_token_accuracy": 0.820248544216156,
+      "step": 168
+    },
+    {
+      "epoch": 2.682539682539683,
+      "grad_norm": 1.108176589012146,
+      "learning_rate": 4.816168961212553e-06,
+      "loss": 0.4966,
+      "mean_token_accuracy": 0.7906358242034912,
+      "step": 169
+    },
+    {
+      "epoch": 2.6984126984126986,
+      "grad_norm": 1.1852736473083496,
+      "learning_rate": 4.763680599273357e-06,
+      "loss": 0.5509,
+      "mean_token_accuracy": 0.7873461842536926,
+      "step": 170
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 1.0883158445358276,
+      "learning_rate": 4.711218326052859e-06,
+      "loss": 0.3889,
+      "mean_token_accuracy": 0.8340739011764526,
+      "step": 171
+    },
+    {
+      "epoch": 2.7301587301587302,
+      "grad_norm": 1.0482765436172485,
+      "learning_rate": 4.6587879331766465e-06,
+      "loss": 0.5589,
+      "mean_token_accuracy": 0.7785695195198059,
+      "step": 172
+    },
+    {
+      "epoch": 2.746031746031746,
+      "grad_norm": 1.1065349578857422,
+      "learning_rate": 4.606395208750844e-06,
+      "loss": 0.4934,
+      "mean_token_accuracy": 0.8306599855422974,
+      "step": 173
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 1.0907114744186401,
+      "learning_rate": 4.554045936723132e-06,
+      "loss": 0.4629,
+      "mean_token_accuracy": 0.8285999298095703,
+      "step": 174
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 1.130142092704773,
+      "learning_rate": 4.501745896244219e-06,
+      "loss": 0.6057,
+      "mean_token_accuracy": 0.7609834671020508,
+      "step": 175
+    },
+    {
+      "epoch": 2.7936507936507935,
+      "grad_norm": 1.2471946477890015,
+      "learning_rate": 4.4495008610298435e-06,
+      "loss": 0.3814,
+      "mean_token_accuracy": 0.8319938778877258,
+      "step": 176
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "grad_norm": 1.151918649673462,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.4777,
+      "mean_token_accuracy": 0.8117051124572754,
+      "step": 177
+    },
+    {
+      "epoch": 2.825396825396825,
+      "grad_norm": 1.0310879945755005,
+      "learning_rate": 4.345198870259139e-06,
+      "loss": 0.5337,
+      "mean_token_accuracy": 0.7743932604789734,
+      "step": 178
+    },
+    {
+      "epoch": 2.8412698412698414,
+      "grad_norm": 1.0700514316558838,
+      "learning_rate": 4.2931534292263265e-06,
+      "loss": 0.4176,
+      "mean_token_accuracy": 0.808311402797699,
+      "step": 179
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.2629222869873047,
+      "learning_rate": 4.241186021233925e-06,
+      "loss": 0.4556,
+      "mean_token_accuracy": 0.81524258852005,
+      "step": 180
+    },
+    {
+      "epoch": 2.873015873015873,
+      "grad_norm": 1.1769040822982788,
+      "learning_rate": 4.189302383276378e-06,
+      "loss": 0.4642,
+      "mean_token_accuracy": 0.8150965571403503,
+      "step": 181
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 1.0976675748825073,
+      "learning_rate": 4.137508243100249e-06,
+      "loss": 0.4879,
+      "mean_token_accuracy": 0.7843369841575623,
+      "step": 182
+    },
+    {
+      "epoch": 2.9047619047619047,
+      "grad_norm": 1.0868701934814453,
+      "learning_rate": 4.085809318571905e-06,
+      "loss": 0.4594,
+      "mean_token_accuracy": 0.7947729229927063,
+      "step": 183
+    },
+    {
+      "epoch": 2.9206349206349205,
+      "grad_norm": 1.0909900665283203,
+      "learning_rate": 4.034211317046285e-06,
+      "loss": 0.4022,
+      "mean_token_accuracy": 0.8373859524726868,
+      "step": 184
+    },
+    {
+      "epoch": 2.9365079365079367,
+      "grad_norm": 1.2175990343093872,
+      "learning_rate": 3.982719934736832e-06,
+      "loss": 0.454,
+      "mean_token_accuracy": 0.8179551959037781,
+      "step": 185
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 1.1618547439575195,
+      "learning_rate": 3.931340856086652e-06,
+      "loss": 0.5671,
+      "mean_token_accuracy": 0.7677510380744934,
+      "step": 186
+    },
+    {
+      "epoch": 2.9682539682539684,
+      "grad_norm": 1.2595247030258179,
+      "learning_rate": 3.880079753140978e-06,
+      "loss": 0.3102,
+      "mean_token_accuracy": 0.8672084808349609,
+      "step": 187
+    },
+    {
+      "epoch": 2.984126984126984,
+      "grad_norm": 1.1393849849700928,
+      "learning_rate": 3.82894228492099e-06,
+      "loss": 0.4904,
+      "mean_token_accuracy": 0.7898647785186768,
+      "step": 188
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9801763296127319,
+      "learning_rate": 3.777934096799094e-06,
+      "loss": 0.3096,
+      "mean_token_accuracy": 0.8739486932754517,
+      "step": 189
+    },
+    {
+      "epoch": 3.015873015873016,
+      "grad_norm": 1.1817115545272827,
+      "learning_rate": 3.7270608198756852e-06,
+      "loss": 0.2919,
+      "mean_token_accuracy": 0.8657442331314087,
+      "step": 190
+    },
+    {
+      "epoch": 3.0317460317460316,
+      "grad_norm": 0.9881290197372437,
+      "learning_rate": 3.676328070357503e-06,
+      "loss": 0.2769,
+      "mean_token_accuracy": 0.8417280316352844,
+      "step": 191
+    },
+    {
+      "epoch": 3.0476190476190474,
+      "grad_norm": 0.9517524242401123,
+      "learning_rate": 3.6257414489376217e-06,
+      "loss": 0.3832,
+      "mean_token_accuracy": 0.8356850147247314,
+      "step": 192
+    },
+    {
+      "epoch": 3.0634920634920633,
+      "grad_norm": 0.9438294768333435,
+      "learning_rate": 3.5753065401771577e-06,
+      "loss": 0.3145,
+      "mean_token_accuracy": 0.8428582549095154,
+      "step": 193
+    },
+    {
+      "epoch": 3.0793650793650795,
+      "grad_norm": 0.9360758662223816,
+      "learning_rate": 3.5250289118887515e-06,
+      "loss": 0.301,
+      "mean_token_accuracy": 0.8718671202659607,
+      "step": 194
+    },
+    {
+      "epoch": 3.0952380952380953,
+      "grad_norm": 1.0166903734207153,
+      "learning_rate": 3.4749141145219118e-06,
+      "loss": 0.4573,
+      "mean_token_accuracy": 0.8153039813041687,
+      "step": 195
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 1.1550116539001465,
+      "learning_rate": 3.424967680550261e-06,
+      "loss": 0.2792,
+      "mean_token_accuracy": 0.8631125688552856,
+      "step": 196
+    },
+    {
+      "epoch": 3.126984126984127,
+      "grad_norm": 1.2632681131362915,
+      "learning_rate": 3.3751951238607745e-06,
+      "loss": 0.4172,
+      "mean_token_accuracy": 0.8394821882247925,
+      "step": 197
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 1.038863182067871,
+      "learning_rate": 3.3256019391450696e-06,
+      "loss": 0.3061,
+      "mean_token_accuracy": 0.8498005867004395,
+      "step": 198
+    },
+    {
+      "epoch": 3.1587301587301586,
+      "grad_norm": 1.0904754400253296,
+      "learning_rate": 3.2761936012928147e-06,
+      "loss": 0.348,
+      "mean_token_accuracy": 0.8540592789649963,
+      "step": 199
+    },
+    {
+      "epoch": 3.1746031746031744,
+      "grad_norm": 0.9854816198348999,
+      "learning_rate": 3.226975564787322e-06,
+      "loss": 0.2568,
+      "mean_token_accuracy": 0.875607967376709,
+      "step": 200
+    },
+    {
+      "epoch": 3.1904761904761907,
+      "grad_norm": 0.8879172205924988,
+      "learning_rate": 3.177953263103394e-06,
+      "loss": 0.2795,
+      "mean_token_accuracy": 0.8490285873413086,
+      "step": 201
+    },
+    {
+      "epoch": 3.2063492063492065,
+      "grad_norm": 0.9653210043907166,
+      "learning_rate": 3.1291321081074887e-06,
+      "loss": 0.3708,
+      "mean_token_accuracy": 0.8345485925674438,
+      "step": 202
+    },
+    {
+      "epoch": 3.2222222222222223,
+      "grad_norm": 0.9958736300468445,
+      "learning_rate": 3.0805174894602775e-06,
+      "loss": 0.2408,
+      "mean_token_accuracy": 0.880729615688324,
+      "step": 203
+    },
+    {
+      "epoch": 3.238095238095238,
+      "grad_norm": 1.0178455114364624,
+      "learning_rate": 3.032114774021636e-06,
+      "loss": 0.2956,
+      "mean_token_accuracy": 0.8619508147239685,
+      "step": 204
+    },
+    {
+      "epoch": 3.253968253968254,
+      "grad_norm": 0.8538744449615479,
+      "learning_rate": 2.9839293052581767e-06,
+      "loss": 0.3073,
+      "mean_token_accuracy": 0.8429595828056335,
+      "step": 205
+    },
+    {
+      "epoch": 3.2698412698412698,
+      "grad_norm": 0.9814417958259583,
+      "learning_rate": 2.9359664026533443e-06,
+      "loss": 0.2406,
+      "mean_token_accuracy": 0.8716104030609131,
+      "step": 206
+    },
+    {
+      "epoch": 3.2857142857142856,
+      "grad_norm": 0.9848408699035645,
+      "learning_rate": 2.8882313611201684e-06,
+      "loss": 0.288,
+      "mean_token_accuracy": 0.8815993070602417,
+      "step": 207
+    },
+    {
+      "epoch": 3.3015873015873014,
+      "grad_norm": 0.8855112195014954,
+      "learning_rate": 2.8407294504167238e-06,
+      "loss": 0.2531,
+      "mean_token_accuracy": 0.8810189366340637,
+      "step": 208
+    },
+    {
+      "epoch": 3.317460317460317,
+      "grad_norm": 0.8929734826087952,
+      "learning_rate": 2.793465914564375e-06,
+      "loss": 0.4829,
+      "mean_token_accuracy": 0.8090415000915527,
+      "step": 209
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.0123332738876343,
+      "learning_rate": 2.7464459712688517e-06,
+      "loss": 0.2815,
+      "mean_token_accuracy": 0.8740373849868774,
+      "step": 210
+    },
+    {
+      "epoch": 3.3492063492063493,
+      "grad_norm": 1.0554940700531006,
+      "learning_rate": 2.6996748113442397e-06,
+      "loss": 0.3835,
+      "mean_token_accuracy": 0.8110551834106445,
+      "step": 211
+    },
+    {
+      "epoch": 3.365079365079365,
+      "grad_norm": 0.9500500559806824,
+      "learning_rate": 2.653157598139932e-06,
+      "loss": 0.2907,
+      "mean_token_accuracy": 0.8597709536552429,
+      "step": 212
+    },
+    {
+      "epoch": 3.380952380952381,
+      "grad_norm": 0.9809661507606506,
+      "learning_rate": 2.6068994669706184e-06,
+      "loss": 0.2737,
+      "mean_token_accuracy": 0.8710864186286926,
+      "step": 213
+    },
+    {
+      "epoch": 3.3968253968253967,
+      "grad_norm": 0.967326283454895,
+      "learning_rate": 2.560905524549364e-06,
+      "loss": 0.4357,
+      "mean_token_accuracy": 0.8136948347091675,
+      "step": 214
+    },
+    {
+      "epoch": 3.4126984126984126,
+      "grad_norm": 0.9581484198570251,
+      "learning_rate": 2.515180848423853e-06,
+      "loss": 0.341,
+      "mean_token_accuracy": 0.8100842833518982,
+      "step": 215
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.993191123008728,
+      "learning_rate": 2.469730486415842e-06,
+      "loss": 0.4183,
+      "mean_token_accuracy": 0.8140695095062256,
+      "step": 216
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 1.1389352083206177,
+      "learning_rate": 2.4245594560639086e-06,
+      "loss": 0.4337,
+      "mean_token_accuracy": 0.8231166005134583,
+      "step": 217
+    },
+    {
+      "epoch": 3.4603174603174605,
+      "grad_norm": 0.9238110780715942,
+      "learning_rate": 2.379672744069527e-06,
+      "loss": 0.2668,
+      "mean_token_accuracy": 0.8638157248497009,
+      "step": 218
+    },
+    {
+      "epoch": 3.4761904761904763,
+      "grad_norm": 0.8576727509498596,
+      "learning_rate": 2.335075305746558e-06,
+      "loss": 0.4097,
+      "mean_token_accuracy": 0.8153740167617798,
+      "step": 219
+    },
+    {
+      "epoch": 3.492063492063492,
+      "grad_norm": 0.9489086270332336,
+      "learning_rate": 2.2907720644742064e-06,
+      "loss": 0.3302,
+      "mean_token_accuracy": 0.8554107546806335,
+      "step": 220
+    },
+    {
+      "epoch": 3.507936507936508,
+      "grad_norm": 0.8985493183135986,
+      "learning_rate": 2.2467679111534963e-06,
+      "loss": 0.2694,
+      "mean_token_accuracy": 0.8727717995643616,
+      "step": 221
+    },
+    {
+      "epoch": 3.5238095238095237,
+      "grad_norm": 0.944635808467865,
+      "learning_rate": 2.2030677036673345e-06,
+      "loss": 0.2121,
+      "mean_token_accuracy": 0.8995314836502075,
+      "step": 222
+    },
+    {
+      "epoch": 3.5396825396825395,
+      "grad_norm": 0.9656152725219727,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.2291,
+      "mean_token_accuracy": 0.878724217414856,
+      "step": 223
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 0.9597203731536865,
+      "learning_rate": 2.1165983894256647e-06,
+      "loss": 0.3377,
+      "mean_token_accuracy": 0.792270839214325,
+      "step": 224
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.9298219084739685,
+      "learning_rate": 2.0738388285373532e-06,
+      "loss": 0.3623,
+      "mean_token_accuracy": 0.8369730710983276,
+      "step": 225
+    },
+    {
+      "epoch": 3.5873015873015874,
+      "grad_norm": 0.9328715801239014,
+      "learning_rate": 2.0314023041641567e-06,
+      "loss": 0.2316,
+      "mean_token_accuracy": 0.8964474201202393,
+      "step": 226
+    },
+    {
+      "epoch": 3.6031746031746033,
+      "grad_norm": 0.9059308171272278,
+      "learning_rate": 1.9892935011290037e-06,
+      "loss": 0.3551,
+      "mean_token_accuracy": 0.82100510597229,
+      "step": 227
+    },
+    {
+      "epoch": 3.619047619047619,
+      "grad_norm": 0.9704643487930298,
+      "learning_rate": 1.947517068075694e-06,
+      "loss": 0.3542,
+      "mean_token_accuracy": 0.819314181804657,
+      "step": 228
+    },
+    {
+      "epoch": 3.634920634920635,
+      "grad_norm": 0.9183152914047241,
+      "learning_rate": 1.9060776169557083e-06,
+      "loss": 0.3369,
+      "mean_token_accuracy": 0.8172284364700317,
+      "step": 229
+    },
+    {
+      "epoch": 3.6507936507936507,
+      "grad_norm": 0.8920512199401855,
+      "learning_rate": 1.864979722519068e-06,
+      "loss": 0.3374,
+      "mean_token_accuracy": 0.8380458950996399,
+      "step": 230
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.9079098701477051,
+      "learning_rate": 1.8242279218092968e-06,
+      "loss": 0.3542,
+      "mean_token_accuracy": 0.810836672782898,
+      "step": 231
+    },
+    {
+      "epoch": 3.682539682539683,
+      "grad_norm": 0.9223353862762451,
+      "learning_rate": 1.7838267136625536e-06,
+      "loss": 0.323,
+      "mean_token_accuracy": 0.8441075682640076,
+      "step": 232
+    },
+    {
+      "epoch": 3.6984126984126986,
+      "grad_norm": 0.9578335285186768,
+      "learning_rate": 1.743780558210979e-06,
+      "loss": 0.3374,
+      "mean_token_accuracy": 0.8461949825286865,
+      "step": 233
+    },
+    {
+      "epoch": 3.7142857142857144,
+      "grad_norm": 0.9013341665267944,
+      "learning_rate": 1.704093876390312e-06,
+      "loss": 0.3819,
+      "mean_token_accuracy": 0.8001118302345276,
+      "step": 234
+    },
+    {
+      "epoch": 3.7301587301587302,
+      "grad_norm": 0.9634210467338562,
+      "learning_rate": 1.664771049451837e-06,
+      "loss": 0.334,
+      "mean_token_accuracy": 0.8557538986206055,
+      "step": 235
+    },
+    {
+      "epoch": 3.746031746031746,
+      "grad_norm": 0.9999906420707703,
+      "learning_rate": 1.6258164184787123e-06,
+      "loss": 0.3963,
+      "mean_token_accuracy": 0.8313020467758179,
+      "step": 236
+    },
+    {
+      "epoch": 3.761904761904762,
+      "grad_norm": 0.8461647033691406,
+      "learning_rate": 1.5872342839067305e-06,
+      "loss": 0.2897,
+      "mean_token_accuracy": 0.8658589124679565,
+      "step": 237
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 0.9704185724258423,
+      "learning_rate": 1.5490289050495678e-06,
+      "loss": 0.2794,
+      "mean_token_accuracy": 0.8769487738609314,
+      "step": 238
+    },
+    {
+      "epoch": 3.7936507936507935,
+      "grad_norm": 0.9365107417106628,
+      "learning_rate": 1.511204499628574e-06,
+      "loss": 0.2495,
+      "mean_token_accuracy": 0.85855633020401,
+      "step": 239
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 0.8701555728912354,
+      "learning_rate": 1.4737652433071515e-06,
+      "loss": 0.2165,
+      "mean_token_accuracy": 0.9040277600288391,
+      "step": 240
+    },
+    {
+      "epoch": 3.825396825396825,
+      "grad_norm": 0.8181148767471313,
+      "learning_rate": 1.4367152692297799e-06,
+      "loss": 0.2553,
+      "mean_token_accuracy": 0.8754419088363647,
+      "step": 241
+    },
+    {
+      "epoch": 3.8412698412698414,
+      "grad_norm": 0.9489231705665588,
+      "learning_rate": 1.4000586675657312e-06,
+      "loss": 0.3396,
+      "mean_token_accuracy": 0.8487692475318909,
+      "step": 242
+    },
+    {
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.900195300579071,
+      "learning_rate": 1.3637994850575342e-06,
+      "loss": 0.3302,
+      "mean_token_accuracy": 0.8432536721229553,
+      "step": 243
+    },
+    {
+      "epoch": 3.873015873015873,
+      "grad_norm": 0.8330630660057068,
+      "learning_rate": 1.3279417245742288e-06,
+      "loss": 0.3202,
+      "mean_token_accuracy": 0.8341889977455139,
+      "step": 244
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.8900310397148132,
+      "learning_rate": 1.2924893446694648e-06,
+      "loss": 0.2512,
+      "mean_token_accuracy": 0.9006067514419556,
+      "step": 245
+    },
+    {
+      "epoch": 3.9047619047619047,
+      "grad_norm": 1.012221097946167,
+      "learning_rate": 1.257446259144494e-06,
+      "loss": 0.2737,
+      "mean_token_accuracy": 0.8853955864906311,
+      "step": 246
+    },
+    {
+      "epoch": 3.9206349206349205,
+      "grad_norm": 0.9133668541908264,
+      "learning_rate": 1.222816336616104e-06,
+      "loss": 0.3018,
+      "mean_token_accuracy": 0.8480285406112671,
+      "step": 247
+    },
+    {
+      "epoch": 3.9365079365079367,
+      "grad_norm": 0.9964957237243652,
+      "learning_rate": 1.1886034000895341e-06,
+      "loss": 0.2809,
+      "mean_token_accuracy": 0.8873778581619263,
+      "step": 248
+    },
+    {
+      "epoch": 3.9523809523809526,
+      "grad_norm": 0.9411323666572571,
+      "learning_rate": 1.1548112265364336e-06,
+      "loss": 0.2238,
+      "mean_token_accuracy": 0.8850132822990417,
+      "step": 249
+    },
+    {
+      "epoch": 3.9682539682539684,
+      "grad_norm": 1.0889853239059448,
+      "learning_rate": 1.1214435464779006e-06,
+      "loss": 0.2481,
+      "mean_token_accuracy": 0.8736922144889832,
+      "step": 250
+    },
+    {
+      "epoch": 3.984126984126984,
+      "grad_norm": 0.9061523675918579,
+      "learning_rate": 1.088504043572643e-06,
+      "loss": 0.3973,
+      "mean_token_accuracy": 0.8074966073036194,
+      "step": 251
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.730003833770752,
+      "learning_rate": 1.055996354210323e-06,
+      "loss": 0.2061,
+      "mean_token_accuracy": 0.8607027530670166,
+      "step": 252
+    },
+    {
+      "epoch": 4.015873015873016,
+      "grad_norm": 1.1500871181488037,
+      "learning_rate": 1.0239240671101065e-06,
+      "loss": 0.3139,
+      "mean_token_accuracy": 0.850020170211792,
+      "step": 253
+    },
+    {
+      "epoch": 4.031746031746032,
+      "grad_norm": 1.156367540359497,
+      "learning_rate": 9.922907229244905e-07,
+      "loss": 0.2297,
+      "mean_token_accuracy": 0.8770912289619446,
+      "step": 254
+    },
+    {
+      "epoch": 4.0476190476190474,
+      "grad_norm": 0.7985445261001587,
+      "learning_rate": 9.610998138484262e-07,
+      "loss": 0.3192,
+      "mean_token_accuracy": 0.8431568145751953,
+      "step": 255
+    },
+    {
+      "epoch": 4.063492063492063,
+      "grad_norm": 0.815024733543396,
+      "learning_rate": 9.303547832337934e-07,
+      "loss": 0.3501,
+      "mean_token_accuracy": 0.8213564157485962,
+      "step": 256
+    },
+    {
+      "epoch": 4.079365079365079,
+      "grad_norm": 0.8376876711845398,
+      "learning_rate": 9.000590252092701e-07,
+      "loss": 0.2319,
+      "mean_token_accuracy": 0.8903968930244446,
+      "step": 257
+    },
+    {
+      "epoch": 4.095238095238095,
+      "grad_norm": 0.8753305673599243,
+      "learning_rate": 8.702158843056319e-07,
+      "loss": 0.192,
+      "mean_token_accuracy": 0.8974818587303162,
+      "step": 258
+    },
+    {
+      "epoch": 4.111111111111111,
+      "grad_norm": 0.6304527521133423,
+      "learning_rate": 8.408286550865319e-07,
+      "loss": 0.1804,
+      "mean_token_accuracy": 0.8988710045814514,
+      "step": 259
+    },
+    {
+      "epoch": 4.1269841269841265,
+      "grad_norm": 0.789614737033844,
+      "learning_rate": 8.119005817847924e-07,
+      "loss": 0.2458,
+      "mean_token_accuracy": 0.881997287273407,
+      "step": 260
+    },
+    {
+      "epoch": 4.142857142857143,
+      "grad_norm": 0.6855416297912598,
+      "learning_rate": 7.834348579442552e-07,
+      "loss": 0.2613,
+      "mean_token_accuracy": 0.8605210781097412,
+      "step": 261
+    },
+    {
+      "epoch": 4.158730158730159,
+      "grad_norm": 1.0017073154449463,
+      "learning_rate": 7.554346260672263e-07,
+      "loss": 0.2093,
+      "mean_token_accuracy": 0.9028944373130798,
+      "step": 262
+    },
+    {
+      "epoch": 4.174603174603175,
+      "grad_norm": 0.8033848404884338,
+      "learning_rate": 7.279029772675572e-07,
+      "loss": 0.2089,
+      "mean_token_accuracy": 0.8698593378067017,
+      "step": 263
+    },
+    {
+      "epoch": 4.190476190476191,
+      "grad_norm": 0.9745374321937561,
+      "learning_rate": 7.008429509293979e-07,
+      "loss": 0.3764,
+      "mean_token_accuracy": 0.8211672306060791,
+      "step": 264
+    },
+    {
+      "epoch": 4.2063492063492065,
+      "grad_norm": 0.7626347541809082,
+      "learning_rate": 6.742575343716584e-07,
+      "loss": 0.1828,
+      "mean_token_accuracy": 0.9040178656578064,
+      "step": 265
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 0.7874695062637329,
+      "learning_rate": 6.481496625182271e-07,
+      "loss": 0.2049,
+      "mean_token_accuracy": 0.9025614261627197,
+      "step": 266
+    },
+    {
+      "epoch": 4.238095238095238,
+      "grad_norm": 0.7818242311477661,
+      "learning_rate": 6.225222175739598e-07,
+      "loss": 0.2095,
+      "mean_token_accuracy": 0.8919832706451416,
+      "step": 267
+    },
+    {
+      "epoch": 4.253968253968254,
+      "grad_norm": 0.7495545148849487,
+      "learning_rate": 5.973780287065007e-07,
+      "loss": 0.1767,
+      "mean_token_accuracy": 0.8752344250679016,
+      "step": 268
+    },
+    {
+      "epoch": 4.26984126984127,
+      "grad_norm": 0.7969830632209778,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.2481,
+      "mean_token_accuracy": 0.8807870149612427,
+      "step": 269
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.8366702198982239,
+      "learning_rate": 5.485504688184307e-07,
+      "loss": 0.2136,
+      "mean_token_accuracy": 0.8853451609611511,
+      "step": 270
+    },
+    {
+      "epoch": 4.301587301587301,
+      "grad_norm": 0.7982764840126038,
+      "learning_rate": 5.24872488165562e-07,
+      "loss": 0.3475,
+      "mean_token_accuracy": 0.8398772478103638,
+      "step": 271
+    },
+    {
+      "epoch": 4.317460317460317,
+      "grad_norm": 0.8142274022102356,
+      "learning_rate": 5.016885437299113e-07,
+      "loss": 0.1818,
+      "mean_token_accuracy": 0.9124555587768555,
+      "step": 272
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.7483785152435303,
+      "learning_rate": 4.790011949264173e-07,
+      "loss": 0.2946,
+      "mean_token_accuracy": 0.8563975095748901,
+      "step": 273
+    },
+    {
+      "epoch": 4.349206349206349,
+      "grad_norm": 0.7258701324462891,
+      "learning_rate": 4.5681294634784437e-07,
+      "loss": 0.2076,
+      "mean_token_accuracy": 0.8760812878608704,
+      "step": 274
+    },
+    {
+      "epoch": 4.365079365079365,
+      "grad_norm": 0.694442093372345,
+      "learning_rate": 4.3512624748828225e-07,
+      "loss": 0.1756,
+      "mean_token_accuracy": 0.9021351337432861,
+      "step": 275
+    },
+    {
+      "epoch": 4.380952380952381,
+      "grad_norm": 0.7568174600601196,
+      "learning_rate": 4.139434924727359e-07,
+      "loss": 0.3157,
+      "mean_token_accuracy": 0.844300389289856,
+      "step": 276
+    },
+    {
+      "epoch": 4.396825396825397,
+      "grad_norm": 0.8990548253059387,
+      "learning_rate": 3.9326701979281623e-07,
+      "loss": 0.3777,
+      "mean_token_accuracy": 0.8513249754905701,
+      "step": 277
+    },
+    {
+      "epoch": 4.412698412698413,
+      "grad_norm": 0.7914615869522095,
+      "learning_rate": 3.7309911204858997e-07,
+      "loss": 0.2545,
+      "mean_token_accuracy": 0.8884080052375793,
+      "step": 278
+    },
+    {
+      "epoch": 4.428571428571429,
+      "grad_norm": 0.6982975006103516,
+      "learning_rate": 3.534419956965823e-07,
+      "loss": 0.2258,
+      "mean_token_accuracy": 0.8522327542304993,
+      "step": 279
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.6678464412689209,
+      "learning_rate": 3.3429784080398765e-07,
+      "loss": 0.223,
+      "mean_token_accuracy": 0.858345091342926,
+      "step": 280
+    },
+    {
+      "epoch": 4.4603174603174605,
+      "grad_norm": 0.8046327233314514,
+      "learning_rate": 3.1566876080910193e-07,
+      "loss": 0.2271,
+      "mean_token_accuracy": 0.890484094619751,
+      "step": 281
+    },
+    {
+      "epoch": 4.476190476190476,
+      "grad_norm": 0.6547771096229553,
+      "learning_rate": 2.9755681228800904e-07,
+      "loss": 0.1113,
+      "mean_token_accuracy": 0.9428154826164246,
+      "step": 282
+    },
+    {
+      "epoch": 4.492063492063492,
+      "grad_norm": 0.6625367999076843,
+      "learning_rate": 2.799639947275412e-07,
+      "loss": 0.2267,
+      "mean_token_accuracy": 0.8839855194091797,
+      "step": 283
+    },
+    {
+      "epoch": 4.507936507936508,
+      "grad_norm": 0.6415932178497314,
+      "learning_rate": 2.6289225030454556e-07,
+      "loss": 0.1348,
+      "mean_token_accuracy": 0.9356445074081421,
+      "step": 284
+    },
+    {
+      "epoch": 4.523809523809524,
+      "grad_norm": 0.6927193999290466,
+      "learning_rate": 2.4634346367147233e-07,
+      "loss": 0.1656,
+      "mean_token_accuracy": 0.9024729132652283,
+      "step": 285
+    },
+    {
+      "epoch": 4.5396825396825395,
+      "grad_norm": 0.7541980743408203,
+      "learning_rate": 2.303194617483212e-07,
+      "loss": 0.2002,
+      "mean_token_accuracy": 0.910742998123169,
+      "step": 286
+    },
+    {
+      "epoch": 4.555555555555555,
+      "grad_norm": 0.7845000624656677,
+      "learning_rate": 2.1482201352095277e-07,
+      "loss": 0.2971,
+      "mean_token_accuracy": 0.8502859473228455,
+      "step": 287
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.7539421319961548,
+      "learning_rate": 1.998528298458019e-07,
+      "loss": 0.1639,
+      "mean_token_accuracy": 0.9152542352676392,
+      "step": 288
+    },
+    {
+      "epoch": 4.587301587301587,
+      "grad_norm": 0.8608452081680298,
+      "learning_rate": 1.8541356326100436e-07,
+      "loss": 0.221,
+      "mean_token_accuracy": 0.9015839099884033,
+      "step": 289
+    },
+    {
+      "epoch": 4.603174603174603,
+      "grad_norm": 0.6219279170036316,
+      "learning_rate": 1.7150580780396385e-07,
+      "loss": 0.1736,
+      "mean_token_accuracy": 0.8898955583572388,
+      "step": 290
+    },
+    {
+      "epoch": 4.619047619047619,
+      "grad_norm": 0.803567111492157,
+      "learning_rate": 1.5813109883537792e-07,
+      "loss": 0.3578,
+      "mean_token_accuracy": 0.8290396928787231,
+      "step": 291
+    },
+    {
+      "epoch": 4.634920634920634,
+      "grad_norm": 0.7509638071060181,
+      "learning_rate": 1.4529091286973994e-07,
+      "loss": 0.2899,
+      "mean_token_accuracy": 0.8564021587371826,
+      "step": 292
+    },
+    {
+      "epoch": 4.650793650793651,
+      "grad_norm": 0.6981105208396912,
+      "learning_rate": 1.3298666741233424e-07,
+      "loss": 0.1755,
+      "mean_token_accuracy": 0.9039936661720276,
+      "step": 293
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.732633650302887,
+      "learning_rate": 1.2121972080275378e-07,
+      "loss": 0.2293,
+      "mean_token_accuracy": 0.8728380799293518,
+      "step": 294
+    },
+    {
+      "epoch": 4.682539682539683,
+      "grad_norm": 0.6291465759277344,
+      "learning_rate": 1.0999137206494315e-07,
+      "loss": 0.2377,
+      "mean_token_accuracy": 0.8596920371055603,
+      "step": 295
+    },
+    {
+      "epoch": 4.698412698412699,
+      "grad_norm": 0.724481999874115,
+      "learning_rate": 9.93028607637908e-08,
+      "loss": 0.2136,
+      "mean_token_accuracy": 0.8830126523971558,
+      "step": 296
+    },
+    {
+      "epoch": 4.714285714285714,
+      "grad_norm": 0.7379451394081116,
+      "learning_rate": 8.915536686828764e-08,
+      "loss": 0.2342,
+      "mean_token_accuracy": 0.8728898763656616,
+      "step": 297
+    },
+    {
+      "epoch": 4.73015873015873,
+      "grad_norm": 0.6381033658981323,
+      "learning_rate": 7.955001062125989e-08,
+      "loss": 0.3198,
+      "mean_token_accuracy": 0.8249152302742004,
+      "step": 298
+    },
+    {
+      "epoch": 4.746031746031746,
+      "grad_norm": 1.0338735580444336,
+      "learning_rate": 7.048785241570321e-08,
+      "loss": 0.3214,
+      "mean_token_accuracy": 0.8409817218780518,
+      "step": 299
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.9547169208526611,
+      "learning_rate": 6.19698926777168e-08,
+      "loss": 0.3432,
+      "mean_token_accuracy": 0.85186368227005,
+      "step": 300
+    },
+    {
+      "epoch": 4.777777777777778,
+      "grad_norm": 0.7398821711540222,
+      "learning_rate": 5.399707175606117e-08,
+      "loss": 0.2026,
+      "mean_token_accuracy": 0.8905254006385803,
+      "step": 301
+    },
+    {
+      "epoch": 4.7936507936507935,
+      "grad_norm": 1.3651663064956665,
+      "learning_rate": 4.657026981834623e-08,
+      "loss": 0.166,
+      "mean_token_accuracy": 0.8877707719802856,
+      "step": 302
+    },
+    {
+      "epoch": 4.809523809523809,
+      "grad_norm": 0.5856400728225708,
+      "learning_rate": 3.9690306753866204e-08,
+      "loss": 0.1787,
+      "mean_token_accuracy": 0.87652987241745,
+      "step": 303
+    },
+    {
+      "epoch": 4.825396825396825,
+      "grad_norm": 0.7481511831283569,
+      "learning_rate": 3.3357942083085404e-08,
+      "loss": 0.2439,
+      "mean_token_accuracy": 0.8784143328666687,
+      "step": 304
+    },
+    {
+      "epoch": 4.841269841269841,
+      "grad_norm": 1.0625805854797363,
+      "learning_rate": 2.7573874873791372e-08,
+      "loss": 0.3078,
+      "mean_token_accuracy": 0.8467578887939453,
+      "step": 305
+    },
+    {
+      "epoch": 4.857142857142857,
+      "grad_norm": 0.604770839214325,
+      "learning_rate": 2.233874366391997e-08,
+      "loss": 0.1143,
+      "mean_token_accuracy": 0.9412245750427246,
+      "step": 306
+    },
+    {
+      "epoch": 4.8730158730158735,
+      "grad_norm": 0.7869849801063538,
+      "learning_rate": 1.7653126391063425e-08,
+      "loss": 0.2249,
+      "mean_token_accuracy": 0.9017248749732971,
+      "step": 307
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 0.593639612197876,
+      "learning_rate": 1.3517540328669143e-08,
+      "loss": 0.1476,
+      "mean_token_accuracy": 0.9134231805801392,
+      "step": 308
+    },
+    {
+      "epoch": 4.904761904761905,
+      "grad_norm": 0.727486789226532,
+      "learning_rate": 9.93244202893262e-09,
+      "loss": 0.259,
+      "mean_token_accuracy": 0.8798890709877014,
+      "step": 309
+    },
+    {
+      "epoch": 4.920634920634921,
+      "grad_norm": 0.7199143767356873,
+      "learning_rate": 6.898227272398306e-09,
+      "loss": 0.2811,
+      "mean_token_accuracy": 0.8704081177711487,
+      "step": 310
+    },
+    {
+      "epoch": 4.936507936507937,
+      "grad_norm": 0.6624844670295715,
+      "learning_rate": 4.415231024265665e-09,
+      "loss": 0.1653,
+      "mean_token_accuracy": 0.9027133584022522,
+      "step": 311
+    },
+    {
+      "epoch": 4.9523809523809526,
+      "grad_norm": 0.6468021273612976,
+      "learning_rate": 2.4837273974115393e-09,
+      "loss": 0.2231,
+      "mean_token_accuracy": 0.8691893815994263,
+      "step": 312
+    },
+    {
+      "epoch": 4.968253968253968,
+      "grad_norm": 0.7659016251564026,
+      "learning_rate": 1.1039296221276863e-09,
+      "loss": 0.17,
+      "mean_token_accuracy": 0.9162414073944092,
+      "step": 313
+    },
+    {
+      "epoch": 4.984126984126984,
+      "grad_norm": 0.7621476650238037,
+      "learning_rate": 2.7599002258127395e-10,
+      "loss": 0.4016,
+      "mean_token_accuracy": 0.8406723737716675,
+      "step": 314
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7477962374687195,
+      "learning_rate": 0.0,
+      "loss": 0.259,
+      "mean_token_accuracy": 0.898563027381897,
+      "step": 315
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1003419865540198e+17,
+  "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 sha256:57968985d878f5196883f699a1751b4408dbad7e4a38a61484c69971da51118e
+size 5880