Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "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": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "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": "4.51.3"
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb0575d4c2ee06300c5ed086da9c18fdd7bbb2074319f832971fe0af829b935
+size 4498420872

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363dc9e276ccefd539de09ec7a34c57706ef295bf3da9d1bdc2c5300ddd2efaa
+size 4718804768

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47653d43ab0fe23158e2c00c9ef0bce8563ee839d823fc833820691a8e699f18
+size 4467075880

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691090e1132bda7a066de9b86d9fed4af12c48fc7e15001804e91d17077aedc2
+size 4467075880

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a6c5de03ee6f3d74aa3771fc1eb4a7e5773605f92d7b7b20d05684cc09764c
+size 4718804760

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a685615b6bd2853789c0235a000269a40ed7aedc5f281f696912897cb7c4376
+size 4467075904

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b085998983b5812c5f2ecf778ad0512aa5f9eff8ae3b9e0b728ac2a55389691
+size 4467075904

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14601cd2d083ea2a5b8bf5437cb3d054698afe9c9c5fc59b99c390c5035c179a
+size 4718804800

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fbeb25d2c0176eb7b6d5de9fe8da1a71765b1cab91c3edc7b58a3daa1ef926
+size 4467075904

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22902da69483f0b1be944ec4f68dc78d565f29035d88f8af2a0af7105950def0
+size 4467075904

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb9be826fdfe935d9dcf107fb2a6cfd1e1a234b66737bceaacb7254024d450c
+size 4718804800

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e1c80de439383451c7f03c7ff9f2e2927eacb0ca33a4c86187f32656e93911
+size 4467075904

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f28948ad07df5f653c649b0dcb6decceebff71ef8ac2a7593a9799b85047d8
+size 4467075904

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a7427532b110b0b7e24956fc7859a4b8771d10e5d9b9138513516fa7a9340d
+size 4718804800

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7713afd7fe5b4ae679d1d1dd63f3e5a05b29108ff38f40381627cd2f42ca38
+size 4467075904

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063e020a4c3b096a1dda074bae393e77a3b2300b69871fe13a25b4197a73ff71
+size 4467075904

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8630bbba946cbe96d1e5b154ce54ba7fc5c84695f1d36ad9f332a463778dbb3e
+size 4718804800

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6294a43839b1ae1b3f766d6139fc3e6f9d2d27eb1aea428ba322666d79120dc
+size 4467075904

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e15ff3f7f880bf3dbb059f26f756a7f167481f52b072c7b17373faebf6cb6a98
+size 4467075904

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be18fe27254b0f605390936481f98929cf02f3c1cc3a1699900a25f77e761f60
+size 4718804800

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4c33fe6c0b824add99824215ae6a4d1ace33ce6153afb0ea210573758dac2c
+size 4467075904

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a06af8476a2bd3b74089883f2c8f0d187dc4b0d7ef716cc24e34ea6564c6a1d
+size 4467075904

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a9fe27c7cd6aa1a6d21443c9e48b6c83212a2b42088ca70974bac75c3d1fe8
+size 4718804800

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606e636ecc32f9c947b0b430e64840cf6dca13c11d0bdd749c20fee3a13ffadc
+size 4467075904

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba7eed2415d8dfe689cd39570333cce11d8b7668899aeb915df53ca20daacc21
+size 4467075904

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39e0c34bbb92f25815325bda1374e0d00f933e0955bcd0f2466fab79725c4ae
+size 4718804800

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88258a3f6eb967945d45cb6be032a980eaec8139179ccb24d6f7a92ea9db492
+size 4467075904

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a26cc0c9aaa165b5fc40807d674bd8099e561bd035521e7d444279392ffb57
+size 4467075904

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4477e8f3611d607e2d58d863fb0589b6f5e808530ffb3fd4bc6ef118345fb66
+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 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 3.529888391494751,
+      "learning_rate": 0.0,
+      "loss": 0.9759,
+      "step": 1
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 3.281986951828003,
+      "learning_rate": 3.125e-07,
+      "loss": 1.2739,
+      "step": 2
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 3.5553019046783447,
+      "learning_rate": 6.25e-07,
+      "loss": 1.0645,
+      "step": 3
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 3.12208890914917,
+      "learning_rate": 9.375000000000001e-07,
+      "loss": 1.1015,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2750279903411865,
+      "learning_rate": 1.25e-06,
+      "loss": 1.0683,
+      "step": 5
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 3.2686679363250732,
+      "learning_rate": 1.5625e-06,
+      "loss": 1.1439,
+      "step": 6
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 2.7951087951660156,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.0532,
+      "step": 7
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.5674972534179688,
+      "learning_rate": 2.1875000000000002e-06,
+      "loss": 0.9506,
+      "step": 8
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 1.8560075759887695,
+      "learning_rate": 2.5e-06,
+      "loss": 1.1197,
+      "step": 9
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.9324836730957031,
+      "learning_rate": 2.8125e-06,
+      "loss": 1.0172,
+      "step": 10
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 2.0385169982910156,
+      "learning_rate": 3.125e-06,
+      "loss": 1.1426,
+      "step": 11
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 1.6919538974761963,
+      "learning_rate": 3.4375e-06,
+      "loss": 0.8428,
+      "step": 12
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 1.6007992029190063,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.0347,
+      "step": 13
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 1.3211313486099243,
+      "learning_rate": 4.0625000000000005e-06,
+      "loss": 0.8957,
+      "step": 14
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.3300317525863647,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.9216,
+      "step": 15
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.6186965703964233,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 1.0288,
+      "step": 16
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 1.6145991086959839,
+      "learning_rate": 5e-06,
+      "loss": 0.9375,
+      "step": 17
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 1.5419466495513916,
+      "learning_rate": 5.3125e-06,
+      "loss": 0.9756,
+      "step": 18
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 1.648453950881958,
+      "learning_rate": 5.625e-06,
+      "loss": 0.97,
+      "step": 19
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.3759514093399048,
+      "learning_rate": 5.9375e-06,
+      "loss": 0.8475,
+      "step": 20
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 1.2092012166976929,
+      "learning_rate": 6.25e-06,
+      "loss": 0.8766,
+      "step": 21
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.9984509348869324,
+      "learning_rate": 6.5625e-06,
+      "loss": 0.774,
+      "step": 22
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 1.0240399837493896,
+      "learning_rate": 6.875e-06,
+      "loss": 0.9397,
+      "step": 23
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 1.1769076585769653,
+      "learning_rate": 7.1875e-06,
+      "loss": 0.8844,
+      "step": 24
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4975842237472534,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.0161,
+      "step": 25
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 1.109714388847351,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.842,
+      "step": 26
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 1.2334775924682617,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 0.8422,
+      "step": 27
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 1.3736600875854492,
+      "learning_rate": 8.4375e-06,
+      "loss": 1.1298,
+      "step": 28
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.9003278017044067,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.8767,
+      "step": 29
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.9821781516075134,
+      "learning_rate": 9.0625e-06,
+      "loss": 0.9183,
+      "step": 30
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 1.1022597551345825,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.8969,
+      "step": 31
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.9418491125106812,
+      "learning_rate": 9.6875e-06,
+      "loss": 1.1137,
+      "step": 32
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.8792409300804138,
+      "learning_rate": 1e-05,
+      "loss": 0.8646,
+      "step": 33
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.8813374638557434,
+      "learning_rate": 9.999929833574693e-06,
+      "loss": 0.8997,
+      "step": 34
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.0796589851379395,
+      "learning_rate": 9.999719336268101e-06,
+      "loss": 0.9681,
+      "step": 35
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7816510796546936,
+      "learning_rate": 9.999368513988161e-06,
+      "loss": 0.9548,
+      "step": 36
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.8990465998649597,
+      "learning_rate": 9.99887737658125e-06,
+      "loss": 0.6577,
+      "step": 37
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.8825920224189758,
+      "learning_rate": 9.998245937831916e-06,
+      "loss": 0.7376,
+      "step": 38
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.9657986164093018,
+      "learning_rate": 9.997474215462472e-06,
+      "loss": 0.8895,
+      "step": 39
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8648184537887573,
+      "learning_rate": 9.996562231132523e-06,
+      "loss": 0.8063,
+      "step": 40
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 1.1329277753829956,
+      "learning_rate": 9.995510010438338e-06,
+      "loss": 0.9288,
+      "step": 41
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.7937431931495667,
+      "learning_rate": 9.994317582912147e-06,
+      "loss": 0.9438,
+      "step": 42
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.7383329272270203,
+      "learning_rate": 9.992984982021295e-06,
+      "loss": 0.9329,
+      "step": 43
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.8337100744247437,
+      "learning_rate": 9.991512245167322e-06,
+      "loss": 1.0846,
+      "step": 44
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.7664881944656372,
+      "learning_rate": 9.9898994136849e-06,
+      "loss": 0.9438,
+      "step": 45
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.802118182182312,
+      "learning_rate": 9.988146532840678e-06,
+      "loss": 0.6985,
+      "step": 46
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.8228673934936523,
+      "learning_rate": 9.986253651832005e-06,
+      "loss": 0.65,
+      "step": 47
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.8711133003234863,
+      "learning_rate": 9.984220823785562e-06,
+      "loss": 0.9301,
+      "step": 48
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.9292516112327576,
+      "learning_rate": 9.98204810575586e-06,
+      "loss": 0.8637,
+      "step": 49
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.977744460105896,
+      "learning_rate": 9.97973555872364e-06,
+      "loss": 1.1101,
+      "step": 50
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.7829723358154297,
+      "learning_rate": 9.977283247594167e-06,
+      "loss": 0.8359,
+      "step": 51
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 1.2702577114105225,
+      "learning_rate": 9.974691241195401e-06,
+      "loss": 0.7864,
+      "step": 52
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 1.000289797782898,
+      "learning_rate": 9.971959612276077e-06,
+      "loss": 0.729,
+      "step": 53
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7019366025924683,
+      "learning_rate": 9.969088437503642e-06,
+      "loss": 0.6929,
+      "step": 54
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.8953970670700073,
+      "learning_rate": 9.96607779746213e-06,
+      "loss": 0.9943,
+      "step": 55
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.8025823831558228,
+      "learning_rate": 9.962927776649877e-06,
+      "loss": 0.8219,
+      "step": 56
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.7636550664901733,
+      "learning_rate": 9.959638463477165e-06,
+      "loss": 0.8059,
+      "step": 57
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 1.036100149154663,
+      "learning_rate": 9.956209950263733e-06,
+      "loss": 0.8751,
+      "step": 58
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.7618421912193298,
+      "learning_rate": 9.952642333236187e-06,
+      "loss": 0.8882,
+      "step": 59
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.137510061264038,
+      "learning_rate": 9.948935712525299e-06,
+      "loss": 0.8802,
+      "step": 60
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 1.068774938583374,
+      "learning_rate": 9.945090192163202e-06,
+      "loss": 0.8555,
+      "step": 61
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 1.0687304735183716,
+      "learning_rate": 9.941105880080462e-06,
+      "loss": 0.8317,
+      "step": 62
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.8124951124191284,
+      "learning_rate": 9.936982888103051e-06,
+      "loss": 0.7598,
+      "step": 63
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 1.915030598640442,
+      "learning_rate": 9.932721331949215e-06,
+      "loss": 0.8643,
+      "step": 64
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.7891221046447754,
+      "learning_rate": 9.928321331226219e-06,
+      "loss": 1.0374,
+      "step": 65
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.9374336004257202,
+      "learning_rate": 9.92378300942699e-06,
+      "loss": 0.9368,
+      "step": 66
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.7771198749542236,
+      "learning_rate": 9.919106493926656e-06,
+      "loss": 0.7693,
+      "step": 67
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.7613469362258911,
+      "learning_rate": 9.914291915978967e-06,
+      "loss": 0.8428,
+      "step": 68
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.7074638605117798,
+      "learning_rate": 9.909339410712614e-06,
+      "loss": 0.8441,
+      "step": 69
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.778361976146698,
+      "learning_rate": 9.90424911712743e-06,
+      "loss": 0.747,
+      "step": 70
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 1.0298734903335571,
+      "learning_rate": 9.8990211780905e-06,
+      "loss": 0.9775,
+      "step": 71
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.7833291292190552,
+      "learning_rate": 9.89365574033214e-06,
+      "loss": 0.9342,
+      "step": 72
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.8498789668083191,
+      "learning_rate": 9.888152954441785e-06,
+      "loss": 0.9777,
+      "step": 73
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.7668773531913757,
+      "learning_rate": 9.882512974863763e-06,
+      "loss": 0.9195,
+      "step": 74
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.8688188195228577,
+      "learning_rate": 9.876735959892954e-06,
+      "loss": 0.7036,
+      "step": 75
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.8813723921775818,
+      "learning_rate": 9.870822071670353e-06,
+      "loss": 0.8859,
+      "step": 76
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.755993127822876,
+      "learning_rate": 9.864771476178523e-06,
+      "loss": 0.8843,
+      "step": 77
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.8362938761711121,
+      "learning_rate": 9.858584343236922e-06,
+      "loss": 0.8544,
+      "step": 78
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6849308609962463,
+      "learning_rate": 9.852260846497153e-06,
+      "loss": 0.811,
+      "step": 79
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.7551285028457642,
+      "learning_rate": 9.84580116343808e-06,
+      "loss": 0.6442,
+      "step": 80
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.7571239471435547,
+      "learning_rate": 9.83920547536085e-06,
+      "loss": 0.8653,
+      "step": 81
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.6928921937942505,
+      "learning_rate": 9.832473967383807e-06,
+      "loss": 0.727,
+      "step": 82
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.7975277900695801,
+      "learning_rate": 9.82560682843729e-06,
+      "loss": 0.9674,
+      "step": 83
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.7363450527191162,
+      "learning_rate": 9.818604251258336e-06,
+      "loss": 0.7874,
+      "step": 84
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.6111811995506287,
+      "learning_rate": 9.811466432385269e-06,
+      "loss": 0.8086,
+      "step": 85
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.7025948166847229,
+      "learning_rate": 9.804193572152181e-06,
+      "loss": 0.8113,
+      "step": 86
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.9773002862930298,
+      "learning_rate": 9.796785874683314e-06,
+      "loss": 0.7697,
+      "step": 87
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.7383718490600586,
+      "learning_rate": 9.789243547887333e-06,
+      "loss": 0.7011,
+      "step": 88
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.7938329577445984,
+      "learning_rate": 9.781566803451476e-06,
+      "loss": 0.8166,
+      "step": 89
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.7793764472007751,
+      "learning_rate": 9.773755856835632e-06,
+      "loss": 0.8311,
+      "step": 90
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.9532372951507568,
+      "learning_rate": 9.765810927266281e-06,
+      "loss": 0.8119,
+      "step": 91
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.7444455623626709,
+      "learning_rate": 9.757732237730346e-06,
+      "loss": 0.7035,
+      "step": 92
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.7543677687644958,
+      "learning_rate": 9.749520014968936e-06,
+      "loss": 0.8596,
+      "step": 93
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.8793447017669678,
+      "learning_rate": 9.741174489470973e-06,
+      "loss": 0.8417,
+      "step": 94
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.7709240913391113,
+      "learning_rate": 9.732695895466736e-06,
+      "loss": 0.951,
+      "step": 95
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.7557228207588196,
+      "learning_rate": 9.724084470921276e-06,
+      "loss": 0.7728,
+      "step": 96
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6922687292098999,
+      "learning_rate": 9.715340457527746e-06,
+      "loss": 0.7111,
+      "step": 97
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6909214854240417,
+      "learning_rate": 9.70646410070061e-06,
+      "loss": 0.7744,
+      "step": 98
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.8292551040649414,
+      "learning_rate": 9.697455649568761e-06,
+      "loss": 0.8375,
+      "step": 99
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.9321988224983215,
+      "learning_rate": 9.688315356968521e-06,
+      "loss": 0.7568,
+      "step": 100
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.727719247341156,
+      "learning_rate": 9.679043479436558e-06,
+      "loss": 0.7956,
+      "step": 101
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.8989289999008179,
+      "learning_rate": 9.669640277202668e-06,
+      "loss": 0.8649,
+      "step": 102
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.7082470655441284,
+      "learning_rate": 9.660106014182488e-06,
+      "loss": 0.7592,
+      "step": 103
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6200354695320129,
+      "learning_rate": 9.650440957970082e-06,
+      "loss": 0.8397,
+      "step": 104
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.7283597588539124,
+      "learning_rate": 9.640645379830424e-06,
+      "loss": 0.8769,
+      "step": 105
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.9149224162101746,
+      "learning_rate": 9.630719554691797e-06,
+      "loss": 0.8941,
+      "step": 106
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.9291213154792786,
+      "learning_rate": 9.620663761138067e-06,
+      "loss": 0.7206,
+      "step": 107
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 10.9785795211792,
+      "learning_rate": 9.61047828140087e-06,
+      "loss": 0.8174,
+      "step": 108
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.7933905720710754,
+      "learning_rate": 9.600163401351687e-06,
+      "loss": 0.6462,
+      "step": 109
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.7751436233520508,
+      "learning_rate": 9.589719410493822e-06,
+      "loss": 0.7219,
+      "step": 110
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.6992522478103638,
+      "learning_rate": 9.579146601954276e-06,
+      "loss": 0.8772,
+      "step": 111
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7739602327346802,
+      "learning_rate": 9.568445272475523e-06,
+      "loss": 0.7861,
+      "step": 112
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.651563823223114,
+      "learning_rate": 9.557615722407178e-06,
+      "loss": 0.6754,
+      "step": 113
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7253920435905457,
+      "learning_rate": 9.546658255697564e-06,
+      "loss": 0.9073,
+      "step": 114
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.6836376786231995,
+      "learning_rate": 9.535573179885192e-06,
+      "loss": 0.6826,
+      "step": 115
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.8201433420181274,
+      "learning_rate": 9.524360806090116e-06,
+      "loss": 0.8268,
+      "step": 116
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7789636850357056,
+      "learning_rate": 9.513021449005214e-06,
+      "loss": 0.7877,
+      "step": 117
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6954028010368347,
+      "learning_rate": 9.501555426887347e-06,
+      "loss": 0.8713,
+      "step": 118
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6693722605705261,
+      "learning_rate": 9.489963061548429e-06,
+      "loss": 0.7329,
+      "step": 119
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.7430814504623413,
+      "learning_rate": 9.47824467834639e-06,
+      "loss": 0.8962,
+      "step": 120
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.7947912216186523,
+      "learning_rate": 9.466400606176062e-06,
+      "loss": 0.8082,
+      "step": 121
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.7026137113571167,
+      "learning_rate": 9.454431177459921e-06,
+      "loss": 0.6821,
+      "step": 122
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.9153499007225037,
+      "learning_rate": 9.44233672813878e-06,
+      "loss": 0.8049,
+      "step": 123
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.7252680659294128,
+      "learning_rate": 9.430117597662347e-06,
+      "loss": 0.8743,
+      "step": 124
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7242833971977234,
+      "learning_rate": 9.417774128979706e-06,
+      "loss": 0.75,
+      "step": 125
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.7559160590171814,
+      "learning_rate": 9.405306668529686e-06,
+      "loss": 0.8542,
+      "step": 126
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.7200192809104919,
+      "learning_rate": 9.392715566231139e-06,
+      "loss": 0.5788,
+      "step": 127
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.7620433568954468,
+      "learning_rate": 9.380001175473122e-06,
+      "loss": 0.7527,
+      "step": 128
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 1.239641785621643,
+      "learning_rate": 9.367163853104975e-06,
+      "loss": 0.6383,
+      "step": 129
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.87204909324646,
+      "learning_rate": 9.354203959426304e-06,
+      "loss": 0.8664,
+      "step": 130
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.8700604438781738,
+      "learning_rate": 9.341121858176877e-06,
+      "loss": 0.7677,
+      "step": 131
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.9424646496772766,
+      "learning_rate": 9.327917916526404e-06,
+      "loss": 0.6948,
+      "step": 132
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.665458083152771,
+      "learning_rate": 9.314592505064239e-06,
+      "loss": 0.588,
+      "step": 133
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.8682693839073181,
+      "learning_rate": 9.301145997788979e-06,
+      "loss": 0.5747,
+      "step": 134
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.8103286623954773,
+      "learning_rate": 9.28757877209796e-06,
+      "loss": 0.6656,
+      "step": 135
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7613607048988342,
+      "learning_rate": 9.273891208776677e-06,
+      "loss": 0.711,
+      "step": 136
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.8730084300041199,
+      "learning_rate": 9.260083691988084e-06,
+      "loss": 0.8754,
+      "step": 137
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.7556143999099731,
+      "learning_rate": 9.24615660926182e-06,
+      "loss": 0.6424,
+      "step": 138
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 1.0018525123596191,
+      "learning_rate": 9.232110351483328e-06,
+      "loss": 0.7747,
+      "step": 139
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.9340951442718506,
+      "learning_rate": 9.217945312882888e-06,
+      "loss": 0.636,
+      "step": 140
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.9967073202133179,
+      "learning_rate": 9.203661891024547e-06,
+      "loss": 0.6471,
+      "step": 141
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.8169956207275391,
+      "learning_rate": 9.189260486794969e-06,
+      "loss": 0.7279,
+      "step": 142
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.646855890750885,
+      "learning_rate": 9.174741504392173e-06,
+      "loss": 0.7133,
+      "step": 143
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.7574021220207214,
+      "learning_rate": 9.160105351314199e-06,
+      "loss": 0.7038,
+      "step": 144
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.9536041617393494,
+      "learning_rate": 9.145352438347662e-06,
+      "loss": 0.6865,
+      "step": 145
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.7507240176200867,
+      "learning_rate": 9.13048317955623e-06,
+      "loss": 0.6116,
+      "step": 146
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.6842953562736511,
+      "learning_rate": 9.115497992268995e-06,
+      "loss": 0.7511,
+      "step": 147
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.8292526602745056,
+      "learning_rate": 9.10039729706877e-06,
+      "loss": 0.6075,
+      "step": 148
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.6467744708061218,
+      "learning_rate": 9.085181517780272e-06,
+      "loss": 0.7418,
+      "step": 149
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.1456820964813232,
+      "learning_rate": 9.069851081458242e-06,
+      "loss": 0.5051,
+      "step": 150
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.8263956308364868,
+      "learning_rate": 9.054406418375443e-06,
+      "loss": 0.7456,
+      "step": 151
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6378977298736572,
+      "learning_rate": 9.038847962010595e-06,
+      "loss": 0.6425,
+      "step": 152
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.9762052893638611,
+      "learning_rate": 9.023176149036204e-06,
+      "loss": 0.7058,
+      "step": 153
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.8176211714744568,
+      "learning_rate": 9.007391419306308e-06,
+      "loss": 0.8694,
+      "step": 154
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.6775219440460205,
+      "learning_rate": 8.991494215844133e-06,
+      "loss": 0.6892,
+      "step": 155
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 1.118199348449707,
+      "learning_rate": 8.975484984829651e-06,
+      "loss": 0.8759,
+      "step": 156
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.7018398642539978,
+      "learning_rate": 8.959364175587068e-06,
+      "loss": 0.6773,
+      "step": 157
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6770821809768677,
+      "learning_rate": 8.94313224057221e-06,
+      "loss": 0.7726,
+      "step": 158
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.8408511877059937,
+      "learning_rate": 8.926789635359817e-06,
+      "loss": 0.6043,
+      "step": 159
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.7826766967773438,
+      "learning_rate": 8.910336818630766e-06,
+      "loss": 0.7796,
+      "step": 160
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.7298358678817749,
+      "learning_rate": 8.893774252159186e-06,
+      "loss": 0.6702,
+      "step": 161
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.8671301007270813,
+      "learning_rate": 8.877102400799515e-06,
+      "loss": 0.6406,
+      "step": 162
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.720834493637085,
+      "learning_rate": 8.86032173247344e-06,
+      "loss": 0.748,
+      "step": 163
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.7987313866615295,
+      "learning_rate": 8.84343271815676e-06,
+      "loss": 0.8697,
+      "step": 164
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.7665778994560242,
+      "learning_rate": 8.826435831866185e-06,
+      "loss": 0.6625,
+      "step": 165
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.6895793080329895,
+      "learning_rate": 8.80933155064601e-06,
+      "loss": 0.7735,
+      "step": 166
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.9538195133209229,
+      "learning_rate": 8.792120354554749e-06,
+      "loss": 0.6729,
+      "step": 167
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.8142169713973999,
+      "learning_rate": 8.77480272665164e-06,
+      "loss": 0.6107,
+      "step": 168
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.8024977445602417,
+      "learning_rate": 8.757379152983103e-06,
+      "loss": 0.7148,
+      "step": 169
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.7409650683403015,
+      "learning_rate": 8.739850122569092e-06,
+      "loss": 0.6056,
+      "step": 170
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.6165910959243774,
+      "learning_rate": 8.722216127389362e-06,
+      "loss": 0.6297,
+      "step": 171
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.7439899444580078,
+      "learning_rate": 8.704477662369682e-06,
+      "loss": 0.6994,
+      "step": 172
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.6972307562828064,
+      "learning_rate": 8.68663522536792e-06,
+      "loss": 0.8256,
+      "step": 173
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.6038833260536194,
+      "learning_rate": 8.668689317160086e-06,
+      "loss": 0.7476,
+      "step": 174
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.817054808139801,
+      "learning_rate": 8.650640441426275e-06,
+      "loss": 0.7969,
+      "step": 175
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.7446957230567932,
+      "learning_rate": 8.632489104736517e-06,
+      "loss": 0.7285,
+      "step": 176
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 1.1956993341445923,
+      "learning_rate": 8.614235816536582e-06,
+      "loss": 0.7024,
+      "step": 177
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.6924423575401306,
+      "learning_rate": 8.59588108913366e-06,
+      "loss": 0.6699,
+      "step": 178
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.8742955923080444,
+      "learning_rate": 8.577425437681994e-06,
+      "loss": 0.7336,
+      "step": 179
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.7388396263122559,
+      "learning_rate": 8.558869380168423e-06,
+      "loss": 0.588,
+      "step": 180
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.8500674962997437,
+      "learning_rate": 8.540213437397833e-06,
+      "loss": 0.5773,
+      "step": 181
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.8708571791648865,
+      "learning_rate": 8.521458132978553e-06,
+      "loss": 0.7042,
+      "step": 182
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.8043896555900574,
+      "learning_rate": 8.502603993307647e-06,
+      "loss": 0.6666,
+      "step": 183
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.615947961807251,
+      "learning_rate": 8.483651547556149e-06,
+      "loss": 0.7716,
+      "step": 184
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.8101812601089478,
+      "learning_rate": 8.464601327654207e-06,
+      "loss": 0.6362,
+      "step": 185
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.7290023565292358,
+      "learning_rate": 8.445453868276155e-06,
+      "loss": 0.6423,
+      "step": 186
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.7233790159225464,
+      "learning_rate": 8.426209706825502e-06,
+      "loss": 0.6329,
+      "step": 187
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7887610197067261,
+      "learning_rate": 8.406869383419854e-06,
+      "loss": 0.703,
+      "step": 188
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.7258707880973816,
+      "learning_rate": 8.387433440875759e-06,
+      "loss": 0.9264,
+      "step": 189
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.7772265076637268,
+      "learning_rate": 8.367902424693457e-06,
+      "loss": 0.894,
+      "step": 190
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7494915723800659,
+      "learning_rate": 8.348276883041584e-06,
+      "loss": 0.6773,
+      "step": 191
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.7700024843215942,
+      "learning_rate": 8.328557366741782e-06,
+      "loss": 0.6375,
+      "step": 192
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.7172104120254517,
+      "learning_rate": 8.308744429253239e-06,
+      "loss": 0.6576,
+      "step": 193
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.6948909163475037,
+      "learning_rate": 8.28883862665715e-06,
+      "loss": 0.6145,
+      "step": 194
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.8243352174758911,
+      "learning_rate": 8.268840517641123e-06,
+      "loss": 0.8129,
+      "step": 195
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6141502857208252,
+      "learning_rate": 8.248750663483487e-06,
+      "loss": 0.5691,
+      "step": 196
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.9223580360412598,
+      "learning_rate": 8.228569628037542e-06,
+      "loss": 0.7174,
+      "step": 197
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.6116068959236145,
+      "learning_rate": 8.208297977715734e-06,
+      "loss": 0.6997,
+      "step": 198
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.7027202248573303,
+      "learning_rate": 8.187936281473758e-06,
+      "loss": 0.7805,
+      "step": 199
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6105661392211914,
+      "learning_rate": 8.167485110794591e-06,
+      "loss": 0.6618,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 625,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.861399930614579e+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 sha256:1c04c96d855c79b2a2f46cfb1428bd38b5a33019677a977bebdcf73f2b657930
+size 5816