Add files using upload-large-folder tool

.gitattributes

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

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "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": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "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": "4.49.0"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026b10ef0affa65462299519643703289b4b8cc79c579232c9b9223110c536f2
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2208c35b72f3f8f2764375ecc9796e4fea86f98dff905c3273b35c8aae083d9
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9650a4ae7dcea64bf06cb6c92d048a1a851980a3334892cbf6ed724ba3081915
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055c9b32be6641701a98138336ea49e7f8e17f7df1dde94282d98c52db4224d1
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8302bbbd833243393313301f72c8957b1ec4e7a5b0f259ada245638ce5f63b3e
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e6a466ca90351058606e5f2ef0e818c7c177acaf7d152bb032f06ad16df3590
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6ff8570449c647d022df3ee56f83a5077e7071fa34a4ab60eb707cea1a4c15
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168ff26fff6bcdd720e8bc7f8eda9072307596d2c07c7f6f91f15b1db7655d29
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e90bf95967688ee67d2545497b5bc9c80b711ce97f1e494065382ab31c945be8
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fa303c3abc803ecee1bf893c5e454def7c03fc6cb4ddf5aa30d4c3c14fe1da
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f77bbc561c7a455c5a6c9400d69dd422a10fe7b0cb12ac01059186289cb79c
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2227888e679948337feeb93ee8ee92e80b6cfc95577a65243c6b7a6bf40358b
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c75cc58a34b5155be0b5eb1defeac91d2f150b2ca7b049a2586165ad211482
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44904c4e7c6bf4ad00759cb410079e6ff07c005c62085c8261d99684d1fcbb3
+size 2123397800

model.safetensors.index.json

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

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9280e4caecbe4b136a3495e2b9cca27cda6e11665f12b3b57371ec819f24562b
+size 1064

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 +1,209 @@
+{
+  "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": 23000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1573 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.875,
+  "eval_steps": 500,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03125,
+      "grad_norm": 2.2394336497968363,
+      "learning_rate": 4.99987952239832e-06,
+      "loss": 0.5298,
+      "step": 1
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 1.740164276561001,
+      "learning_rate": 4.999518101205162e-06,
+      "loss": 0.3808,
+      "step": 2
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 1.0986511897661202,
+      "learning_rate": 4.998915771255054e-06,
+      "loss": 0.4084,
+      "step": 3
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.9909665868124784,
+      "learning_rate": 4.998072590601808e-06,
+      "loss": 0.4519,
+      "step": 4
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.8707901845900359,
+      "learning_rate": 4.996988640512931e-06,
+      "loss": 0.3661,
+      "step": 5
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.8281058863167303,
+      "learning_rate": 4.99566402546179e-06,
+      "loss": 0.446,
+      "step": 6
+    },
+    {
+      "epoch": 0.21875,
+      "grad_norm": 0.6430636455930517,
+      "learning_rate": 4.99409887311754e-06,
+      "loss": 0.41,
+      "step": 7
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.6401620888566166,
+      "learning_rate": 4.992293334332821e-06,
+      "loss": 0.3417,
+      "step": 8
+    },
+    {
+      "epoch": 0.28125,
+      "grad_norm": 0.6789953401375264,
+      "learning_rate": 4.990247583129219e-06,
+      "loss": 0.3184,
+      "step": 9
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.6666322339922938,
+      "learning_rate": 4.987961816680493e-06,
+      "loss": 0.3705,
+      "step": 10
+    },
+    {
+      "epoch": 0.34375,
+      "grad_norm": 0.605694167260075,
+      "learning_rate": 4.985436255293571e-06,
+      "loss": 0.4175,
+      "step": 11
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.5636874361093738,
+      "learning_rate": 4.982671142387316e-06,
+      "loss": 0.3418,
+      "step": 12
+    },
+    {
+      "epoch": 0.40625,
+      "grad_norm": 0.5383819643599538,
+      "learning_rate": 4.979666744469065e-06,
+      "loss": 0.3598,
+      "step": 13
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 0.5149272148576994,
+      "learning_rate": 4.976423351108943e-06,
+      "loss": 0.3488,
+      "step": 14
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.6707806575261855,
+      "learning_rate": 4.972941274911953e-06,
+      "loss": 0.3219,
+      "step": 15
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5334614805882701,
+      "learning_rate": 4.9692208514878445e-06,
+      "loss": 0.3084,
+      "step": 16
+    },
+    {
+      "epoch": 0.53125,
+      "grad_norm": 0.4618784605737609,
+      "learning_rate": 4.965262439418772e-06,
+      "loss": 0.2874,
+      "step": 17
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 0.5721238012337726,
+      "learning_rate": 4.961066420224729e-06,
+      "loss": 0.344,
+      "step": 18
+    },
+    {
+      "epoch": 0.59375,
+      "grad_norm": 0.4165484302490015,
+      "learning_rate": 4.95663319832678e-06,
+      "loss": 0.2634,
+      "step": 19
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.5820109920395683,
+      "learning_rate": 4.9519632010080765e-06,
+      "loss": 0.3757,
+      "step": 20
+    },
+    {
+      "epoch": 0.65625,
+      "grad_norm": 0.6700687637578895,
+      "learning_rate": 4.947056878372681e-06,
+      "loss": 0.3269,
+      "step": 21
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 0.6924817738571202,
+      "learning_rate": 4.941914703302181e-06,
+      "loss": 0.3455,
+      "step": 22
+    },
+    {
+      "epoch": 0.71875,
+      "grad_norm": 0.6710140492879704,
+      "learning_rate": 4.9365371714101125e-06,
+      "loss": 0.3484,
+      "step": 23
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.4799672671377543,
+      "learning_rate": 4.930924800994192e-06,
+      "loss": 0.2684,
+      "step": 24
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.5055935562066771,
+      "learning_rate": 4.925078132986361e-06,
+      "loss": 0.3241,
+      "step": 25
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 0.4813125247659047,
+      "learning_rate": 4.91899773090065e-06,
+      "loss": 0.3423,
+      "step": 26
+    },
+    {
+      "epoch": 0.84375,
+      "grad_norm": 0.5560310753021765,
+      "learning_rate": 4.912684180778869e-06,
+      "loss": 0.3657,
+      "step": 27
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.48171901776229475,
+      "learning_rate": 4.906138091134118e-06,
+      "loss": 0.3216,
+      "step": 28
+    },
+    {
+      "epoch": 0.90625,
+      "grad_norm": 0.42369283722005974,
+      "learning_rate": 4.899360092892144e-06,
+      "loss": 0.3163,
+      "step": 29
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.524728101631975,
+      "learning_rate": 4.8923508393305224e-06,
+      "loss": 0.3408,
+      "step": 30
+    },
+    {
+      "epoch": 0.96875,
+      "grad_norm": 0.4063805418469225,
+      "learning_rate": 4.885111006015702e-06,
+      "loss": 0.2803,
+      "step": 31
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.44407841545113647,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 0.296,
+      "step": 32
+    },
+    {
+      "epoch": 1.03125,
+      "grad_norm": 0.4423143989195224,
+      "learning_rate": 4.869942413443777e-06,
+      "loss": 0.3118,
+      "step": 33
+    },
+    {
+      "epoch": 1.0625,
+      "grad_norm": 0.46073261979647195,
+      "learning_rate": 4.862015116167195e-06,
+      "loss": 0.3178,
+      "step": 34
+    },
+    {
+      "epoch": 1.09375,
+      "grad_norm": 0.4688369735828424,
+      "learning_rate": 4.8538601629575525e-06,
+      "loss": 0.2897,
+      "step": 35
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.4284697832466092,
+      "learning_rate": 4.845478339806211e-06,
+      "loss": 0.285,
+      "step": 36
+    },
+    {
+      "epoch": 1.15625,
+      "grad_norm": 0.39817183870518563,
+      "learning_rate": 4.836870454570732e-06,
+      "loss": 0.2738,
+      "step": 37
+    },
+    {
+      "epoch": 1.1875,
+      "grad_norm": 0.5010876930979401,
+      "learning_rate": 4.828037336897009e-06,
+      "loss": 0.2747,
+      "step": 38
+    },
+    {
+      "epoch": 1.21875,
+      "grad_norm": 0.42604579765626815,
+      "learning_rate": 4.8189798381393105e-06,
+      "loss": 0.3109,
+      "step": 39
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.41157008816282203,
+      "learning_rate": 4.809698831278217e-06,
+      "loss": 0.2681,
+      "step": 40
+    },
+    {
+      "epoch": 1.28125,
+      "grad_norm": 0.36744775321321765,
+      "learning_rate": 4.800195210836488e-06,
+      "loss": 0.2469,
+      "step": 41
+    },
+    {
+      "epoch": 1.3125,
+      "grad_norm": 0.38947720902026384,
+      "learning_rate": 4.79046989279284e-06,
+      "loss": 0.2324,
+      "step": 42
+    },
+    {
+      "epoch": 1.34375,
+      "grad_norm": 0.42310974390248596,
+      "learning_rate": 4.780523814493669e-06,
+      "loss": 0.2654,
+      "step": 43
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.39744333584037517,
+      "learning_rate": 4.770357934562704e-06,
+      "loss": 0.2411,
+      "step": 44
+    },
+    {
+      "epoch": 1.40625,
+      "grad_norm": 0.44279738030538934,
+      "learning_rate": 4.759973232808609e-06,
+      "loss": 0.281,
+      "step": 45
+    },
+    {
+      "epoch": 1.4375,
+      "grad_norm": 0.3914368627497957,
+      "learning_rate": 4.7493707101305545e-06,
+      "loss": 0.2423,
+      "step": 46
+    },
+    {
+      "epoch": 1.46875,
+      "grad_norm": 0.4319870734337111,
+      "learning_rate": 4.738551388421743e-06,
+      "loss": 0.2334,
+      "step": 47
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.4251155801268978,
+      "learning_rate": 4.72751631047092e-06,
+      "loss": 0.2688,
+      "step": 48
+    },
+    {
+      "epoch": 1.53125,
+      "grad_norm": 0.41965617223551865,
+      "learning_rate": 4.716266539861867e-06,
+      "loss": 0.288,
+      "step": 49
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 0.3891378701055059,
+      "learning_rate": 4.704803160870888e-06,
+      "loss": 0.2818,
+      "step": 50
+    },
+    {
+      "epoch": 1.59375,
+      "grad_norm": 0.3888595960872248,
+      "learning_rate": 4.693127278362311e-06,
+      "loss": 0.2354,
+      "step": 51
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.4016619714514077,
+      "learning_rate": 4.681240017681994e-06,
+      "loss": 0.2562,
+      "step": 52
+    },
+    {
+      "epoch": 1.65625,
+      "grad_norm": 0.5121471946559132,
+      "learning_rate": 4.669142524548861e-06,
+      "loss": 0.2476,
+      "step": 53
+    },
+    {
+      "epoch": 1.6875,
+      "grad_norm": 0.4633480737331638,
+      "learning_rate": 4.65683596494448e-06,
+      "loss": 0.2681,
+      "step": 54
+    },
+    {
+      "epoch": 1.71875,
+      "grad_norm": 0.4013796153387593,
+      "learning_rate": 4.644321525000681e-06,
+      "loss": 0.2424,
+      "step": 55
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.9238636643109417,
+      "learning_rate": 4.631600410885231e-06,
+      "loss": 0.2235,
+      "step": 56
+    },
+    {
+      "epoch": 1.78125,
+      "grad_norm": 0.5108292775568174,
+      "learning_rate": 4.618673848685586e-06,
+      "loss": 0.2656,
+      "step": 57
+    },
+    {
+      "epoch": 1.8125,
+      "grad_norm": 0.4083379408887923,
+      "learning_rate": 4.605543084290716e-06,
+      "loss": 0.2451,
+      "step": 58
+    },
+    {
+      "epoch": 1.84375,
+      "grad_norm": 0.43539867698309076,
+      "learning_rate": 4.592209383271023e-06,
+      "loss": 0.2735,
+      "step": 59
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.3638102430175956,
+      "learning_rate": 4.578674030756364e-06,
+      "loss": 0.2441,
+      "step": 60
+    },
+    {
+      "epoch": 1.90625,
+      "grad_norm": 0.45746025113403654,
+      "learning_rate": 4.564938331312183e-06,
+      "loss": 0.2711,
+      "step": 61
+    },
+    {
+      "epoch": 1.9375,
+      "grad_norm": 0.3828705185761755,
+      "learning_rate": 4.551003608813784e-06,
+      "loss": 0.2689,
+      "step": 62
+    },
+    {
+      "epoch": 1.96875,
+      "grad_norm": 0.7723878548213299,
+      "learning_rate": 4.536871206318724e-06,
+      "loss": 0.2646,
+      "step": 63
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4119966458262975,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.2581,
+      "step": 64
+    },
+    {
+      "epoch": 2.03125,
+      "grad_norm": 0.34415181939181905,
+      "learning_rate": 4.508018828701613e-06,
+      "loss": 0.2112,
+      "step": 65
+    },
+    {
+      "epoch": 2.0625,
+      "grad_norm": 0.4091277177709592,
+      "learning_rate": 4.493301634431768e-06,
+      "loss": 0.2325,
+      "step": 66
+    },
+    {
+      "epoch": 2.09375,
+      "grad_norm": 0.3166321134445452,
+      "learning_rate": 4.4783923216016515e-06,
+      "loss": 0.1796,
+      "step": 67
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.3482541384421591,
+      "learning_rate": 4.463292327201862e-06,
+      "loss": 0.2126,
+      "step": 68
+    },
+    {
+      "epoch": 2.15625,
+      "grad_norm": 0.3628052220535386,
+      "learning_rate": 4.448003106601292e-06,
+      "loss": 0.1823,
+      "step": 69
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 0.4035919217048586,
+      "learning_rate": 4.432526133406843e-06,
+      "loss": 0.1895,
+      "step": 70
+    },
+    {
+      "epoch": 2.21875,
+      "grad_norm": 0.5165078405158365,
+      "learning_rate": 4.416862899321404e-06,
+      "loss": 0.2387,
+      "step": 71
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.4429767351171174,
+      "learning_rate": 4.401014914000078e-06,
+      "loss": 0.2372,
+      "step": 72
+    },
+    {
+      "epoch": 2.28125,
+      "grad_norm": 0.542713434284815,
+      "learning_rate": 4.384983704904674e-06,
+      "loss": 0.2047,
+      "step": 73
+    },
+    {
+      "epoch": 2.3125,
+      "grad_norm": 0.7431203126973699,
+      "learning_rate": 4.368770817156493e-06,
+      "loss": 0.1969,
+      "step": 74
+    },
+    {
+      "epoch": 2.34375,
+      "grad_norm": 0.42767478217888505,
+      "learning_rate": 4.352377813387398e-06,
+      "loss": 0.2212,
+      "step": 75
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.4186278371414481,
+      "learning_rate": 4.335806273589214e-06,
+      "loss": 0.2352,
+      "step": 76
+    },
+    {
+      "epoch": 2.40625,
+      "grad_norm": 0.3673245542378708,
+      "learning_rate": 4.319057794961437e-06,
+      "loss": 0.1682,
+      "step": 77
+    },
+    {
+      "epoch": 2.4375,
+      "grad_norm": 0.4202626242980855,
+      "learning_rate": 4.3021339917572975e-06,
+      "loss": 0.2005,
+      "step": 78
+    },
+    {
+      "epoch": 2.46875,
+      "grad_norm": 0.34611554658143534,
+      "learning_rate": 4.285036495128171e-06,
+      "loss": 0.1638,
+      "step": 79
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.4130916633006024,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.262,
+      "step": 80
+    },
+    {
+      "epoch": 2.53125,
+      "grad_norm": 0.3825732844394237,
+      "learning_rate": 4.250327029746309e-06,
+      "loss": 0.2107,
+      "step": 81
+    },
+    {
+      "epoch": 2.5625,
+      "grad_norm": 0.5304304939674155,
+      "learning_rate": 4.2327184063640905e-06,
+      "loss": 0.1824,
+      "step": 82
+    },
+    {
+      "epoch": 2.59375,
+      "grad_norm": 0.3721970337050105,
+      "learning_rate": 4.2149427799754825e-06,
+      "loss": 0.2022,
+      "step": 83
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.48998201951971176,
+      "learning_rate": 4.197001863832355e-06,
+      "loss": 0.2099,
+      "step": 84
+    },
+    {
+      "epoch": 2.65625,
+      "grad_norm": 0.3708581437412575,
+      "learning_rate": 4.178897387117547e-06,
+      "loss": 0.1799,
+      "step": 85
+    },
+    {
+      "epoch": 2.6875,
+      "grad_norm": 0.42462919503218965,
+      "learning_rate": 4.160631094778205e-06,
+      "loss": 0.2037,
+      "step": 86
+    },
+    {
+      "epoch": 2.71875,
+      "grad_norm": 0.37645767525187157,
+      "learning_rate": 4.142204747357604e-06,
+      "loss": 0.1803,
+      "step": 87
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.4093657454888683,
+      "learning_rate": 4.123620120825459e-06,
+      "loss": 0.2133,
+      "step": 88
+    },
+    {
+      "epoch": 2.78125,
+      "grad_norm": 0.47695453907098256,
+      "learning_rate": 4.104879006406758e-06,
+      "loss": 0.1889,
+      "step": 89
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 0.3945066509872425,
+      "learning_rate": 4.085983210409114e-06,
+      "loss": 0.2112,
+      "step": 90
+    },
+    {
+      "epoch": 2.84375,
+      "grad_norm": 0.37745415339235017,
+      "learning_rate": 4.0669345540486745e-06,
+      "loss": 0.2007,
+      "step": 91
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.4607310898061174,
+      "learning_rate": 4.047734873274586e-06,
+      "loss": 0.2257,
+      "step": 92
+    },
+    {
+      "epoch": 2.90625,
+      "grad_norm": 0.420700842549809,
+      "learning_rate": 4.0283860185920415e-06,
+      "loss": 0.2006,
+      "step": 93
+    },
+    {
+      "epoch": 2.9375,
+      "grad_norm": 0.3875612398615003,
+      "learning_rate": 4.0088898548839285e-06,
+      "loss": 0.193,
+      "step": 94
+    },
+    {
+      "epoch": 2.96875,
+      "grad_norm": 0.45432379635664477,
+      "learning_rate": 3.989248261231084e-06,
+      "loss": 0.2082,
+      "step": 95
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.354128163601168,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 0.1765,
+      "step": 96
+    },
+    {
+      "epoch": 3.03125,
+      "grad_norm": 0.39612766482379574,
+      "learning_rate": 3.949536370316285e-06,
+      "loss": 0.1506,
+      "step": 97
+    },
+    {
+      "epoch": 3.0625,
+      "grad_norm": 0.3300469180047683,
+      "learning_rate": 3.929469900569031e-06,
+      "loss": 0.1848,
+      "step": 98
+    },
+    {
+      "epoch": 3.09375,
+      "grad_norm": 0.38840461255151465,
+      "learning_rate": 3.909265655537542e-06,
+      "loss": 0.1676,
+      "step": 99
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 0.3285461189075836,
+      "learning_rate": 3.888925582549006e-06,
+      "loss": 0.1365,
+      "step": 100
+    },
+    {
+      "epoch": 3.15625,
+      "grad_norm": 0.5170838354530907,
+      "learning_rate": 3.868451642021992e-06,
+      "loss": 0.1765,
+      "step": 101
+    },
+    {
+      "epoch": 3.1875,
+      "grad_norm": 0.4041772657051392,
+      "learning_rate": 3.847845807277501e-06,
+      "loss": 0.1419,
+      "step": 102
+    },
+    {
+      "epoch": 3.21875,
+      "grad_norm": 0.5302128110684335,
+      "learning_rate": 3.827110064348774e-06,
+      "loss": 0.1666,
+      "step": 103
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.4660451553905167,
+      "learning_rate": 3.806246411789872e-06,
+      "loss": 0.1377,
+      "step": 104
+    },
+    {
+      "epoch": 3.28125,
+      "grad_norm": 0.4002753774676628,
+      "learning_rate": 3.785256860483054e-06,
+      "loss": 0.1306,
+      "step": 105
+    },
+    {
+      "epoch": 3.3125,
+      "grad_norm": 0.45635455587621315,
+      "learning_rate": 3.764143433444962e-06,
+      "loss": 0.163,
+      "step": 106
+    },
+    {
+      "epoch": 3.34375,
+      "grad_norm": 0.37905637459156455,
+      "learning_rate": 3.7429081656316363e-06,
+      "loss": 0.1406,
+      "step": 107
+    },
+    {
+      "epoch": 3.375,
+      "grad_norm": 0.36546010104015225,
+      "learning_rate": 3.721553103742388e-06,
+      "loss": 0.1511,
+      "step": 108
+    },
+    {
+      "epoch": 3.40625,
+      "grad_norm": 0.4594286270535004,
+      "learning_rate": 3.7000803060225284e-06,
+      "loss": 0.1305,
+      "step": 109
+    },
+    {
+      "epoch": 3.4375,
+      "grad_norm": 0.40651366787823534,
+      "learning_rate": 3.6784918420649952e-06,
+      "loss": 0.1529,
+      "step": 110
+    },
+    {
+      "epoch": 3.46875,
+      "grad_norm": 0.5440044921202766,
+      "learning_rate": 3.656789792610876e-06,
+      "loss": 0.1513,
+      "step": 111
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.4821069073470484,
+      "learning_rate": 3.634976249348867e-06,
+      "loss": 0.1716,
+      "step": 112
+    },
+    {
+      "epoch": 3.53125,
+      "grad_norm": 0.6498760363990219,
+      "learning_rate": 3.613053314713671e-06,
+      "loss": 0.1533,
+      "step": 113
+    },
+    {
+      "epoch": 3.5625,
+      "grad_norm": 0.4250290395428464,
+      "learning_rate": 3.591023101683355e-06,
+      "loss": 0.1767,
+      "step": 114
+    },
+    {
+      "epoch": 3.59375,
+      "grad_norm": 0.38939149597815365,
+      "learning_rate": 3.5688877335757055e-06,
+      "loss": 0.1659,
+      "step": 115
+    },
+    {
+      "epoch": 3.625,
+      "grad_norm": 0.43948642504162183,
+      "learning_rate": 3.5466493438435707e-06,
+      "loss": 0.1462,
+      "step": 116
+    },
+    {
+      "epoch": 3.65625,
+      "grad_norm": 0.4903824604348807,
+      "learning_rate": 3.524310075869239e-06,
+      "loss": 0.1491,
+      "step": 117
+    },
+    {
+      "epoch": 3.6875,
+      "grad_norm": 0.4657546939224425,
+      "learning_rate": 3.5018720827578523e-06,
+      "loss": 0.1566,
+      "step": 118
+    },
+    {
+      "epoch": 3.71875,
+      "grad_norm": 0.4756253089988171,
+      "learning_rate": 3.47933752712989e-06,
+      "loss": 0.1326,
+      "step": 119
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.6850972684126732,
+      "learning_rate": 3.4567085809127247e-06,
+      "loss": 0.1401,
+      "step": 120
+    },
+    {
+      "epoch": 3.78125,
+      "grad_norm": 0.39364163187698803,
+      "learning_rate": 3.433987425131291e-06,
+      "loss": 0.1705,
+      "step": 121
+    },
+    {
+      "epoch": 3.8125,
+      "grad_norm": 0.8491154102878922,
+      "learning_rate": 3.4111762496978753e-06,
+      "loss": 0.1598,
+      "step": 122
+    },
+    {
+      "epoch": 3.84375,
+      "grad_norm": 0.3779648803711784,
+      "learning_rate": 3.3882772532010405e-06,
+      "loss": 0.1659,
+      "step": 123
+    },
+    {
+      "epoch": 3.875,
+      "grad_norm": 0.390463984917053,
+      "learning_rate": 3.3652926426937327e-06,
+      "loss": 0.1497,
+      "step": 124
+    },
+    {
+      "epoch": 3.90625,
+      "grad_norm": 0.39280155164389263,
+      "learning_rate": 3.3422246334805504e-06,
+      "loss": 0.1517,
+      "step": 125
+    },
+    {
+      "epoch": 3.9375,
+      "grad_norm": 0.3755269188701736,
+      "learning_rate": 3.3190754489042343e-06,
+      "loss": 0.1392,
+      "step": 126
+    },
+    {
+      "epoch": 3.96875,
+      "grad_norm": 0.3557534616990425,
+      "learning_rate": 3.2958473201313744e-06,
+      "loss": 0.1732,
+      "step": 127
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.452729068394037,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.1304,
+      "step": 128
+    },
+    {
+      "epoch": 4.03125,
+      "grad_norm": 0.45305681837419015,
+      "learning_rate": 3.2491631924906418e-06,
+      "loss": 0.1207,
+      "step": 129
+    },
+    {
+      "epoch": 4.0625,
+      "grad_norm": 0.4022759878801443,
+      "learning_rate": 3.225711693136156e-06,
+      "loss": 0.1049,
+      "step": 130
+    },
+    {
+      "epoch": 4.09375,
+      "grad_norm": 0.4288103397748838,
+      "learning_rate": 3.2021902481782308e-06,
+      "loss": 0.1088,
+      "step": 131
+    },
+    {
+      "epoch": 4.125,
+      "grad_norm": 0.37543034416997534,
+      "learning_rate": 3.1786011246626858e-06,
+      "loss": 0.1151,
+      "step": 132
+    },
+    {
+      "epoch": 4.15625,
+      "grad_norm": 0.4949259404136992,
+      "learning_rate": 3.1549465961583436e-06,
+      "loss": 0.1342,
+      "step": 133
+    },
+    {
+      "epoch": 4.1875,
+      "grad_norm": 0.5089415457753128,
+      "learning_rate": 3.131228942537895e-06,
+      "loss": 0.1011,
+      "step": 134
+    },
+    {
+      "epoch": 4.21875,
+      "grad_norm": 0.4458186626680738,
+      "learning_rate": 3.10745044975816e-06,
+      "loss": 0.1244,
+      "step": 135
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.470168570137067,
+      "learning_rate": 3.0836134096397642e-06,
+      "loss": 0.1305,
+      "step": 136
+    },
+    {
+      "epoch": 4.28125,
+      "grad_norm": 0.3665739173342618,
+      "learning_rate": 3.0597201196462467e-06,
+      "loss": 0.0973,
+      "step": 137
+    },
+    {
+      "epoch": 4.3125,
+      "grad_norm": 0.34951065919116203,
+      "learning_rate": 3.035772882662627e-06,
+      "loss": 0.1087,
+      "step": 138
+    },
+    {
+      "epoch": 4.34375,
+      "grad_norm": 0.39558552323317786,
+      "learning_rate": 3.0117740067734496e-06,
+      "loss": 0.1227,
+      "step": 139
+    },
+    {
+      "epoch": 4.375,
+      "grad_norm": 0.38865489898187766,
+      "learning_rate": 2.9877258050403214e-06,
+      "loss": 0.1117,
+      "step": 140
+    },
+    {
+      "epoch": 4.40625,
+      "grad_norm": 0.3661757548934599,
+      "learning_rate": 2.9636305952789775e-06,
+      "loss": 0.1104,
+      "step": 141
+    },
+    {
+      "epoch": 4.4375,
+      "grad_norm": 0.3637528683552047,
+      "learning_rate": 2.939490699835887e-06,
+      "loss": 0.1285,
+      "step": 142
+    },
+    {
+      "epoch": 4.46875,
+      "grad_norm": 0.49782839811269636,
+      "learning_rate": 2.915308445364414e-06,
+      "loss": 0.1151,
+      "step": 143
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.4510644225332588,
+      "learning_rate": 2.8910861626005774e-06,
+      "loss": 0.0908,
+      "step": 144
+    },
+    {
+      "epoch": 4.53125,
+      "grad_norm": 0.42204924035077557,
+      "learning_rate": 2.8668261861384045e-06,
+      "loss": 0.1103,
+      "step": 145
+    },
+    {
+      "epoch": 4.5625,
+      "grad_norm": 0.4092078682229767,
+      "learning_rate": 2.8425308542049208e-06,
+      "loss": 0.102,
+      "step": 146
+    },
+    {
+      "epoch": 4.59375,
+      "grad_norm": 0.4377811123358122,
+      "learning_rate": 2.8182025084347835e-06,
+      "loss": 0.1019,
+      "step": 147
+    },
+    {
+      "epoch": 4.625,
+      "grad_norm": 0.40430035219965416,
+      "learning_rate": 2.7938434936445946e-06,
+      "loss": 0.1215,
+      "step": 148
+    },
+    {
+      "epoch": 4.65625,
+      "grad_norm": 0.41793422453606693,
+      "learning_rate": 2.7694561576068983e-06,
+      "loss": 0.0995,
+      "step": 149
+    },
+    {
+      "epoch": 4.6875,
+      "grad_norm": 0.4094291043597894,
+      "learning_rate": 2.7450428508239024e-06,
+      "loss": 0.1157,
+      "step": 150
+    },
+    {
+      "epoch": 4.71875,
+      "grad_norm": 0.46702497217402006,
+      "learning_rate": 2.7206059263009245e-06,
+      "loss": 0.1035,
+      "step": 151
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 0.4265298988852787,
+      "learning_rate": 2.696147739319613e-06,
+      "loss": 0.1161,
+      "step": 152
+    },
+    {
+      "epoch": 4.78125,
+      "grad_norm": 0.39560706745129126,
+      "learning_rate": 2.671670647210934e-06,
+      "loss": 0.0934,
+      "step": 153
+    },
+    {
+      "epoch": 4.8125,
+      "grad_norm": 0.45750798547925925,
+      "learning_rate": 2.6471770091279725e-06,
+      "loss": 0.1198,
+      "step": 154
+    },
+    {
+      "epoch": 4.84375,
+      "grad_norm": 0.4135822172423458,
+      "learning_rate": 2.6226691858185454e-06,
+      "loss": 0.0993,
+      "step": 155
+    },
+    {
+      "epoch": 4.875,
+      "grad_norm": 0.3881797560141128,
+      "learning_rate": 2.5981495393976718e-06,
+      "loss": 0.1148,
+      "step": 156
+    },
+    {
+      "epoch": 4.90625,
+      "grad_norm": 0.42849991504445745,
+      "learning_rate": 2.5736204331199087e-06,
+      "loss": 0.1103,
+      "step": 157
+    },
+    {
+      "epoch": 4.9375,
+      "grad_norm": 0.40236517866109184,
+      "learning_rate": 2.5490842311515706e-06,
+      "loss": 0.1342,
+      "step": 158
+    },
+    {
+      "epoch": 4.96875,
+      "grad_norm": 0.43341169220800396,
+      "learning_rate": 2.5245432983428746e-06,
+      "loss": 0.1157,
+      "step": 159
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.34584354992172495,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0859,
+      "step": 160
+    },
+    {
+      "epoch": 5.03125,
+      "grad_norm": 0.4143904072465387,
+      "learning_rate": 2.4754567016571263e-06,
+      "loss": 0.0754,
+      "step": 161
+    },
+    {
+      "epoch": 5.0625,
+      "grad_norm": 0.3919204276591812,
+      "learning_rate": 2.45091576884843e-06,
+      "loss": 0.0779,
+      "step": 162
+    },
+    {
+      "epoch": 5.09375,
+      "grad_norm": 0.36564792990584655,
+      "learning_rate": 2.426379566880092e-06,
+      "loss": 0.0846,
+      "step": 163
+    },
+    {
+      "epoch": 5.125,
+      "grad_norm": 0.529521055415997,
+      "learning_rate": 2.4018504606023295e-06,
+      "loss": 0.0844,
+      "step": 164
+    },
+    {
+      "epoch": 5.15625,
+      "grad_norm": 0.431451074610151,
+      "learning_rate": 2.377330814181455e-06,
+      "loss": 0.0786,
+      "step": 165
+    },
+    {
+      "epoch": 5.1875,
+      "grad_norm": 0.7684174507597721,
+      "learning_rate": 2.3528229908720275e-06,
+      "loss": 0.0844,
+      "step": 166
+    },
+    {
+      "epoch": 5.21875,
+      "grad_norm": 0.44474891738541866,
+      "learning_rate": 2.3283293527890662e-06,
+      "loss": 0.0815,
+      "step": 167
+    },
+    {
+      "epoch": 5.25,
+      "grad_norm": 0.43540222849729127,
+      "learning_rate": 2.3038522606803882e-06,
+      "loss": 0.0772,
+      "step": 168
+    },
+    {
+      "epoch": 5.28125,
+      "grad_norm": 0.372712057692664,
+      "learning_rate": 2.2793940736990768e-06,
+      "loss": 0.0805,
+      "step": 169
+    },
+    {
+      "epoch": 5.3125,
+      "grad_norm": 0.4448901557779222,
+      "learning_rate": 2.2549571491760985e-06,
+      "loss": 0.0761,
+      "step": 170
+    },
+    {
+      "epoch": 5.34375,
+      "grad_norm": 0.3863228908718508,
+      "learning_rate": 2.2305438423931017e-06,
+      "loss": 0.0644,
+      "step": 171
+    },
+    {
+      "epoch": 5.375,
+      "grad_norm": 0.39062361374554433,
+      "learning_rate": 2.2061565063554063e-06,
+      "loss": 0.0684,
+      "step": 172
+    },
+    {
+      "epoch": 5.40625,
+      "grad_norm": 0.40361146609711873,
+      "learning_rate": 2.1817974915652174e-06,
+      "loss": 0.0814,
+      "step": 173
+    },
+    {
+      "epoch": 5.4375,
+      "grad_norm": 0.43921414806678843,
+      "learning_rate": 2.1574691457950805e-06,
+      "loss": 0.0822,
+      "step": 174
+    },
+    {
+      "epoch": 5.46875,
+      "grad_norm": 0.44480838697237224,
+      "learning_rate": 2.133173813861596e-06,
+      "loss": 0.0866,
+      "step": 175
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.42051348090512747,
+      "learning_rate": 2.1089138373994226e-06,
+      "loss": 0.071,
+      "step": 176
+    },
+    {
+      "epoch": 5.53125,
+      "grad_norm": 0.3983612848583139,
+      "learning_rate": 2.084691554635587e-06,
+      "loss": 0.0838,
+      "step": 177
+    },
+    {
+      "epoch": 5.5625,
+      "grad_norm": 0.4911594568608088,
+      "learning_rate": 2.0605093001641138e-06,
+      "loss": 0.0809,
+      "step": 178
+    },
+    {
+      "epoch": 5.59375,
+      "grad_norm": 0.41760316408981346,
+      "learning_rate": 2.036369404721023e-06,
+      "loss": 0.0691,
+      "step": 179
+    },
+    {
+      "epoch": 5.625,
+      "grad_norm": 0.47280852373511856,
+      "learning_rate": 2.01227419495968e-06,
+      "loss": 0.0811,
+      "step": 180
+    },
+    {
+      "epoch": 5.65625,
+      "grad_norm": 0.39986092972135084,
+      "learning_rate": 1.9882259932265513e-06,
+      "loss": 0.0717,
+      "step": 181
+    },
+    {
+      "epoch": 5.6875,
+      "grad_norm": 0.40904716656384654,
+      "learning_rate": 1.964227117337374e-06,
+      "loss": 0.0982,
+      "step": 182
+    },
+    {
+      "epoch": 5.71875,
+      "grad_norm": 0.3996787578567523,
+      "learning_rate": 1.940279880353754e-06,
+      "loss": 0.0883,
+      "step": 183
+    },
+    {
+      "epoch": 5.75,
+      "grad_norm": 0.5625574567447781,
+      "learning_rate": 1.9163865903602374e-06,
+      "loss": 0.0871,
+      "step": 184
+    },
+    {
+      "epoch": 5.78125,
+      "grad_norm": 0.386964669236494,
+      "learning_rate": 1.8925495502418407e-06,
+      "loss": 0.0635,
+      "step": 185
+    },
+    {
+      "epoch": 5.8125,
+      "grad_norm": 0.40351438572982834,
+      "learning_rate": 1.8687710574621051e-06,
+      "loss": 0.0681,
+      "step": 186
+    },
+    {
+      "epoch": 5.84375,
+      "grad_norm": 0.4228827894009542,
+      "learning_rate": 1.8450534038416568e-06,
+      "loss": 0.0659,
+      "step": 187
+    },
+    {
+      "epoch": 5.875,
+      "grad_norm": 0.3712122399780234,
+      "learning_rate": 1.8213988753373147e-06,
+      "loss": 0.0671,
+      "step": 188
+    },
+    {
+      "epoch": 5.90625,
+      "grad_norm": 0.43867000444079457,
+      "learning_rate": 1.7978097518217705e-06,
+      "loss": 0.0731,
+      "step": 189
+    },
+    {
+      "epoch": 5.9375,
+      "grad_norm": 0.6740106312876709,
+      "learning_rate": 1.7742883068638447e-06,
+      "loss": 0.0714,
+      "step": 190
+    },
+    {
+      "epoch": 5.96875,
+      "grad_norm": 0.4228466835838196,
+      "learning_rate": 1.7508368075093584e-06,
+      "loss": 0.0819,
+      "step": 191
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.3563426355737081,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.0548,
+      "step": 192
+    },
+    {
+      "epoch": 6.03125,
+      "grad_norm": 0.4910211429767737,
+      "learning_rate": 1.7041526798686258e-06,
+      "loss": 0.0864,
+      "step": 193
+    },
+    {
+      "epoch": 6.0625,
+      "grad_norm": 0.5006110615030569,
+      "learning_rate": 1.6809245510957667e-06,
+      "loss": 0.0654,
+      "step": 194
+    },
+    {
+      "epoch": 6.09375,
+      "grad_norm": 0.3502324650817108,
+      "learning_rate": 1.6577753665194502e-06,
+      "loss": 0.0658,
+      "step": 195
+    },
+    {
+      "epoch": 6.125,
+      "grad_norm": 0.5999695575705828,
+      "learning_rate": 1.634707357306267e-06,
+      "loss": 0.0451,
+      "step": 196
+    },
+    {
+      "epoch": 6.15625,
+      "grad_norm": 0.4785665941529937,
+      "learning_rate": 1.6117227467989605e-06,
+      "loss": 0.0546,
+      "step": 197
+    },
+    {
+      "epoch": 6.1875,
+      "grad_norm": 0.5095514480098127,
+      "learning_rate": 1.588823750302126e-06,
+      "loss": 0.0624,
+      "step": 198
+    },
+    {
+      "epoch": 6.21875,
+      "grad_norm": 0.47258708232050645,
+      "learning_rate": 1.5660125748687094e-06,
+      "loss": 0.0568,
+      "step": 199
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.4103151403943041,
+      "learning_rate": 1.5432914190872757e-06,
+      "loss": 0.0547,
+      "step": 200
+    },
+    {
+      "epoch": 6.28125,
+      "grad_norm": 0.40314839324043505,
+      "learning_rate": 1.5206624728701103e-06,
+      "loss": 0.0568,
+      "step": 201
+    },
+    {
+      "epoch": 6.3125,
+      "grad_norm": 0.43007255326114996,
+      "learning_rate": 1.4981279172421481e-06,
+      "loss": 0.0608,
+      "step": 202
+    },
+    {
+      "epoch": 6.34375,
+      "grad_norm": 0.35567074942204735,
+      "learning_rate": 1.4756899241307615e-06,
+      "loss": 0.0439,
+      "step": 203
+    },
+    {
+      "epoch": 6.375,
+      "grad_norm": 0.4211372568538995,
+      "learning_rate": 1.4533506561564305e-06,
+      "loss": 0.0567,
+      "step": 204
+    },
+    {
+      "epoch": 6.40625,
+      "grad_norm": 0.3696720423651608,
+      "learning_rate": 1.4311122664242955e-06,
+      "loss": 0.0568,
+      "step": 205
+    },
+    {
+      "epoch": 6.4375,
+      "grad_norm": 0.32678314141276715,
+      "learning_rate": 1.4089768983166445e-06,
+      "loss": 0.0541,
+      "step": 206
+    },
+    {
+      "epoch": 6.46875,
+      "grad_norm": 0.5124523798563752,
+      "learning_rate": 1.38694668528633e-06,
+      "loss": 0.0647,
+      "step": 207
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 0.4908724555671687,
+      "learning_rate": 1.3650237506511333e-06,
+      "loss": 0.0512,
+      "step": 208
+    },
+    {
+      "epoch": 6.53125,
+      "grad_norm": 0.45698703902133064,
+      "learning_rate": 1.343210207389125e-06,
+      "loss": 0.0471,
+      "step": 209
+    },
+    {
+      "epoch": 6.5625,
+      "grad_norm": 2.0837321278798675,
+      "learning_rate": 1.3215081579350058e-06,
+      "loss": 0.0401,
+      "step": 210
+    },
+    {
+      "epoch": 6.59375,
+      "grad_norm": 0.44377226616386084,
+      "learning_rate": 1.2999196939774722e-06,
+      "loss": 0.0533,
+      "step": 211
+    },
+    {
+      "epoch": 6.625,
+      "grad_norm": 0.4148622551357974,
+      "learning_rate": 1.2784468962576136e-06,
+      "loss": 0.043,
+      "step": 212
+    },
+    {
+      "epoch": 6.65625,
+      "grad_norm": 0.4525924081364697,
+      "learning_rate": 1.2570918343683636e-06,
+      "loss": 0.05,
+      "step": 213
+    },
+    {
+      "epoch": 6.6875,
+      "grad_norm": 0.48264486607444934,
+      "learning_rate": 1.235856566555039e-06,
+      "loss": 0.071,
+      "step": 214
+    },
+    {
+      "epoch": 6.71875,
+      "grad_norm": 0.41420210019322223,
+      "learning_rate": 1.214743139516946e-06,
+      "loss": 0.0372,
+      "step": 215
+    },
+    {
+      "epoch": 6.75,
+      "grad_norm": 0.4521124791878032,
+      "learning_rate": 1.193753588210128e-06,
+      "loss": 0.0473,
+      "step": 216
+    },
+    {
+      "epoch": 6.78125,
+      "grad_norm": 0.4592162304890299,
+      "learning_rate": 1.1728899356512265e-06,
+      "loss": 0.0552,
+      "step": 217
+    },
+    {
+      "epoch": 6.8125,
+      "grad_norm": 0.4136741288075781,
+      "learning_rate": 1.1521541927224994e-06,
+      "loss": 0.0431,
+      "step": 218
+    },
+    {
+      "epoch": 6.84375,
+      "grad_norm": 0.40334351070651664,
+      "learning_rate": 1.1315483579780095e-06,
+      "loss": 0.044,
+      "step": 219
+    },
+    {
+      "epoch": 6.875,
+      "grad_norm": 0.38291505271607423,
+      "learning_rate": 1.1110744174509952e-06,
+      "loss": 0.0452,
+      "step": 220
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 320,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 220852321255424.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d90aa83713724549f5e304bba980c43933f8390284acad860147c2a71ca11134
+size 7608