upload files

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen2.5-14B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "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": "4.44.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb81c3c7b10b574586379209deca4b255df5a8f19d6a5fb540b93bc3a7091793
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfd3cd2dea14161e06563d53319a3ccd9600fd1273f17f85931a8d45420fdaf
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:134b4db2a8449809641cc3dd92363c1e23b9441a4b6b5a220c7f76601b949308
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e713f9debf4e19983342b9bae27f36487553b534984b1122c13943fbfa4e98c
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624056bf666c70de2a0f836325caa6c6ac751787b26b4c8c87d58a045ef83632
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6edc60498b9f1e16c21d9665c8c6e534066be68fa01172a82fb66f2435b28879
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2359 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9986799924570997,
+  "eval_steps": 500,
+  "global_step": 331,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003017160098057703,
+      "grad_norm": 20.078946749628592,
+      "learning_rate": 0.0,
+      "loss": 1.4468,
+      "step": 1
+    },
+    {
+      "epoch": 0.006034320196115406,
+      "grad_norm": 4.878738050586557,
+      "learning_rate": 5e-06,
+      "loss": 1.1585,
+      "step": 2
+    },
+    {
+      "epoch": 0.00905148029417311,
+      "grad_norm": 5.517865422306177,
+      "learning_rate": 7.924812503605782e-06,
+      "loss": 1.1812,
+      "step": 3
+    },
+    {
+      "epoch": 0.012068640392230812,
+      "grad_norm": 2.1032343536449445,
+      "learning_rate": 1e-05,
+      "loss": 1.1021,
+      "step": 4
+    },
+    {
+      "epoch": 0.015085800490288516,
+      "grad_norm": 2.592635550230835,
+      "learning_rate": 1e-05,
+      "loss": 1.1066,
+      "step": 5
+    },
+    {
+      "epoch": 0.01810296058834622,
+      "grad_norm": 8.062413826195554,
+      "learning_rate": 1e-05,
+      "loss": 1.0541,
+      "step": 6
+    },
+    {
+      "epoch": 0.021120120686403922,
+      "grad_norm": 470.52936338944204,
+      "learning_rate": 1e-05,
+      "loss": 1.1385,
+      "step": 7
+    },
+    {
+      "epoch": 0.024137280784461625,
+      "grad_norm": 5.56198780429065,
+      "learning_rate": 1e-05,
+      "loss": 1.141,
+      "step": 8
+    },
+    {
+      "epoch": 0.02715444088251933,
+      "grad_norm": 3.1646497668353124,
+      "learning_rate": 1e-05,
+      "loss": 1.0944,
+      "step": 9
+    },
+    {
+      "epoch": 0.030171600980577033,
+      "grad_norm": 2.0038474699480413,
+      "learning_rate": 1e-05,
+      "loss": 1.0951,
+      "step": 10
+    },
+    {
+      "epoch": 0.033188761078634735,
+      "grad_norm": 1.4888187403163304,
+      "learning_rate": 1e-05,
+      "loss": 1.0766,
+      "step": 11
+    },
+    {
+      "epoch": 0.03620592117669244,
+      "grad_norm": 1.7152815980179157,
+      "learning_rate": 1e-05,
+      "loss": 1.0706,
+      "step": 12
+    },
+    {
+      "epoch": 0.03922308127475014,
+      "grad_norm": 1.4300762542819367,
+      "learning_rate": 1e-05,
+      "loss": 1.0547,
+      "step": 13
+    },
+    {
+      "epoch": 0.042240241372807845,
+      "grad_norm": 1.4526317270279436,
+      "learning_rate": 1e-05,
+      "loss": 1.0137,
+      "step": 14
+    },
+    {
+      "epoch": 0.04525740147086555,
+      "grad_norm": 1.2974541466019103,
+      "learning_rate": 1e-05,
+      "loss": 1.0501,
+      "step": 15
+    },
+    {
+      "epoch": 0.04827456156892325,
+      "grad_norm": 1.2017850759065756,
+      "learning_rate": 1e-05,
+      "loss": 1.0339,
+      "step": 16
+    },
+    {
+      "epoch": 0.051291721666980955,
+      "grad_norm": 1.1650312606754425,
+      "learning_rate": 1e-05,
+      "loss": 1.0284,
+      "step": 17
+    },
+    {
+      "epoch": 0.05430888176503866,
+      "grad_norm": 1.218417579737997,
+      "learning_rate": 1e-05,
+      "loss": 1.0101,
+      "step": 18
+    },
+    {
+      "epoch": 0.05732604186309636,
+      "grad_norm": 1.1592394623790696,
+      "learning_rate": 1e-05,
+      "loss": 1.006,
+      "step": 19
+    },
+    {
+      "epoch": 0.060343201961154065,
+      "grad_norm": 1.2412789400669013,
+      "learning_rate": 1e-05,
+      "loss": 1.0081,
+      "step": 20
+    },
+    {
+      "epoch": 0.06336036205921176,
+      "grad_norm": 1.1656784199257328,
+      "learning_rate": 1e-05,
+      "loss": 1.0274,
+      "step": 21
+    },
+    {
+      "epoch": 0.06637752215726947,
+      "grad_norm": 1.156112593546092,
+      "learning_rate": 1e-05,
+      "loss": 1.0349,
+      "step": 22
+    },
+    {
+      "epoch": 0.06939468225532718,
+      "grad_norm": 1.1792204176695948,
+      "learning_rate": 1e-05,
+      "loss": 0.9633,
+      "step": 23
+    },
+    {
+      "epoch": 0.07241184235338488,
+      "grad_norm": 1.1670774133822364,
+      "learning_rate": 1e-05,
+      "loss": 0.9912,
+      "step": 24
+    },
+    {
+      "epoch": 0.07542900245144257,
+      "grad_norm": 1.1275491972747138,
+      "learning_rate": 1e-05,
+      "loss": 0.9776,
+      "step": 25
+    },
+    {
+      "epoch": 0.07844616254950028,
+      "grad_norm": 1.1802067276415016,
+      "learning_rate": 1e-05,
+      "loss": 1.0141,
+      "step": 26
+    },
+    {
+      "epoch": 0.08146332264755798,
+      "grad_norm": 1.228045833889261,
+      "learning_rate": 1e-05,
+      "loss": 0.9936,
+      "step": 27
+    },
+    {
+      "epoch": 0.08448048274561569,
+      "grad_norm": 1.2484185459639683,
+      "learning_rate": 1e-05,
+      "loss": 0.9932,
+      "step": 28
+    },
+    {
+      "epoch": 0.0874976428436734,
+      "grad_norm": 1.2339564712822966,
+      "learning_rate": 1e-05,
+      "loss": 0.95,
+      "step": 29
+    },
+    {
+      "epoch": 0.0905148029417311,
+      "grad_norm": 1.211784252377512,
+      "learning_rate": 1e-05,
+      "loss": 0.9711,
+      "step": 30
+    },
+    {
+      "epoch": 0.09353196303978879,
+      "grad_norm": 1.1575974315931057,
+      "learning_rate": 1e-05,
+      "loss": 0.9771,
+      "step": 31
+    },
+    {
+      "epoch": 0.0965491231378465,
+      "grad_norm": 1.2117409563580097,
+      "learning_rate": 1e-05,
+      "loss": 0.9495,
+      "step": 32
+    },
+    {
+      "epoch": 0.0995662832359042,
+      "grad_norm": 1.109114323976095,
+      "learning_rate": 1e-05,
+      "loss": 0.9782,
+      "step": 33
+    },
+    {
+      "epoch": 0.10258344333396191,
+      "grad_norm": 1.0945987254678533,
+      "learning_rate": 1e-05,
+      "loss": 0.9621,
+      "step": 34
+    },
+    {
+      "epoch": 0.10560060343201962,
+      "grad_norm": 1.1441153052598225,
+      "learning_rate": 1e-05,
+      "loss": 0.976,
+      "step": 35
+    },
+    {
+      "epoch": 0.10861776353007732,
+      "grad_norm": 1.0701754107374204,
+      "learning_rate": 1e-05,
+      "loss": 0.9364,
+      "step": 36
+    },
+    {
+      "epoch": 0.11163492362813501,
+      "grad_norm": 1.0982624299638388,
+      "learning_rate": 1e-05,
+      "loss": 0.9873,
+      "step": 37
+    },
+    {
+      "epoch": 0.11465208372619272,
+      "grad_norm": 1.1658342852048704,
+      "learning_rate": 1e-05,
+      "loss": 0.9727,
+      "step": 38
+    },
+    {
+      "epoch": 0.11766924382425042,
+      "grad_norm": 1.140425640145812,
+      "learning_rate": 1e-05,
+      "loss": 0.962,
+      "step": 39
+    },
+    {
+      "epoch": 0.12068640392230813,
+      "grad_norm": 1.2113716827018828,
+      "learning_rate": 1e-05,
+      "loss": 0.9794,
+      "step": 40
+    },
+    {
+      "epoch": 0.12370356402036584,
+      "grad_norm": 1.0811873110464318,
+      "learning_rate": 1e-05,
+      "loss": 0.9614,
+      "step": 41
+    },
+    {
+      "epoch": 0.12672072411842353,
+      "grad_norm": 1.1319113211223166,
+      "learning_rate": 1e-05,
+      "loss": 0.9588,
+      "step": 42
+    },
+    {
+      "epoch": 0.12973788421648125,
+      "grad_norm": 1.0450336690045927,
+      "learning_rate": 1e-05,
+      "loss": 0.951,
+      "step": 43
+    },
+    {
+      "epoch": 0.13275504431453894,
+      "grad_norm": 1.0888061493358059,
+      "learning_rate": 1e-05,
+      "loss": 0.9631,
+      "step": 44
+    },
+    {
+      "epoch": 0.13577220441259663,
+      "grad_norm": 1.092452045324181,
+      "learning_rate": 1e-05,
+      "loss": 0.9648,
+      "step": 45
+    },
+    {
+      "epoch": 0.13878936451065435,
+      "grad_norm": 0.9926260475544896,
+      "learning_rate": 1e-05,
+      "loss": 0.9274,
+      "step": 46
+    },
+    {
+      "epoch": 0.14180652460871204,
+      "grad_norm": 1.1102540887315238,
+      "learning_rate": 1e-05,
+      "loss": 0.919,
+      "step": 47
+    },
+    {
+      "epoch": 0.14482368470676976,
+      "grad_norm": 1.0120307941022935,
+      "learning_rate": 1e-05,
+      "loss": 0.9526,
+      "step": 48
+    },
+    {
+      "epoch": 0.14784084480482745,
+      "grad_norm": 1.0962499453405279,
+      "learning_rate": 1e-05,
+      "loss": 0.9078,
+      "step": 49
+    },
+    {
+      "epoch": 0.15085800490288515,
+      "grad_norm": 1.1837778452202325,
+      "learning_rate": 1e-05,
+      "loss": 0.9376,
+      "step": 50
+    },
+    {
+      "epoch": 0.15387516500094287,
+      "grad_norm": 1.064164454110782,
+      "learning_rate": 1e-05,
+      "loss": 0.9128,
+      "step": 51
+    },
+    {
+      "epoch": 0.15689232509900056,
+      "grad_norm": 1.1508638128558335,
+      "learning_rate": 1e-05,
+      "loss": 0.9533,
+      "step": 52
+    },
+    {
+      "epoch": 0.15990948519705828,
+      "grad_norm": 1.1609288313516257,
+      "learning_rate": 1e-05,
+      "loss": 0.9551,
+      "step": 53
+    },
+    {
+      "epoch": 0.16292664529511597,
+      "grad_norm": 1.0596156545796473,
+      "learning_rate": 1e-05,
+      "loss": 0.9083,
+      "step": 54
+    },
+    {
+      "epoch": 0.1659438053931737,
+      "grad_norm": 1.0399099372944773,
+      "learning_rate": 1e-05,
+      "loss": 0.95,
+      "step": 55
+    },
+    {
+      "epoch": 0.16896096549123138,
+      "grad_norm": 1.0914115337494106,
+      "learning_rate": 1e-05,
+      "loss": 0.9159,
+      "step": 56
+    },
+    {
+      "epoch": 0.17197812558928907,
+      "grad_norm": 1.1208151691589456,
+      "learning_rate": 1e-05,
+      "loss": 0.9404,
+      "step": 57
+    },
+    {
+      "epoch": 0.1749952856873468,
+      "grad_norm": 1.1380068007034254,
+      "learning_rate": 1e-05,
+      "loss": 0.9248,
+      "step": 58
+    },
+    {
+      "epoch": 0.17801244578540448,
+      "grad_norm": 1.1725768888546018,
+      "learning_rate": 1e-05,
+      "loss": 0.9013,
+      "step": 59
+    },
+    {
+      "epoch": 0.1810296058834622,
+      "grad_norm": 1.0230578555799743,
+      "learning_rate": 1e-05,
+      "loss": 0.9184,
+      "step": 60
+    },
+    {
+      "epoch": 0.1840467659815199,
+      "grad_norm": 1.1965830709717151,
+      "learning_rate": 1e-05,
+      "loss": 0.9636,
+      "step": 61
+    },
+    {
+      "epoch": 0.18706392607957759,
+      "grad_norm": 1.0854955199511183,
+      "learning_rate": 1e-05,
+      "loss": 0.9149,
+      "step": 62
+    },
+    {
+      "epoch": 0.1900810861776353,
+      "grad_norm": 1.0776069945953626,
+      "learning_rate": 1e-05,
+      "loss": 0.895,
+      "step": 63
+    },
+    {
+      "epoch": 0.193098246275693,
+      "grad_norm": 1.0925276020001646,
+      "learning_rate": 1e-05,
+      "loss": 0.9017,
+      "step": 64
+    },
+    {
+      "epoch": 0.19611540637375072,
+      "grad_norm": 1.051729020151003,
+      "learning_rate": 1e-05,
+      "loss": 0.9168,
+      "step": 65
+    },
+    {
+      "epoch": 0.1991325664718084,
+      "grad_norm": 1.1276428621962828,
+      "learning_rate": 1e-05,
+      "loss": 0.9359,
+      "step": 66
+    },
+    {
+      "epoch": 0.2021497265698661,
+      "grad_norm": 1.039214095313065,
+      "learning_rate": 1e-05,
+      "loss": 0.9458,
+      "step": 67
+    },
+    {
+      "epoch": 0.20516688666792382,
+      "grad_norm": 1.108230624792472,
+      "learning_rate": 1e-05,
+      "loss": 0.9012,
+      "step": 68
+    },
+    {
+      "epoch": 0.2081840467659815,
+      "grad_norm": 1.0659907986207233,
+      "learning_rate": 1e-05,
+      "loss": 0.932,
+      "step": 69
+    },
+    {
+      "epoch": 0.21120120686403923,
+      "grad_norm": 1.1484942212933387,
+      "learning_rate": 1e-05,
+      "loss": 0.9212,
+      "step": 70
+    },
+    {
+      "epoch": 0.21421836696209692,
+      "grad_norm": 1.0080008398377343,
+      "learning_rate": 1e-05,
+      "loss": 0.9335,
+      "step": 71
+    },
+    {
+      "epoch": 0.21723552706015464,
+      "grad_norm": 1.099906576331005,
+      "learning_rate": 1e-05,
+      "loss": 0.9478,
+      "step": 72
+    },
+    {
+      "epoch": 0.22025268715821233,
+      "grad_norm": 1.002361667650721,
+      "learning_rate": 1e-05,
+      "loss": 0.9215,
+      "step": 73
+    },
+    {
+      "epoch": 0.22326984725627003,
+      "grad_norm": 1.0106913848906898,
+      "learning_rate": 1e-05,
+      "loss": 0.9103,
+      "step": 74
+    },
+    {
+      "epoch": 0.22628700735432775,
+      "grad_norm": 1.031802831727699,
+      "learning_rate": 1e-05,
+      "loss": 0.9591,
+      "step": 75
+    },
+    {
+      "epoch": 0.22930416745238544,
+      "grad_norm": 1.091719276309555,
+      "learning_rate": 1e-05,
+      "loss": 0.9431,
+      "step": 76
+    },
+    {
+      "epoch": 0.23232132755044316,
+      "grad_norm": 1.0393979811839362,
+      "learning_rate": 1e-05,
+      "loss": 0.8945,
+      "step": 77
+    },
+    {
+      "epoch": 0.23533848764850085,
+      "grad_norm": 1.1503832361551256,
+      "learning_rate": 1e-05,
+      "loss": 0.9163,
+      "step": 78
+    },
+    {
+      "epoch": 0.23835564774655854,
+      "grad_norm": 1.1141284366563844,
+      "learning_rate": 1e-05,
+      "loss": 0.9093,
+      "step": 79
+    },
+    {
+      "epoch": 0.24137280784461626,
+      "grad_norm": 1.0708909622724119,
+      "learning_rate": 1e-05,
+      "loss": 0.9359,
+      "step": 80
+    },
+    {
+      "epoch": 0.24438996794267395,
+      "grad_norm": 1.0342956680966762,
+      "learning_rate": 1e-05,
+      "loss": 0.9066,
+      "step": 81
+    },
+    {
+      "epoch": 0.24740712804073167,
+      "grad_norm": 1.041231965271414,
+      "learning_rate": 1e-05,
+      "loss": 0.9042,
+      "step": 82
+    },
+    {
+      "epoch": 0.25042428813878936,
+      "grad_norm": 1.0891891643003724,
+      "learning_rate": 1e-05,
+      "loss": 0.9157,
+      "step": 83
+    },
+    {
+      "epoch": 0.25344144823684706,
+      "grad_norm": 0.9463606441668,
+      "learning_rate": 1e-05,
+      "loss": 0.8652,
+      "step": 84
+    },
+    {
+      "epoch": 0.25645860833490475,
+      "grad_norm": 0.9943090136893116,
+      "learning_rate": 1e-05,
+      "loss": 0.9138,
+      "step": 85
+    },
+    {
+      "epoch": 0.2594757684329625,
+      "grad_norm": 1.0622250754003486,
+      "learning_rate": 1e-05,
+      "loss": 0.9029,
+      "step": 86
+    },
+    {
+      "epoch": 0.2624929285310202,
+      "grad_norm": 1.0190810445181397,
+      "learning_rate": 1e-05,
+      "loss": 0.8701,
+      "step": 87
+    },
+    {
+      "epoch": 0.2655100886290779,
+      "grad_norm": 1.0471126343927182,
+      "learning_rate": 1e-05,
+      "loss": 0.9173,
+      "step": 88
+    },
+    {
+      "epoch": 0.26852724872713557,
+      "grad_norm": 1.094441431551059,
+      "learning_rate": 1e-05,
+      "loss": 0.9539,
+      "step": 89
+    },
+    {
+      "epoch": 0.27154440882519326,
+      "grad_norm": 1.02572224910356,
+      "learning_rate": 1e-05,
+      "loss": 0.9036,
+      "step": 90
+    },
+    {
+      "epoch": 0.274561568923251,
+      "grad_norm": 1.0647463602381582,
+      "learning_rate": 1e-05,
+      "loss": 0.8895,
+      "step": 91
+    },
+    {
+      "epoch": 0.2775787290213087,
+      "grad_norm": 1.0867418650830927,
+      "learning_rate": 1e-05,
+      "loss": 0.8903,
+      "step": 92
+    },
+    {
+      "epoch": 0.2805958891193664,
+      "grad_norm": 1.0448439572661483,
+      "learning_rate": 1e-05,
+      "loss": 0.9013,
+      "step": 93
+    },
+    {
+      "epoch": 0.2836130492174241,
+      "grad_norm": 1.0782737190600102,
+      "learning_rate": 1e-05,
+      "loss": 0.9088,
+      "step": 94
+    },
+    {
+      "epoch": 0.2866302093154818,
+      "grad_norm": 1.0853475076773287,
+      "learning_rate": 1e-05,
+      "loss": 0.876,
+      "step": 95
+    },
+    {
+      "epoch": 0.2896473694135395,
+      "grad_norm": 1.0978686199970553,
+      "learning_rate": 1e-05,
+      "loss": 0.9286,
+      "step": 96
+    },
+    {
+      "epoch": 0.2926645295115972,
+      "grad_norm": 1.0673815458666747,
+      "learning_rate": 1e-05,
+      "loss": 0.8973,
+      "step": 97
+    },
+    {
+      "epoch": 0.2956816896096549,
+      "grad_norm": 1.184691172374345,
+      "learning_rate": 1e-05,
+      "loss": 0.8944,
+      "step": 98
+    },
+    {
+      "epoch": 0.2986988497077126,
+      "grad_norm": 0.9861386386631925,
+      "learning_rate": 1e-05,
+      "loss": 0.9048,
+      "step": 99
+    },
+    {
+      "epoch": 0.3017160098057703,
+      "grad_norm": 1.1329936556607971,
+      "learning_rate": 1e-05,
+      "loss": 0.9401,
+      "step": 100
+    },
+    {
+      "epoch": 0.30473316990382804,
+      "grad_norm": 0.9543730308331345,
+      "learning_rate": 1e-05,
+      "loss": 0.9149,
+      "step": 101
+    },
+    {
+      "epoch": 0.30775033000188573,
+      "grad_norm": 1.1462193660108113,
+      "learning_rate": 1e-05,
+      "loss": 0.9071,
+      "step": 102
+    },
+    {
+      "epoch": 0.3107674900999434,
+      "grad_norm": 1.0904581574091061,
+      "learning_rate": 1e-05,
+      "loss": 0.8971,
+      "step": 103
+    },
+    {
+      "epoch": 0.3137846501980011,
+      "grad_norm": 1.0495767709008346,
+      "learning_rate": 1e-05,
+      "loss": 0.919,
+      "step": 104
+    },
+    {
+      "epoch": 0.31680181029605886,
+      "grad_norm": 0.9640542155531093,
+      "learning_rate": 1e-05,
+      "loss": 0.8713,
+      "step": 105
+    },
+    {
+      "epoch": 0.31981897039411655,
+      "grad_norm": 0.9610132463708185,
+      "learning_rate": 1e-05,
+      "loss": 0.8933,
+      "step": 106
+    },
+    {
+      "epoch": 0.32283613049217424,
+      "grad_norm": 1.0843824473667214,
+      "learning_rate": 1e-05,
+      "loss": 0.9093,
+      "step": 107
+    },
+    {
+      "epoch": 0.32585329059023194,
+      "grad_norm": 0.9945425158672618,
+      "learning_rate": 1e-05,
+      "loss": 0.9071,
+      "step": 108
+    },
+    {
+      "epoch": 0.32887045068828963,
+      "grad_norm": 1.0765546524524479,
+      "learning_rate": 1e-05,
+      "loss": 0.865,
+      "step": 109
+    },
+    {
+      "epoch": 0.3318876107863474,
+      "grad_norm": 1.01041125101344,
+      "learning_rate": 1e-05,
+      "loss": 0.8907,
+      "step": 110
+    },
+    {
+      "epoch": 0.33490477088440507,
+      "grad_norm": 1.0874945222389107,
+      "learning_rate": 1e-05,
+      "loss": 0.894,
+      "step": 111
+    },
+    {
+      "epoch": 0.33792193098246276,
+      "grad_norm": 1.0493603540512813,
+      "learning_rate": 1e-05,
+      "loss": 0.9138,
+      "step": 112
+    },
+    {
+      "epoch": 0.34093909108052045,
+      "grad_norm": 1.0124123297722831,
+      "learning_rate": 1e-05,
+      "loss": 0.9149,
+      "step": 113
+    },
+    {
+      "epoch": 0.34395625117857814,
+      "grad_norm": 1.0531088139319633,
+      "learning_rate": 1e-05,
+      "loss": 0.8856,
+      "step": 114
+    },
+    {
+      "epoch": 0.3469734112766359,
+      "grad_norm": 0.9763912034026013,
+      "learning_rate": 1e-05,
+      "loss": 0.905,
+      "step": 115
+    },
+    {
+      "epoch": 0.3499905713746936,
+      "grad_norm": 1.0488345908663115,
+      "learning_rate": 1e-05,
+      "loss": 0.8907,
+      "step": 116
+    },
+    {
+      "epoch": 0.3530077314727513,
+      "grad_norm": 1.0142709732139472,
+      "learning_rate": 1e-05,
+      "loss": 0.8983,
+      "step": 117
+    },
+    {
+      "epoch": 0.35602489157080897,
+      "grad_norm": 0.9983943961658387,
+      "learning_rate": 1e-05,
+      "loss": 0.8881,
+      "step": 118
+    },
+    {
+      "epoch": 0.35904205166886666,
+      "grad_norm": 1.0281018778884328,
+      "learning_rate": 1e-05,
+      "loss": 0.8989,
+      "step": 119
+    },
+    {
+      "epoch": 0.3620592117669244,
+      "grad_norm": 1.0050409064254446,
+      "learning_rate": 1e-05,
+      "loss": 0.9113,
+      "step": 120
+    },
+    {
+      "epoch": 0.3650763718649821,
+      "grad_norm": 1.0317911761320575,
+      "learning_rate": 1e-05,
+      "loss": 0.8926,
+      "step": 121
+    },
+    {
+      "epoch": 0.3680935319630398,
+      "grad_norm": 1.0867071456016715,
+      "learning_rate": 1e-05,
+      "loss": 0.8698,
+      "step": 122
+    },
+    {
+      "epoch": 0.3711106920610975,
+      "grad_norm": 1.0792050089286005,
+      "learning_rate": 1e-05,
+      "loss": 0.8385,
+      "step": 123
+    },
+    {
+      "epoch": 0.37412785215915517,
+      "grad_norm": 1.136911850598409,
+      "learning_rate": 1e-05,
+      "loss": 0.884,
+      "step": 124
+    },
+    {
+      "epoch": 0.3771450122572129,
+      "grad_norm": 0.9468447682708495,
+      "learning_rate": 1e-05,
+      "loss": 0.9048,
+      "step": 125
+    },
+    {
+      "epoch": 0.3801621723552706,
+      "grad_norm": 0.99640914665336,
+      "learning_rate": 1e-05,
+      "loss": 0.9092,
+      "step": 126
+    },
+    {
+      "epoch": 0.3831793324533283,
+      "grad_norm": 1.0035906051414294,
+      "learning_rate": 1e-05,
+      "loss": 0.8612,
+      "step": 127
+    },
+    {
+      "epoch": 0.386196492551386,
+      "grad_norm": 1.0443720188110175,
+      "learning_rate": 1e-05,
+      "loss": 0.898,
+      "step": 128
+    },
+    {
+      "epoch": 0.3892136526494437,
+      "grad_norm": 1.0019284346638992,
+      "learning_rate": 1e-05,
+      "loss": 0.9194,
+      "step": 129
+    },
+    {
+      "epoch": 0.39223081274750143,
+      "grad_norm": 0.9947835482545767,
+      "learning_rate": 1e-05,
+      "loss": 0.8823,
+      "step": 130
+    },
+    {
+      "epoch": 0.3952479728455591,
+      "grad_norm": 1.117124665050851,
+      "learning_rate": 1e-05,
+      "loss": 0.8698,
+      "step": 131
+    },
+    {
+      "epoch": 0.3982651329436168,
+      "grad_norm": 1.0902265836998275,
+      "learning_rate": 1e-05,
+      "loss": 0.9015,
+      "step": 132
+    },
+    {
+      "epoch": 0.4012822930416745,
+      "grad_norm": 0.9890942371356929,
+      "learning_rate": 1e-05,
+      "loss": 0.8702,
+      "step": 133
+    },
+    {
+      "epoch": 0.4042994531397322,
+      "grad_norm": 1.079316692788872,
+      "learning_rate": 1e-05,
+      "loss": 0.9274,
+      "step": 134
+    },
+    {
+      "epoch": 0.40731661323778995,
+      "grad_norm": 1.0507683546070807,
+      "learning_rate": 1e-05,
+      "loss": 0.8548,
+      "step": 135
+    },
+    {
+      "epoch": 0.41033377333584764,
+      "grad_norm": 1.1173910988640408,
+      "learning_rate": 1e-05,
+      "loss": 0.8663,
+      "step": 136
+    },
+    {
+      "epoch": 0.41335093343390533,
+      "grad_norm": 1.073210708775559,
+      "learning_rate": 1e-05,
+      "loss": 0.8612,
+      "step": 137
+    },
+    {
+      "epoch": 0.416368093531963,
+      "grad_norm": 1.0396491185269086,
+      "learning_rate": 1e-05,
+      "loss": 0.8994,
+      "step": 138
+    },
+    {
+      "epoch": 0.4193852536300207,
+      "grad_norm": 1.1500475629157627,
+      "learning_rate": 1e-05,
+      "loss": 0.8525,
+      "step": 139
+    },
+    {
+      "epoch": 0.42240241372807846,
+      "grad_norm": 1.2168830597788158,
+      "learning_rate": 1e-05,
+      "loss": 0.9374,
+      "step": 140
+    },
+    {
+      "epoch": 0.42541957382613615,
+      "grad_norm": 0.9553833702288597,
+      "learning_rate": 1e-05,
+      "loss": 0.9103,
+      "step": 141
+    },
+    {
+      "epoch": 0.42843673392419385,
+      "grad_norm": 0.9850371340573859,
+      "learning_rate": 1e-05,
+      "loss": 0.8806,
+      "step": 142
+    },
+    {
+      "epoch": 0.43145389402225154,
+      "grad_norm": 1.1473904156348889,
+      "learning_rate": 1e-05,
+      "loss": 0.8773,
+      "step": 143
+    },
+    {
+      "epoch": 0.4344710541203093,
+      "grad_norm": 1.160071820812732,
+      "learning_rate": 1e-05,
+      "loss": 0.8672,
+      "step": 144
+    },
+    {
+      "epoch": 0.437488214218367,
+      "grad_norm": 1.0914396615807336,
+      "learning_rate": 1e-05,
+      "loss": 0.8916,
+      "step": 145
+    },
+    {
+      "epoch": 0.44050537431642467,
+      "grad_norm": 0.9961823995771022,
+      "learning_rate": 1e-05,
+      "loss": 0.8801,
+      "step": 146
+    },
+    {
+      "epoch": 0.44352253441448236,
+      "grad_norm": 1.1627229625741373,
+      "learning_rate": 1e-05,
+      "loss": 0.8486,
+      "step": 147
+    },
+    {
+      "epoch": 0.44653969451254005,
+      "grad_norm": 1.088993191172265,
+      "learning_rate": 1e-05,
+      "loss": 0.8541,
+      "step": 148
+    },
+    {
+      "epoch": 0.4495568546105978,
+      "grad_norm": 0.9925318555430557,
+      "learning_rate": 1e-05,
+      "loss": 0.8823,
+      "step": 149
+    },
+    {
+      "epoch": 0.4525740147086555,
+      "grad_norm": 1.080125550684176,
+      "learning_rate": 1e-05,
+      "loss": 0.8916,
+      "step": 150
+    },
+    {
+      "epoch": 0.4555911748067132,
+      "grad_norm": 1.0335542992312043,
+      "learning_rate": 1e-05,
+      "loss": 0.8523,
+      "step": 151
+    },
+    {
+      "epoch": 0.4586083349047709,
+      "grad_norm": 1.1905484694931652,
+      "learning_rate": 1e-05,
+      "loss": 0.8861,
+      "step": 152
+    },
+    {
+      "epoch": 0.46162549500282857,
+      "grad_norm": 1.0739628080299815,
+      "learning_rate": 1e-05,
+      "loss": 0.8335,
+      "step": 153
+    },
+    {
+      "epoch": 0.4646426551008863,
+      "grad_norm": 1.0040085132370382,
+      "learning_rate": 1e-05,
+      "loss": 0.867,
+      "step": 154
+    },
+    {
+      "epoch": 0.467659815198944,
+      "grad_norm": 1.056602846699296,
+      "learning_rate": 1e-05,
+      "loss": 0.8579,
+      "step": 155
+    },
+    {
+      "epoch": 0.4706769752970017,
+      "grad_norm": 0.9891380470884372,
+      "learning_rate": 1e-05,
+      "loss": 0.8454,
+      "step": 156
+    },
+    {
+      "epoch": 0.4736941353950594,
+      "grad_norm": 0.9790395676599171,
+      "learning_rate": 1e-05,
+      "loss": 0.896,
+      "step": 157
+    },
+    {
+      "epoch": 0.4767112954931171,
+      "grad_norm": 1.027120791419062,
+      "learning_rate": 1e-05,
+      "loss": 0.924,
+      "step": 158
+    },
+    {
+      "epoch": 0.47972845559117483,
+      "grad_norm": 1.0959500600764212,
+      "learning_rate": 1e-05,
+      "loss": 0.8666,
+      "step": 159
+    },
+    {
+      "epoch": 0.4827456156892325,
+      "grad_norm": 1.0401653704511453,
+      "learning_rate": 1e-05,
+      "loss": 0.8685,
+      "step": 160
+    },
+    {
+      "epoch": 0.4857627757872902,
+      "grad_norm": 1.0428336555982345,
+      "learning_rate": 1e-05,
+      "loss": 0.8739,
+      "step": 161
+    },
+    {
+      "epoch": 0.4887799358853479,
+      "grad_norm": 1.0035589157775742,
+      "learning_rate": 1e-05,
+      "loss": 0.9231,
+      "step": 162
+    },
+    {
+      "epoch": 0.4917970959834056,
+      "grad_norm": 1.1332138472380069,
+      "learning_rate": 1e-05,
+      "loss": 0.8874,
+      "step": 163
+    },
+    {
+      "epoch": 0.49481425608146334,
+      "grad_norm": 0.9889223927200703,
+      "learning_rate": 1e-05,
+      "loss": 0.9152,
+      "step": 164
+    },
+    {
+      "epoch": 0.49783141617952104,
+      "grad_norm": 0.9903630601730351,
+      "learning_rate": 1e-05,
+      "loss": 0.8619,
+      "step": 165
+    },
+    {
+      "epoch": 0.5008485762775787,
+      "grad_norm": 0.9870755137328874,
+      "learning_rate": 1e-05,
+      "loss": 0.8652,
+      "step": 166
+    },
+    {
+      "epoch": 0.5038657363756365,
+      "grad_norm": 1.0295502212015513,
+      "learning_rate": 1e-05,
+      "loss": 0.8701,
+      "step": 167
+    },
+    {
+      "epoch": 0.5068828964736941,
+      "grad_norm": 0.9980789726799827,
+      "learning_rate": 1e-05,
+      "loss": 0.8948,
+      "step": 168
+    },
+    {
+      "epoch": 0.5099000565717519,
+      "grad_norm": 0.9895924927460445,
+      "learning_rate": 1e-05,
+      "loss": 0.8652,
+      "step": 169
+    },
+    {
+      "epoch": 0.5129172166698095,
+      "grad_norm": 0.9897691179372796,
+      "learning_rate": 1e-05,
+      "loss": 0.8872,
+      "step": 170
+    },
+    {
+      "epoch": 0.5159343767678672,
+      "grad_norm": 1.0976883085536995,
+      "learning_rate": 1e-05,
+      "loss": 0.8663,
+      "step": 171
+    },
+    {
+      "epoch": 0.518951536865925,
+      "grad_norm": 0.9855831526257474,
+      "learning_rate": 1e-05,
+      "loss": 0.8379,
+      "step": 172
+    },
+    {
+      "epoch": 0.5219686969639826,
+      "grad_norm": 1.007385512988202,
+      "learning_rate": 1e-05,
+      "loss": 0.8806,
+      "step": 173
+    },
+    {
+      "epoch": 0.5249858570620404,
+      "grad_norm": 0.9811416651561021,
+      "learning_rate": 1e-05,
+      "loss": 0.8812,
+      "step": 174
+    },
+    {
+      "epoch": 0.528003017160098,
+      "grad_norm": 1.008567949000168,
+      "learning_rate": 1e-05,
+      "loss": 0.9088,
+      "step": 175
+    },
+    {
+      "epoch": 0.5310201772581558,
+      "grad_norm": 1.0735249094278072,
+      "learning_rate": 1e-05,
+      "loss": 0.8625,
+      "step": 176
+    },
+    {
+      "epoch": 0.5340373373562135,
+      "grad_norm": 1.0099080610350626,
+      "learning_rate": 1e-05,
+      "loss": 0.8774,
+      "step": 177
+    },
+    {
+      "epoch": 0.5370544974542711,
+      "grad_norm": 0.9869119389250737,
+      "learning_rate": 1e-05,
+      "loss": 0.8602,
+      "step": 178
+    },
+    {
+      "epoch": 0.5400716575523289,
+      "grad_norm": 1.0140325571494992,
+      "learning_rate": 1e-05,
+      "loss": 0.8951,
+      "step": 179
+    },
+    {
+      "epoch": 0.5430888176503865,
+      "grad_norm": 0.9746000686910684,
+      "learning_rate": 1e-05,
+      "loss": 0.8546,
+      "step": 180
+    },
+    {
+      "epoch": 0.5461059777484443,
+      "grad_norm": 0.9912039011517177,
+      "learning_rate": 1e-05,
+      "loss": 0.8699,
+      "step": 181
+    },
+    {
+      "epoch": 0.549123137846502,
+      "grad_norm": 0.9866319014883533,
+      "learning_rate": 1e-05,
+      "loss": 0.8708,
+      "step": 182
+    },
+    {
+      "epoch": 0.5521402979445597,
+      "grad_norm": 0.9316538866319553,
+      "learning_rate": 1e-05,
+      "loss": 0.8759,
+      "step": 183
+    },
+    {
+      "epoch": 0.5551574580426174,
+      "grad_norm": 0.9917975239418116,
+      "learning_rate": 1e-05,
+      "loss": 0.8743,
+      "step": 184
+    },
+    {
+      "epoch": 0.558174618140675,
+      "grad_norm": 0.998938334137341,
+      "learning_rate": 1e-05,
+      "loss": 0.8353,
+      "step": 185
+    },
+    {
+      "epoch": 0.5611917782387328,
+      "grad_norm": 1.0536268087144185,
+      "learning_rate": 1e-05,
+      "loss": 0.8892,
+      "step": 186
+    },
+    {
+      "epoch": 0.5642089383367905,
+      "grad_norm": 1.0702585591377483,
+      "learning_rate": 1e-05,
+      "loss": 0.8459,
+      "step": 187
+    },
+    {
+      "epoch": 0.5672260984348482,
+      "grad_norm": 1.0196433385874035,
+      "learning_rate": 1e-05,
+      "loss": 0.92,
+      "step": 188
+    },
+    {
+      "epoch": 0.5702432585329059,
+      "grad_norm": 1.065268517886477,
+      "learning_rate": 1e-05,
+      "loss": 0.8497,
+      "step": 189
+    },
+    {
+      "epoch": 0.5732604186309636,
+      "grad_norm": 0.9934866856892721,
+      "learning_rate": 1e-05,
+      "loss": 0.8795,
+      "step": 190
+    },
+    {
+      "epoch": 0.5762775787290213,
+      "grad_norm": 0.982727769285356,
+      "learning_rate": 1e-05,
+      "loss": 0.9056,
+      "step": 191
+    },
+    {
+      "epoch": 0.579294738827079,
+      "grad_norm": 1.0628075311898817,
+      "learning_rate": 1e-05,
+      "loss": 0.8588,
+      "step": 192
+    },
+    {
+      "epoch": 0.5823118989251367,
+      "grad_norm": 0.9227204348296366,
+      "learning_rate": 1e-05,
+      "loss": 0.8569,
+      "step": 193
+    },
+    {
+      "epoch": 0.5853290590231944,
+      "grad_norm": 0.9899338734692382,
+      "learning_rate": 1e-05,
+      "loss": 0.8857,
+      "step": 194
+    },
+    {
+      "epoch": 0.5883462191212521,
+      "grad_norm": 1.0191415487699054,
+      "learning_rate": 1e-05,
+      "loss": 0.8959,
+      "step": 195
+    },
+    {
+      "epoch": 0.5913633792193098,
+      "grad_norm": 1.0972049175262022,
+      "learning_rate": 1e-05,
+      "loss": 0.8473,
+      "step": 196
+    },
+    {
+      "epoch": 0.5943805393173676,
+      "grad_norm": 0.9801443916922342,
+      "learning_rate": 1e-05,
+      "loss": 0.8882,
+      "step": 197
+    },
+    {
+      "epoch": 0.5973976994154252,
+      "grad_norm": 1.05420177137371,
+      "learning_rate": 1e-05,
+      "loss": 0.8617,
+      "step": 198
+    },
+    {
+      "epoch": 0.600414859513483,
+      "grad_norm": 0.9763149595538684,
+      "learning_rate": 1e-05,
+      "loss": 0.8317,
+      "step": 199
+    },
+    {
+      "epoch": 0.6034320196115406,
+      "grad_norm": 1.0142128497052438,
+      "learning_rate": 1e-05,
+      "loss": 0.8801,
+      "step": 200
+    },
+    {
+      "epoch": 0.6064491797095983,
+      "grad_norm": 1.1223250391910486,
+      "learning_rate": 1e-05,
+      "loss": 0.8651,
+      "step": 201
+    },
+    {
+      "epoch": 0.6094663398076561,
+      "grad_norm": 0.9445148128595584,
+      "learning_rate": 1e-05,
+      "loss": 0.9247,
+      "step": 202
+    },
+    {
+      "epoch": 0.6124834999057137,
+      "grad_norm": 1.0205891212652056,
+      "learning_rate": 1e-05,
+      "loss": 0.8568,
+      "step": 203
+    },
+    {
+      "epoch": 0.6155006600037715,
+      "grad_norm": 1.0132942213261507,
+      "learning_rate": 1e-05,
+      "loss": 0.8474,
+      "step": 204
+    },
+    {
+      "epoch": 0.6185178201018292,
+      "grad_norm": 1.0654107515701503,
+      "learning_rate": 1e-05,
+      "loss": 0.8436,
+      "step": 205
+    },
+    {
+      "epoch": 0.6215349801998868,
+      "grad_norm": 0.9832515183706407,
+      "learning_rate": 1e-05,
+      "loss": 0.8357,
+      "step": 206
+    },
+    {
+      "epoch": 0.6245521402979446,
+      "grad_norm": 1.0121196517905966,
+      "learning_rate": 1e-05,
+      "loss": 0.8852,
+      "step": 207
+    },
+    {
+      "epoch": 0.6275693003960022,
+      "grad_norm": 1.2152715233993958,
+      "learning_rate": 1e-05,
+      "loss": 0.8215,
+      "step": 208
+    },
+    {
+      "epoch": 0.63058646049406,
+      "grad_norm": 1.0114694608145163,
+      "learning_rate": 1e-05,
+      "loss": 0.865,
+      "step": 209
+    },
+    {
+      "epoch": 0.6336036205921177,
+      "grad_norm": 1.0466026516397904,
+      "learning_rate": 1e-05,
+      "loss": 0.8566,
+      "step": 210
+    },
+    {
+      "epoch": 0.6366207806901754,
+      "grad_norm": 0.9459705410503775,
+      "learning_rate": 1e-05,
+      "loss": 0.8327,
+      "step": 211
+    },
+    {
+      "epoch": 0.6396379407882331,
+      "grad_norm": 0.9749006528453033,
+      "learning_rate": 1e-05,
+      "loss": 0.8642,
+      "step": 212
+    },
+    {
+      "epoch": 0.6426551008862907,
+      "grad_norm": 0.9590985337067398,
+      "learning_rate": 1e-05,
+      "loss": 0.8447,
+      "step": 213
+    },
+    {
+      "epoch": 0.6456722609843485,
+      "grad_norm": 1.097321284543017,
+      "learning_rate": 1e-05,
+      "loss": 0.8272,
+      "step": 214
+    },
+    {
+      "epoch": 0.6486894210824062,
+      "grad_norm": 1.0054521678760522,
+      "learning_rate": 1e-05,
+      "loss": 0.8472,
+      "step": 215
+    },
+    {
+      "epoch": 0.6517065811804639,
+      "grad_norm": 1.0099516647809557,
+      "learning_rate": 1e-05,
+      "loss": 0.8654,
+      "step": 216
+    },
+    {
+      "epoch": 0.6547237412785216,
+      "grad_norm": 0.9567498655316358,
+      "learning_rate": 1e-05,
+      "loss": 0.8566,
+      "step": 217
+    },
+    {
+      "epoch": 0.6577409013765793,
+      "grad_norm": 0.9670178838314303,
+      "learning_rate": 1e-05,
+      "loss": 0.8356,
+      "step": 218
+    },
+    {
+      "epoch": 0.660758061474637,
+      "grad_norm": 0.9767210115729468,
+      "learning_rate": 1e-05,
+      "loss": 0.9223,
+      "step": 219
+    },
+    {
+      "epoch": 0.6637752215726948,
+      "grad_norm": 1.0035943684822244,
+      "learning_rate": 1e-05,
+      "loss": 0.8778,
+      "step": 220
+    },
+    {
+      "epoch": 0.6667923816707524,
+      "grad_norm": 0.9836721726138078,
+      "learning_rate": 1e-05,
+      "loss": 0.8601,
+      "step": 221
+    },
+    {
+      "epoch": 0.6698095417688101,
+      "grad_norm": 1.0555276758382468,
+      "learning_rate": 1e-05,
+      "loss": 0.8687,
+      "step": 222
+    },
+    {
+      "epoch": 0.6728267018668678,
+      "grad_norm": 1.0236557982823795,
+      "learning_rate": 1e-05,
+      "loss": 0.869,
+      "step": 223
+    },
+    {
+      "epoch": 0.6758438619649255,
+      "grad_norm": 1.0490641185205225,
+      "learning_rate": 1e-05,
+      "loss": 0.8513,
+      "step": 224
+    },
+    {
+      "epoch": 0.6788610220629833,
+      "grad_norm": 1.0112063959996538,
+      "learning_rate": 1e-05,
+      "loss": 0.8671,
+      "step": 225
+    },
+    {
+      "epoch": 0.6818781821610409,
+      "grad_norm": 0.9797715955787868,
+      "learning_rate": 1e-05,
+      "loss": 0.8721,
+      "step": 226
+    },
+    {
+      "epoch": 0.6848953422590986,
+      "grad_norm": 1.023163793890387,
+      "learning_rate": 1e-05,
+      "loss": 0.8238,
+      "step": 227
+    },
+    {
+      "epoch": 0.6879125023571563,
+      "grad_norm": 0.9901311938407963,
+      "learning_rate": 1e-05,
+      "loss": 0.8455,
+      "step": 228
+    },
+    {
+      "epoch": 0.690929662455214,
+      "grad_norm": 1.0333937580724437,
+      "learning_rate": 1e-05,
+      "loss": 0.8799,
+      "step": 229
+    },
+    {
+      "epoch": 0.6939468225532718,
+      "grad_norm": 0.9781251267252234,
+      "learning_rate": 1e-05,
+      "loss": 0.8558,
+      "step": 230
+    },
+    {
+      "epoch": 0.6969639826513294,
+      "grad_norm": 0.9991779679723747,
+      "learning_rate": 1e-05,
+      "loss": 0.8534,
+      "step": 231
+    },
+    {
+      "epoch": 0.6999811427493872,
+      "grad_norm": 1.0389629537546219,
+      "learning_rate": 1e-05,
+      "loss": 0.8466,
+      "step": 232
+    },
+    {
+      "epoch": 0.7029983028474448,
+      "grad_norm": 1.0204794940839597,
+      "learning_rate": 1e-05,
+      "loss": 0.832,
+      "step": 233
+    },
+    {
+      "epoch": 0.7060154629455025,
+      "grad_norm": 1.0124333073703313,
+      "learning_rate": 1e-05,
+      "loss": 0.826,
+      "step": 234
+    },
+    {
+      "epoch": 0.7090326230435603,
+      "grad_norm": 0.9469683819775043,
+      "learning_rate": 1e-05,
+      "loss": 0.8746,
+      "step": 235
+    },
+    {
+      "epoch": 0.7120497831416179,
+      "grad_norm": 0.9681088394641286,
+      "learning_rate": 1e-05,
+      "loss": 0.8777,
+      "step": 236
+    },
+    {
+      "epoch": 0.7150669432396757,
+      "grad_norm": 0.9534971580611808,
+      "learning_rate": 1e-05,
+      "loss": 0.828,
+      "step": 237
+    },
+    {
+      "epoch": 0.7180841033377333,
+      "grad_norm": 0.9231164924550516,
+      "learning_rate": 1e-05,
+      "loss": 0.8851,
+      "step": 238
+    },
+    {
+      "epoch": 0.7211012634357911,
+      "grad_norm": 0.9564412650063757,
+      "learning_rate": 1e-05,
+      "loss": 0.8407,
+      "step": 239
+    },
+    {
+      "epoch": 0.7241184235338488,
+      "grad_norm": 0.9387537660650889,
+      "learning_rate": 1e-05,
+      "loss": 0.8195,
+      "step": 240
+    },
+    {
+      "epoch": 0.7271355836319064,
+      "grad_norm": 0.984184826582449,
+      "learning_rate": 1e-05,
+      "loss": 0.8417,
+      "step": 241
+    },
+    {
+      "epoch": 0.7301527437299642,
+      "grad_norm": 0.9680344075351693,
+      "learning_rate": 1e-05,
+      "loss": 0.8679,
+      "step": 242
+    },
+    {
+      "epoch": 0.7331699038280218,
+      "grad_norm": 0.9508741001956648,
+      "learning_rate": 1e-05,
+      "loss": 0.8182,
+      "step": 243
+    },
+    {
+      "epoch": 0.7361870639260796,
+      "grad_norm": 0.9991310599384764,
+      "learning_rate": 1e-05,
+      "loss": 0.8917,
+      "step": 244
+    },
+    {
+      "epoch": 0.7392042240241373,
+      "grad_norm": 1.0472945255103463,
+      "learning_rate": 1e-05,
+      "loss": 0.9124,
+      "step": 245
+    },
+    {
+      "epoch": 0.742221384122195,
+      "grad_norm": 0.99539173598333,
+      "learning_rate": 1e-05,
+      "loss": 0.8638,
+      "step": 246
+    },
+    {
+      "epoch": 0.7452385442202527,
+      "grad_norm": 1.0251801530213278,
+      "learning_rate": 1e-05,
+      "loss": 0.8413,
+      "step": 247
+    },
+    {
+      "epoch": 0.7482557043183103,
+      "grad_norm": 1.0408585876445724,
+      "learning_rate": 1e-05,
+      "loss": 0.8381,
+      "step": 248
+    },
+    {
+      "epoch": 0.7512728644163681,
+      "grad_norm": 0.9731694388232142,
+      "learning_rate": 1e-05,
+      "loss": 0.855,
+      "step": 249
+    },
+    {
+      "epoch": 0.7542900245144258,
+      "grad_norm": 1.0030115847404013,
+      "learning_rate": 1e-05,
+      "loss": 0.8596,
+      "step": 250
+    },
+    {
+      "epoch": 0.7573071846124835,
+      "grad_norm": 0.9841974420990679,
+      "learning_rate": 1e-05,
+      "loss": 0.8742,
+      "step": 251
+    },
+    {
+      "epoch": 0.7603243447105412,
+      "grad_norm": 1.055927374179432,
+      "learning_rate": 1e-05,
+      "loss": 0.8286,
+      "step": 252
+    },
+    {
+      "epoch": 0.7633415048085989,
+      "grad_norm": 1.0037342058458762,
+      "learning_rate": 1e-05,
+      "loss": 0.8624,
+      "step": 253
+    },
+    {
+      "epoch": 0.7663586649066566,
+      "grad_norm": 0.9779177922525308,
+      "learning_rate": 1e-05,
+      "loss": 0.8224,
+      "step": 254
+    },
+    {
+      "epoch": 0.7693758250047144,
+      "grad_norm": 1.0485152455162672,
+      "learning_rate": 1e-05,
+      "loss": 0.8353,
+      "step": 255
+    },
+    {
+      "epoch": 0.772392985102772,
+      "grad_norm": 0.9427366336442022,
+      "learning_rate": 1e-05,
+      "loss": 0.859,
+      "step": 256
+    },
+    {
+      "epoch": 0.7754101452008297,
+      "grad_norm": 0.9826256006927524,
+      "learning_rate": 1e-05,
+      "loss": 0.8781,
+      "step": 257
+    },
+    {
+      "epoch": 0.7784273052988874,
+      "grad_norm": 1.097163176429486,
+      "learning_rate": 1e-05,
+      "loss": 0.8603,
+      "step": 258
+    },
+    {
+      "epoch": 0.7814444653969451,
+      "grad_norm": 1.0755684776060006,
+      "learning_rate": 1e-05,
+      "loss": 0.8803,
+      "step": 259
+    },
+    {
+      "epoch": 0.7844616254950029,
+      "grad_norm": 1.060543596503769,
+      "learning_rate": 1e-05,
+      "loss": 0.8749,
+      "step": 260
+    },
+    {
+      "epoch": 0.7874787855930605,
+      "grad_norm": 1.0054727401343206,
+      "learning_rate": 1e-05,
+      "loss": 0.8656,
+      "step": 261
+    },
+    {
+      "epoch": 0.7904959456911183,
+      "grad_norm": 1.0209085800021502,
+      "learning_rate": 1e-05,
+      "loss": 0.8821,
+      "step": 262
+    },
+    {
+      "epoch": 0.7935131057891759,
+      "grad_norm": 0.9243375424290232,
+      "learning_rate": 1e-05,
+      "loss": 0.8622,
+      "step": 263
+    },
+    {
+      "epoch": 0.7965302658872336,
+      "grad_norm": 1.0429931807106287,
+      "learning_rate": 1e-05,
+      "loss": 0.8196,
+      "step": 264
+    },
+    {
+      "epoch": 0.7995474259852914,
+      "grad_norm": 1.0354133838924724,
+      "learning_rate": 1e-05,
+      "loss": 0.8339,
+      "step": 265
+    },
+    {
+      "epoch": 0.802564586083349,
+      "grad_norm": 0.9226609889690002,
+      "learning_rate": 1e-05,
+      "loss": 0.854,
+      "step": 266
+    },
+    {
+      "epoch": 0.8055817461814068,
+      "grad_norm": 0.8608785777678977,
+      "learning_rate": 1e-05,
+      "loss": 0.8371,
+      "step": 267
+    },
+    {
+      "epoch": 0.8085989062794644,
+      "grad_norm": 1.0583845408082262,
+      "learning_rate": 1e-05,
+      "loss": 0.8158,
+      "step": 268
+    },
+    {
+      "epoch": 0.8116160663775221,
+      "grad_norm": 0.9488390352752252,
+      "learning_rate": 1e-05,
+      "loss": 0.8569,
+      "step": 269
+    },
+    {
+      "epoch": 0.8146332264755799,
+      "grad_norm": 1.040418044582926,
+      "learning_rate": 1e-05,
+      "loss": 0.847,
+      "step": 270
+    },
+    {
+      "epoch": 0.8176503865736375,
+      "grad_norm": 1.1259258576677653,
+      "learning_rate": 1e-05,
+      "loss": 0.8178,
+      "step": 271
+    },
+    {
+      "epoch": 0.8206675466716953,
+      "grad_norm": 0.9418385845633765,
+      "learning_rate": 1e-05,
+      "loss": 0.8293,
+      "step": 272
+    },
+    {
+      "epoch": 0.8236847067697529,
+      "grad_norm": 0.9498163839438614,
+      "learning_rate": 1e-05,
+      "loss": 0.8472,
+      "step": 273
+    },
+    {
+      "epoch": 0.8267018668678107,
+      "grad_norm": 0.9864544845499665,
+      "learning_rate": 1e-05,
+      "loss": 0.8751,
+      "step": 274
+    },
+    {
+      "epoch": 0.8297190269658684,
+      "grad_norm": 1.0406919672946373,
+      "learning_rate": 1e-05,
+      "loss": 0.798,
+      "step": 275
+    },
+    {
+      "epoch": 0.832736187063926,
+      "grad_norm": 1.0806255336515647,
+      "learning_rate": 1e-05,
+      "loss": 0.8282,
+      "step": 276
+    },
+    {
+      "epoch": 0.8357533471619838,
+      "grad_norm": 0.9860936672416695,
+      "learning_rate": 1e-05,
+      "loss": 0.858,
+      "step": 277
+    },
+    {
+      "epoch": 0.8387705072600414,
+      "grad_norm": 0.9718313802197633,
+      "learning_rate": 1e-05,
+      "loss": 0.8466,
+      "step": 278
+    },
+    {
+      "epoch": 0.8417876673580992,
+      "grad_norm": 1.0544122713831847,
+      "learning_rate": 1e-05,
+      "loss": 0.8744,
+      "step": 279
+    },
+    {
+      "epoch": 0.8448048274561569,
+      "grad_norm": 1.081992381916025,
+      "learning_rate": 1e-05,
+      "loss": 0.8743,
+      "step": 280
+    },
+    {
+      "epoch": 0.8478219875542146,
+      "grad_norm": 0.9532379328140087,
+      "learning_rate": 1e-05,
+      "loss": 0.857,
+      "step": 281
+    },
+    {
+      "epoch": 0.8508391476522723,
+      "grad_norm": 0.9411887622889539,
+      "learning_rate": 1e-05,
+      "loss": 0.8408,
+      "step": 282
+    },
+    {
+      "epoch": 0.8538563077503301,
+      "grad_norm": 0.9619536563065685,
+      "learning_rate": 1e-05,
+      "loss": 0.8501,
+      "step": 283
+    },
+    {
+      "epoch": 0.8568734678483877,
+      "grad_norm": 0.9802987123695353,
+      "learning_rate": 1e-05,
+      "loss": 0.8235,
+      "step": 284
+    },
+    {
+      "epoch": 0.8598906279464454,
+      "grad_norm": 1.0032810101495542,
+      "learning_rate": 1e-05,
+      "loss": 0.8516,
+      "step": 285
+    },
+    {
+      "epoch": 0.8629077880445031,
+      "grad_norm": 0.9916945079271281,
+      "learning_rate": 1e-05,
+      "loss": 0.8324,
+      "step": 286
+    },
+    {
+      "epoch": 0.8659249481425608,
+      "grad_norm": 0.9901223884800562,
+      "learning_rate": 1e-05,
+      "loss": 0.8408,
+      "step": 287
+    },
+    {
+      "epoch": 0.8689421082406186,
+      "grad_norm": 0.9835034534966476,
+      "learning_rate": 1e-05,
+      "loss": 0.8495,
+      "step": 288
+    },
+    {
+      "epoch": 0.8719592683386762,
+      "grad_norm": 0.9750801588302662,
+      "learning_rate": 1e-05,
+      "loss": 0.8563,
+      "step": 289
+    },
+    {
+      "epoch": 0.874976428436734,
+      "grad_norm": 0.9641976460403898,
+      "learning_rate": 1e-05,
+      "loss": 0.8421,
+      "step": 290
+    },
+    {
+      "epoch": 0.8779935885347916,
+      "grad_norm": 0.9501946334304521,
+      "learning_rate": 1e-05,
+      "loss": 0.8654,
+      "step": 291
+    },
+    {
+      "epoch": 0.8810107486328493,
+      "grad_norm": 0.9100014151244762,
+      "learning_rate": 1e-05,
+      "loss": 0.8631,
+      "step": 292
+    },
+    {
+      "epoch": 0.8840279087309071,
+      "grad_norm": 0.9944179407196427,
+      "learning_rate": 1e-05,
+      "loss": 0.8464,
+      "step": 293
+    },
+    {
+      "epoch": 0.8870450688289647,
+      "grad_norm": 0.9853713974171726,
+      "learning_rate": 1e-05,
+      "loss": 0.8605,
+      "step": 294
+    },
+    {
+      "epoch": 0.8900622289270225,
+      "grad_norm": 0.9254523406321978,
+      "learning_rate": 1e-05,
+      "loss": 0.8478,
+      "step": 295
+    },
+    {
+      "epoch": 0.8930793890250801,
+      "grad_norm": 0.8959456626105031,
+      "learning_rate": 1e-05,
+      "loss": 0.8457,
+      "step": 296
+    },
+    {
+      "epoch": 0.8960965491231379,
+      "grad_norm": 1.0037255347844305,
+      "learning_rate": 1e-05,
+      "loss": 0.8576,
+      "step": 297
+    },
+    {
+      "epoch": 0.8991137092211956,
+      "grad_norm": 0.9449138138513178,
+      "learning_rate": 1e-05,
+      "loss": 0.822,
+      "step": 298
+    },
+    {
+      "epoch": 0.9021308693192532,
+      "grad_norm": 0.9597546807553757,
+      "learning_rate": 1e-05,
+      "loss": 0.7988,
+      "step": 299
+    },
+    {
+      "epoch": 0.905148029417311,
+      "grad_norm": 0.9624792569398237,
+      "learning_rate": 1e-05,
+      "loss": 0.8389,
+      "step": 300
+    },
+    {
+      "epoch": 0.9081651895153686,
+      "grad_norm": 0.9435277465551941,
+      "learning_rate": 1e-05,
+      "loss": 0.8722,
+      "step": 301
+    },
+    {
+      "epoch": 0.9111823496134264,
+      "grad_norm": 0.9681970370411234,
+      "learning_rate": 1e-05,
+      "loss": 0.8183,
+      "step": 302
+    },
+    {
+      "epoch": 0.9141995097114841,
+      "grad_norm": 0.9291647991127606,
+      "learning_rate": 1e-05,
+      "loss": 0.8076,
+      "step": 303
+    },
+    {
+      "epoch": 0.9172166698095418,
+      "grad_norm": 1.0177809366807526,
+      "learning_rate": 1e-05,
+      "loss": 0.8645,
+      "step": 304
+    },
+    {
+      "epoch": 0.9202338299075995,
+      "grad_norm": 0.9855696615573117,
+      "learning_rate": 1e-05,
+      "loss": 0.8546,
+      "step": 305
+    },
+    {
+      "epoch": 0.9232509900056571,
+      "grad_norm": 0.9745085927690291,
+      "learning_rate": 1e-05,
+      "loss": 0.8442,
+      "step": 306
+    },
+    {
+      "epoch": 0.9262681501037149,
+      "grad_norm": 0.9356489869997006,
+      "learning_rate": 1e-05,
+      "loss": 0.8571,
+      "step": 307
+    },
+    {
+      "epoch": 0.9292853102017726,
+      "grad_norm": 1.0346965656565765,
+      "learning_rate": 1e-05,
+      "loss": 0.823,
+      "step": 308
+    },
+    {
+      "epoch": 0.9323024702998303,
+      "grad_norm": 1.123418692750864,
+      "learning_rate": 1e-05,
+      "loss": 0.8717,
+      "step": 309
+    },
+    {
+      "epoch": 0.935319630397888,
+      "grad_norm": 1.0319249558634143,
+      "learning_rate": 1e-05,
+      "loss": 0.8433,
+      "step": 310
+    },
+    {
+      "epoch": 0.9383367904959456,
+      "grad_norm": 0.9462383670551003,
+      "learning_rate": 1e-05,
+      "loss": 0.8607,
+      "step": 311
+    },
+    {
+      "epoch": 0.9413539505940034,
+      "grad_norm": 0.9441101670098899,
+      "learning_rate": 1e-05,
+      "loss": 0.8186,
+      "step": 312
+    },
+    {
+      "epoch": 0.9443711106920611,
+      "grad_norm": 1.0504882586379691,
+      "learning_rate": 1e-05,
+      "loss": 0.845,
+      "step": 313
+    },
+    {
+      "epoch": 0.9473882707901188,
+      "grad_norm": 0.9048369513823565,
+      "learning_rate": 1e-05,
+      "loss": 0.8174,
+      "step": 314
+    },
+    {
+      "epoch": 0.9504054308881765,
+      "grad_norm": 0.9019137471005251,
+      "learning_rate": 1e-05,
+      "loss": 0.8556,
+      "step": 315
+    },
+    {
+      "epoch": 0.9534225909862342,
+      "grad_norm": 0.8875508030205819,
+      "learning_rate": 1e-05,
+      "loss": 0.861,
+      "step": 316
+    },
+    {
+      "epoch": 0.9564397510842919,
+      "grad_norm": 0.9993353590451418,
+      "learning_rate": 1e-05,
+      "loss": 0.8669,
+      "step": 317
+    },
+    {
+      "epoch": 0.9594569111823497,
+      "grad_norm": 0.9488161087038608,
+      "learning_rate": 1e-05,
+      "loss": 0.878,
+      "step": 318
+    },
+    {
+      "epoch": 0.9624740712804073,
+      "grad_norm": 0.9365808217541111,
+      "learning_rate": 1e-05,
+      "loss": 0.8222,
+      "step": 319
+    },
+    {
+      "epoch": 0.965491231378465,
+      "grad_norm": 0.9799964559542612,
+      "learning_rate": 1e-05,
+      "loss": 0.8468,
+      "step": 320
+    },
+    {
+      "epoch": 0.9685083914765227,
+      "grad_norm": 1.0661880405150197,
+      "learning_rate": 1e-05,
+      "loss": 0.8381,
+      "step": 321
+    },
+    {
+      "epoch": 0.9715255515745804,
+      "grad_norm": 1.0265204942074564,
+      "learning_rate": 1e-05,
+      "loss": 0.8467,
+      "step": 322
+    },
+    {
+      "epoch": 0.9745427116726382,
+      "grad_norm": 1.067821792666605,
+      "learning_rate": 1e-05,
+      "loss": 0.8351,
+      "step": 323
+    },
+    {
+      "epoch": 0.9775598717706958,
+      "grad_norm": 1.1466057402506813,
+      "learning_rate": 1e-05,
+      "loss": 0.8551,
+      "step": 324
+    },
+    {
+      "epoch": 0.9805770318687536,
+      "grad_norm": 0.9899578843967808,
+      "learning_rate": 1e-05,
+      "loss": 0.8248,
+      "step": 325
+    },
+    {
+      "epoch": 0.9835941919668112,
+      "grad_norm": 0.8886227742234571,
+      "learning_rate": 1e-05,
+      "loss": 0.8527,
+      "step": 326
+    },
+    {
+      "epoch": 0.9866113520648689,
+      "grad_norm": 0.9780662079081274,
+      "learning_rate": 1e-05,
+      "loss": 0.862,
+      "step": 327
+    },
+    {
+      "epoch": 0.9896285121629267,
+      "grad_norm": 1.0240427016912055,
+      "learning_rate": 1e-05,
+      "loss": 0.8646,
+      "step": 328
+    },
+    {
+      "epoch": 0.9926456722609843,
+      "grad_norm": 0.9797020588373134,
+      "learning_rate": 1e-05,
+      "loss": 0.8764,
+      "step": 329
+    },
+    {
+      "epoch": 0.9956628323590421,
+      "grad_norm": 0.9980560765723044,
+      "learning_rate": 1e-05,
+      "loss": 0.8767,
+      "step": 330
+    },
+    {
+      "epoch": 0.9986799924570997,
+      "grad_norm": 0.9334505105444044,
+      "learning_rate": 1e-05,
+      "loss": 0.8189,
+      "step": 331
+    },
+    {
+      "epoch": 0.9986799924570997,
+      "step": 331,
+      "total_flos": 437602977054720.0,
+      "train_loss": 0.8955676523220143,
+      "train_runtime": 47565.9142,
+      "train_samples_per_second": 0.892,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 331,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 437602977054720.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87047fa2379fd7abc7b1f1c34b8011a23233dc288704be9e7543785f6a9f4b0
+size 7544