Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,26 @@
+{
+  "</think>": 151666,
+  "</tool_call>": 151658,
+  "<think>": 151665,
+  "<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": "Qwen/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": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389e0f1fe47a6863b3ceb87e96c1ef6135647981035e76adb5f576a6645f0a8f
+size 9941058640

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed608d0c55825dbe5cd1c9ba78585d98d02c5bc3668352de4efd0b44f54ad7a
+size 9909694792

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be90e220474956922fe14a59ffbfffa3bd5c744cd86b1376cd253a762f8f6098
+size 9689380560

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.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 +1,223 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": true,
+      "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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,3631 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 3289,
+  "global_step": 16443,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 24.78779624251123,
+      "learning_rate": 6.079027355623101e-10,
+      "loss": 2.6939,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 35.873109917628135,
+      "learning_rate": 1.9452887537993922e-08,
+      "loss": 3.4616,
+      "step": 32
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 54.36320326793996,
+      "learning_rate": 3.8905775075987844e-08,
+      "loss": 3.544,
+      "step": 64
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 26.680119386381374,
+      "learning_rate": 5.8358662613981756e-08,
+      "loss": 3.3751,
+      "step": 96
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 21.12845447174909,
+      "learning_rate": 7.781155015197569e-08,
+      "loss": 3.5534,
+      "step": 128
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 14.326825936063585,
+      "learning_rate": 9.72644376899696e-08,
+      "loss": 3.2669,
+      "step": 160
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 25.878315201522145,
+      "learning_rate": 1.1671732522796351e-07,
+      "loss": 2.9778,
+      "step": 192
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 36.45201708374618,
+      "learning_rate": 1.3617021276595745e-07,
+      "loss": 2.5704,
+      "step": 224
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 23.711566820577637,
+      "learning_rate": 1.5562310030395138e-07,
+      "loss": 1.3894,
+      "step": 256
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.875938314628448,
+      "learning_rate": 1.7507598784194527e-07,
+      "loss": 0.6738,
+      "step": 288
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 6.241944245269492,
+      "learning_rate": 1.945288753799392e-07,
+      "loss": 0.5629,
+      "step": 320
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.8778836099761524,
+      "learning_rate": 2.1398176291793313e-07,
+      "loss": 0.4872,
+      "step": 352
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.5436867519527993,
+      "learning_rate": 2.3343465045592702e-07,
+      "loss": 0.4714,
+      "step": 384
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.3096231574697645,
+      "learning_rate": 2.52887537993921e-07,
+      "loss": 0.4378,
+      "step": 416
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.9666937909371047,
+      "learning_rate": 2.723404255319149e-07,
+      "loss": 0.4291,
+      "step": 448
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.2115158499878724,
+      "learning_rate": 2.917933130699088e-07,
+      "loss": 0.3954,
+      "step": 480
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.7998977018189959,
+      "learning_rate": 3.1124620060790275e-07,
+      "loss": 0.4086,
+      "step": 512
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.8295831973352625,
+      "learning_rate": 3.3069908814589665e-07,
+      "loss": 0.3926,
+      "step": 544
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.14598569285712,
+      "learning_rate": 3.5015197568389055e-07,
+      "loss": 0.4026,
+      "step": 576
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.5109663276292344,
+      "learning_rate": 3.696048632218845e-07,
+      "loss": 0.3688,
+      "step": 608
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.453154442640789,
+      "learning_rate": 3.890577507598784e-07,
+      "loss": 0.3919,
+      "step": 640
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.6423681780897064,
+      "learning_rate": 4.085106382978723e-07,
+      "loss": 0.364,
+      "step": 672
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.8702893489598191,
+      "learning_rate": 4.2796352583586625e-07,
+      "loss": 0.3543,
+      "step": 704
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.8401881440614818,
+      "learning_rate": 4.4741641337386015e-07,
+      "loss": 0.3601,
+      "step": 736
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.850566734809788,
+      "learning_rate": 4.6686930091185405e-07,
+      "loss": 0.3566,
+      "step": 768
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.6994281914890326,
+      "learning_rate": 4.86322188449848e-07,
+      "loss": 0.3505,
+      "step": 800
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.8680937366461803,
+      "learning_rate": 5.05775075987842e-07,
+      "loss": 0.3358,
+      "step": 832
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.660364495604376,
+      "learning_rate": 5.252279635258359e-07,
+      "loss": 0.3312,
+      "step": 864
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.562680158872079,
+      "learning_rate": 5.446808510638298e-07,
+      "loss": 0.3346,
+      "step": 896
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.6948446357514406,
+      "learning_rate": 5.641337386018237e-07,
+      "loss": 0.3356,
+      "step": 928
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.209363365641442,
+      "learning_rate": 5.835866261398176e-07,
+      "loss": 0.3279,
+      "step": 960
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.6925812671610025,
+      "learning_rate": 6.030395136778115e-07,
+      "loss": 0.3367,
+      "step": 992
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.5391435373855369,
+      "learning_rate": 6.224924012158055e-07,
+      "loss": 0.3356,
+      "step": 1024
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.4744316930455266,
+      "learning_rate": 6.419452887537994e-07,
+      "loss": 0.3277,
+      "step": 1056
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.7620056653926688,
+      "learning_rate": 6.613981762917933e-07,
+      "loss": 0.3307,
+      "step": 1088
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4025350626099162,
+      "learning_rate": 6.808510638297872e-07,
+      "loss": 0.3197,
+      "step": 1120
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.3405530061214819,
+      "learning_rate": 7.003039513677811e-07,
+      "loss": 0.3218,
+      "step": 1152
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.4535529320190042,
+      "learning_rate": 7.197568389057751e-07,
+      "loss": 0.3067,
+      "step": 1184
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.445157014748904,
+      "learning_rate": 7.39209726443769e-07,
+      "loss": 0.3087,
+      "step": 1216
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.5871727851863946,
+      "learning_rate": 7.586626139817629e-07,
+      "loss": 0.3252,
+      "step": 1248
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.3848383016325827,
+      "learning_rate": 7.781155015197568e-07,
+      "loss": 0.3113,
+      "step": 1280
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.7455453453163468,
+      "learning_rate": 7.975683890577507e-07,
+      "loss": 0.297,
+      "step": 1312
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.3001668041428838,
+      "learning_rate": 8.170212765957446e-07,
+      "loss": 0.3223,
+      "step": 1344
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.2132377152476534,
+      "learning_rate": 8.364741641337386e-07,
+      "loss": 0.315,
+      "step": 1376
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.4384605625322182,
+      "learning_rate": 8.559270516717325e-07,
+      "loss": 0.3105,
+      "step": 1408
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.1957556077083222,
+      "learning_rate": 8.753799392097264e-07,
+      "loss": 0.3007,
+      "step": 1440
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.466257939308454,
+      "learning_rate": 8.948328267477203e-07,
+      "loss": 0.3034,
+      "step": 1472
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.348037306034132,
+      "learning_rate": 9.142857142857142e-07,
+      "loss": 0.3044,
+      "step": 1504
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.3312009756781122,
+      "learning_rate": 9.337386018237081e-07,
+      "loss": 0.3124,
+      "step": 1536
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.5165497951579907,
+      "learning_rate": 9.531914893617021e-07,
+      "loss": 0.3064,
+      "step": 1568
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.2308464212993413,
+      "learning_rate": 9.72644376899696e-07,
+      "loss": 0.3096,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.4477927464029368,
+      "learning_rate": 9.9209726443769e-07,
+      "loss": 0.2967,
+      "step": 1632
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.6161236994381232,
+      "learning_rate": 9.999959323804955e-07,
+      "loss": 0.307,
+      "step": 1664
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.408597466262752,
+      "learning_rate": 9.999706931043734e-07,
+      "loss": 0.3045,
+      "step": 1696
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.2262804987989535,
+      "learning_rate": 9.999223791032621e-07,
+      "loss": 0.2982,
+      "step": 1728
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4772857240369206,
+      "learning_rate": 9.998509926069568e-07,
+      "loss": 0.3085,
+      "step": 1760
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.1705510022471537,
+      "learning_rate": 9.997565369100982e-07,
+      "loss": 0.3102,
+      "step": 1792
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.354193914272892,
+      "learning_rate": 9.996390163720203e-07,
+      "loss": 0.3079,
+      "step": 1824
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.6499740915478518,
+      "learning_rate": 9.99498436416549e-07,
+      "loss": 0.3058,
+      "step": 1856
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.4176797632580183,
+      "learning_rate": 9.993348035317523e-07,
+      "loss": 0.2898,
+      "step": 1888
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.221569587599335,
+      "learning_rate": 9.991481252696405e-07,
+      "loss": 0.2971,
+      "step": 1920
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.6858523944684565,
+      "learning_rate": 9.98938410245818e-07,
+      "loss": 0.3015,
+      "step": 1952
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.3071072285598695,
+      "learning_rate": 9.987056681390846e-07,
+      "loss": 0.3017,
+      "step": 1984
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.3559736389856838,
+      "learning_rate": 9.984499096909904e-07,
+      "loss": 0.2996,
+      "step": 2016
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.6577354687629797,
+      "learning_rate": 9.981711467053391e-07,
+      "loss": 0.2899,
+      "step": 2048
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.3911817831183464,
+      "learning_rate": 9.97869392047643e-07,
+      "loss": 0.2916,
+      "step": 2080
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.4068725629362402,
+      "learning_rate": 9.9754465964453e-07,
+      "loss": 0.3042,
+      "step": 2112
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.2845003819775453,
+      "learning_rate": 9.971969644831001e-07,
+      "loss": 0.2953,
+      "step": 2144
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3034821415736415,
+      "learning_rate": 9.968263226102348e-07,
+      "loss": 0.2947,
+      "step": 2176
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.297243001736353,
+      "learning_rate": 9.96432751131855e-07,
+      "loss": 0.2849,
+      "step": 2208
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.411186926138334,
+      "learning_rate": 9.960162682121326e-07,
+      "loss": 0.2974,
+      "step": 2240
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.2374941457414885,
+      "learning_rate": 9.955768930726523e-07,
+      "loss": 0.2824,
+      "step": 2272
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.2627652146626807,
+      "learning_rate": 9.95114645991523e-07,
+      "loss": 0.2865,
+      "step": 2304
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.3134029095546937,
+      "learning_rate": 9.946295483024446e-07,
+      "loss": 0.2867,
+      "step": 2336
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.125719093465591,
+      "learning_rate": 9.9412162239372e-07,
+      "loss": 0.292,
+      "step": 2368
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.4224011133495338,
+      "learning_rate": 9.93590891707225e-07,
+      "loss": 0.309,
+      "step": 2400
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.558277250619359,
+      "learning_rate": 9.930373807373245e-07,
+      "loss": 0.289,
+      "step": 2432
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.3208871305799181,
+      "learning_rate": 9.924611150297428e-07,
+      "loss": 0.2883,
+      "step": 2464
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.3373963931205746,
+      "learning_rate": 9.91862121180384e-07,
+      "loss": 0.2808,
+      "step": 2496
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.3910055395902359,
+      "learning_rate": 9.912404268341051e-07,
+      "loss": 0.2932,
+      "step": 2528
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.4574028412197861,
+      "learning_rate": 9.905960606834404e-07,
+      "loss": 0.2947,
+      "step": 2560
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.203878457595175,
+      "learning_rate": 9.899290524672763e-07,
+      "loss": 0.2867,
+      "step": 2592
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.4673267738670204,
+      "learning_rate": 9.892394329694793e-07,
+      "loss": 0.2837,
+      "step": 2624
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.6281520652734605,
+      "learning_rate": 9.885272340174754e-07,
+      "loss": 0.3032,
+      "step": 2656
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.2522157670744074,
+      "learning_rate": 9.877924884807814e-07,
+      "loss": 0.2963,
+      "step": 2688
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4632043067121088,
+      "learning_rate": 9.870352302694869e-07,
+      "loss": 0.2898,
+      "step": 2720
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.398722594166713,
+      "learning_rate": 9.86255494332691e-07,
+      "loss": 0.2896,
+      "step": 2752
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.3916529397644415,
+      "learning_rate": 9.854533166568867e-07,
+      "loss": 0.2967,
+      "step": 2784
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.3208718268032766,
+      "learning_rate": 9.846287342643032e-07,
+      "loss": 0.2838,
+      "step": 2816
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0718990960806063,
+      "learning_rate": 9.837817852111949e-07,
+      "loss": 0.2942,
+      "step": 2848
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.3984255388696125,
+      "learning_rate": 9.829125085860858e-07,
+      "loss": 0.2832,
+      "step": 2880
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.258839102452435,
+      "learning_rate": 9.820209445079655e-07,
+      "loss": 0.2964,
+      "step": 2912
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1619142104791713,
+      "learning_rate": 9.811071341244379e-07,
+      "loss": 0.2727,
+      "step": 2944
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.3494984294429655,
+      "learning_rate": 9.801711196098213e-07,
+      "loss": 0.2848,
+      "step": 2976
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.2501831577892621,
+      "learning_rate": 9.792129441632027e-07,
+      "loss": 0.2749,
+      "step": 3008
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.2580708434458154,
+      "learning_rate": 9.782326520064443e-07,
+      "loss": 0.2868,
+      "step": 3040
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.5601918050638766,
+      "learning_rate": 9.772302883821418e-07,
+      "loss": 0.292,
+      "step": 3072
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.3545732270149806,
+      "learning_rate": 9.762058995515362e-07,
+      "loss": 0.2895,
+      "step": 3104
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.4796071501521761,
+      "learning_rate": 9.751595327923802e-07,
+      "loss": 0.291,
+      "step": 3136
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.3020677021992657,
+      "learning_rate": 9.740912363967546e-07,
+      "loss": 0.294,
+      "step": 3168
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.2903648809439663,
+      "learning_rate": 9.730010596688405e-07,
+      "loss": 0.2971,
+      "step": 3200
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.4322652904369149,
+      "learning_rate": 9.718890529226432e-07,
+      "loss": 0.2842,
+      "step": 3232
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.4918014229559349,
+      "learning_rate": 9.707552674796704e-07,
+      "loss": 0.2855,
+      "step": 3264
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.495160093783148,
+      "learning_rate": 9.695997556665642e-07,
+      "loss": 0.2961,
+      "step": 3296
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.2299397480418435,
+      "learning_rate": 9.68422570812685e-07,
+      "loss": 0.275,
+      "step": 3328
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.4595570985088122,
+      "learning_rate": 9.672237672476504e-07,
+      "loss": 0.2816,
+      "step": 3360
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.2523764393563719,
+      "learning_rate": 9.660034002988288e-07,
+      "loss": 0.2826,
+      "step": 3392
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.1556114989117734,
+      "learning_rate": 9.64761526288785e-07,
+      "loss": 0.2979,
+      "step": 3424
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.2760487310976472,
+      "learning_rate": 9.634982025326808e-07,
+      "loss": 0.2703,
+      "step": 3456
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.1268494754892229,
+      "learning_rate": 9.622134873356302e-07,
+      "loss": 0.2888,
+      "step": 3488
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.5177691734350403,
+      "learning_rate": 9.60907439990008e-07,
+      "loss": 0.2854,
+      "step": 3520
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.4479572539864909,
+      "learning_rate": 9.595801207727145e-07,
+      "loss": 0.2871,
+      "step": 3552
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.3320405553461194,
+      "learning_rate": 9.58231590942392e-07,
+      "loss": 0.2722,
+      "step": 3584
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.2684704306064236,
+      "learning_rate": 9.568619127365979e-07,
+      "loss": 0.2918,
+      "step": 3616
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.153157224662708,
+      "learning_rate": 9.554711493689337e-07,
+      "loss": 0.2727,
+      "step": 3648
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.2053424871803355,
+      "learning_rate": 9.540593650261259e-07,
+      "loss": 0.2727,
+      "step": 3680
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.5070136801134912,
+      "learning_rate": 9.526266248650647e-07,
+      "loss": 0.2829,
+      "step": 3712
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.3626256868915094,
+      "learning_rate": 9.511729950097962e-07,
+      "loss": 0.2948,
+      "step": 3744
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.3413698467022634,
+      "learning_rate": 9.496985425484708e-07,
+      "loss": 0.2804,
+      "step": 3776
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.1666360657022152,
+      "learning_rate": 9.482033355302474e-07,
+      "loss": 0.2779,
+      "step": 3808
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.2681212059953142,
+      "learning_rate": 9.466874429621523e-07,
+      "loss": 0.2766,
+      "step": 3840
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.570024716133246,
+      "learning_rate": 9.451509348058943e-07,
+      "loss": 0.278,
+      "step": 3872
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.348864102054253,
+      "learning_rate": 9.435938819746363e-07,
+      "loss": 0.2814,
+      "step": 3904
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.479630195353394,
+      "learning_rate": 9.420163563297221e-07,
+      "loss": 0.2768,
+      "step": 3936
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3437829697550214,
+      "learning_rate": 9.4041843067736e-07,
+      "loss": 0.2796,
+      "step": 3968
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.7505808749964085,
+      "learning_rate": 9.388001787652626e-07,
+      "loss": 0.2804,
+      "step": 4000
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.2804732688993112,
+      "learning_rate": 9.37161675279243e-07,
+      "loss": 0.2671,
+      "step": 4032
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.5599945996293794,
+      "learning_rate": 9.355029958397686e-07,
+      "loss": 0.2778,
+      "step": 4064
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.140562030900848,
+      "learning_rate": 9.338242169984701e-07,
+      "loss": 0.2779,
+      "step": 4096
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.1891602382042474,
+      "learning_rate": 9.321254162346089e-07,
+      "loss": 0.2779,
+      "step": 4128
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.6066027745264384,
+      "learning_rate": 9.304066719515013e-07,
+      "loss": 0.2831,
+      "step": 4160
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.3535261095585958,
+      "learning_rate": 9.286680634729005e-07,
+      "loss": 0.2869,
+      "step": 4192
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.449372671449822,
+      "learning_rate": 9.269096710393343e-07,
+      "loss": 0.2859,
+      "step": 4224
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.2209167474794183,
+      "learning_rate": 9.251315758044032e-07,
+      "loss": 0.2908,
+      "step": 4256
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4925119088076193,
+      "learning_rate": 9.233338598310343e-07,
+      "loss": 0.2821,
+      "step": 4288
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.2663637068625269,
+      "learning_rate": 9.215166060876943e-07,
+      "loss": 0.2839,
+      "step": 4320
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.335605475288019,
+      "learning_rate": 9.196798984445595e-07,
+      "loss": 0.2767,
+      "step": 4352
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1999064453898192,
+      "learning_rate": 9.178238216696463e-07,
+      "loss": 0.2813,
+      "step": 4384
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.2005680882302527,
+      "learning_rate": 9.159484614248978e-07,
+      "loss": 0.2776,
+      "step": 4416
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.2022881962586156,
+      "learning_rate": 9.140539042622311e-07,
+      "loss": 0.2812,
+      "step": 4448
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.4918926856382582,
+      "learning_rate": 9.121402376195421e-07,
+      "loss": 0.2763,
+      "step": 4480
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.452212648334464,
+      "learning_rate": 9.102075498166705e-07,
+      "loss": 0.2756,
+      "step": 4512
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.4610868927687688,
+      "learning_rate": 9.082559300513237e-07,
+      "loss": 0.2755,
+      "step": 4544
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.2140564103776683,
+      "learning_rate": 9.062854683949602e-07,
+      "loss": 0.266,
+      "step": 4576
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.23274371490023,
+      "learning_rate": 9.042962557886313e-07,
+      "loss": 0.2856,
+      "step": 4608
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.3898063562012308,
+      "learning_rate": 9.022883840387865e-07,
+      "loss": 0.2815,
+      "step": 4640
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.330139097581169,
+      "learning_rate": 9.002619458130339e-07,
+      "loss": 0.28,
+      "step": 4672
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.2874922030319198,
+      "learning_rate": 8.982170346358651e-07,
+      "loss": 0.2669,
+      "step": 4704
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.107586259057668,
+      "learning_rate": 8.961537448843377e-07,
+      "loss": 0.2853,
+      "step": 4736
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.448957134616539,
+      "learning_rate": 8.940721717837205e-07,
+      "loss": 0.2652,
+      "step": 4768
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.210724298652212,
+      "learning_rate": 8.919724114030984e-07,
+      "loss": 0.2795,
+      "step": 4800
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.3698632505550181,
+      "learning_rate": 8.898545606509378e-07,
+      "loss": 0.284,
+      "step": 4832
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.1911981203106947,
+      "learning_rate": 8.877187172706155e-07,
+      "loss": 0.2746,
+      "step": 4864
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.3333516374957606,
+      "learning_rate": 8.855649798359064e-07,
+      "loss": 0.2888,
+      "step": 4896
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.2351888608354114,
+      "learning_rate": 8.833934477464347e-07,
+      "loss": 0.2831,
+      "step": 4928
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.3038819344536112,
+      "learning_rate": 8.812042212230862e-07,
+      "loss": 0.2753,
+      "step": 4960
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.5707271650867898,
+      "learning_rate": 8.789974013033831e-07,
+      "loss": 0.2759,
+      "step": 4992
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.2820047239265864,
+      "learning_rate": 8.767730898368208e-07,
+      "loss": 0.2746,
+      "step": 5024
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.1744722963290781,
+      "learning_rate": 8.745313894801669e-07,
+      "loss": 0.291,
+      "step": 5056
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.0913528023957022,
+      "learning_rate": 8.722724036927242e-07,
+      "loss": 0.2837,
+      "step": 5088
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.3404827415629068,
+      "learning_rate": 8.699962367315552e-07,
+      "loss": 0.2676,
+      "step": 5120
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.163041143181648,
+      "learning_rate": 8.677029936466706e-07,
+      "loss": 0.2832,
+      "step": 5152
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.436779107568984,
+      "learning_rate": 8.653927802761809e-07,
+      "loss": 0.2728,
+      "step": 5184
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.0080451953033644,
+      "learning_rate": 8.630657032414121e-07,
+      "loss": 0.2617,
+      "step": 5216
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.1100819749235487,
+      "learning_rate": 8.607218699419843e-07,
+      "loss": 0.2942,
+      "step": 5248
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.2992077116418177,
+      "learning_rate": 8.583613885508556e-07,
+      "loss": 0.2672,
+      "step": 5280
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.223919929869006,
+      "learning_rate": 8.559843680093296e-07,
+      "loss": 0.277,
+      "step": 5312
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.1391386556761285,
+      "learning_rate": 8.535909180220268e-07,
+      "loss": 0.2806,
+      "step": 5344
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.2127293368764673,
+      "learning_rate": 8.511811490518225e-07,
+      "loss": 0.2619,
+      "step": 5376
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.140029182839281,
+      "learning_rate": 8.48755172314748e-07,
+      "loss": 0.2718,
+      "step": 5408
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.4671327877043736,
+      "learning_rate": 8.463130997748578e-07,
+      "loss": 0.272,
+      "step": 5440
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1390017949538402,
+      "learning_rate": 8.43855044139063e-07,
+      "loss": 0.2737,
+      "step": 5472
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2142876905398077,
+      "learning_rate": 8.413811188519282e-07,
+      "loss": 0.2599,
+      "step": 5504
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 1.266246650515794,
+      "learning_rate": 8.388914380904373e-07,
+      "loss": 0.2465,
+      "step": 5536
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 1.173280963516161,
+      "learning_rate": 8.36386116758723e-07,
+      "loss": 0.2483,
+      "step": 5568
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 1.1617564369184084,
+      "learning_rate": 8.33865270482764e-07,
+      "loss": 0.2568,
+      "step": 5600
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 1.420351934994977,
+      "learning_rate": 8.313290156050487e-07,
+      "loss": 0.2502,
+      "step": 5632
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 1.3547439002353128,
+      "learning_rate": 8.287774691792057e-07,
+      "loss": 0.246,
+      "step": 5664
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.1455753710552021,
+      "learning_rate": 8.262107489646014e-07,
+      "loss": 0.2554,
+      "step": 5696
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 1.3859247572490137,
+      "learning_rate": 8.236289734209054e-07,
+      "loss": 0.2466,
+      "step": 5728
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 1.1343048895326515,
+      "learning_rate": 8.210322617026232e-07,
+      "loss": 0.2467,
+      "step": 5760
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 1.2217575468560562,
+      "learning_rate": 8.184207336535967e-07,
+      "loss": 0.2574,
+      "step": 5792
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 1.3780997994944977,
+      "learning_rate": 8.157945098014733e-07,
+      "loss": 0.2481,
+      "step": 5824
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 1.0870131072717084,
+      "learning_rate": 8.131537113521443e-07,
+      "loss": 0.2588,
+      "step": 5856
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 1.0490087402219708,
+      "learning_rate": 8.104984601841489e-07,
+      "loss": 0.246,
+      "step": 5888
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.2965280317141281,
+      "learning_rate": 8.07828878843051e-07,
+      "loss": 0.249,
+      "step": 5920
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 1.2861279001372838,
+      "learning_rate": 8.051450905357829e-07,
+      "loss": 0.2412,
+      "step": 5952
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 1.409445153252456,
+      "learning_rate": 8.024472191249588e-07,
+      "loss": 0.2431,
+      "step": 5984
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.3691683733505722,
+      "learning_rate": 7.997353891231584e-07,
+      "loss": 0.2517,
+      "step": 6016
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.4906649500848184,
+      "learning_rate": 7.970097256871811e-07,
+      "loss": 0.2517,
+      "step": 6048
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 1.4438858223954047,
+      "learning_rate": 7.942703546122682e-07,
+      "loss": 0.2584,
+      "step": 6080
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.268958450317541,
+      "learning_rate": 7.915174023262988e-07,
+      "loss": 0.2522,
+      "step": 6112
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.4781129605275483,
+      "learning_rate": 7.887509958839538e-07,
+      "loss": 0.243,
+      "step": 6144
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 1.331949493045608,
+      "learning_rate": 7.859712629608524e-07,
+      "loss": 0.2429,
+      "step": 6176
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 1.306062446109076,
+      "learning_rate": 7.831783318476596e-07,
+      "loss": 0.2446,
+      "step": 6208
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 1.242511236714611,
+      "learning_rate": 7.803723314441656e-07,
+      "loss": 0.2451,
+      "step": 6240
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 1.4482758408678764,
+      "learning_rate": 7.775533912533363e-07,
+      "loss": 0.2412,
+      "step": 6272
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 1.3719989834400954,
+      "learning_rate": 7.747216413753366e-07,
+      "loss": 0.2421,
+      "step": 6304
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.1916507119961282,
+      "learning_rate": 7.718772125015263e-07,
+      "loss": 0.2536,
+      "step": 6336
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.2009787273487618,
+      "learning_rate": 7.690202359084278e-07,
+      "loss": 0.2501,
+      "step": 6368
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 1.2823116236203336,
+      "learning_rate": 7.661508434516682e-07,
+      "loss": 0.2524,
+      "step": 6400
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 1.3430035950312693,
+      "learning_rate": 7.632691675598935e-07,
+      "loss": 0.2577,
+      "step": 6432
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.4985924089749454,
+      "learning_rate": 7.60375341228656e-07,
+      "loss": 0.2444,
+      "step": 6464
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.2984272436604025,
+      "learning_rate": 7.574694980142779e-07,
+      "loss": 0.2615,
+      "step": 6496
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.3354550623218928,
+      "learning_rate": 7.545517720276857e-07,
+      "loss": 0.2389,
+      "step": 6528
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.4301768294716657,
+      "learning_rate": 7.51622297928222e-07,
+      "loss": 0.2449,
+      "step": 6560
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.1719113606920948,
+      "learning_rate": 7.4868121091743e-07,
+      "loss": 0.2423,
+      "step": 6592
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 1.4204627356681534,
+      "learning_rate": 7.457286467328135e-07,
+      "loss": 0.2445,
+      "step": 6624
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 1.4900172188399152,
+      "learning_rate": 7.427647416415725e-07,
+      "loss": 0.2483,
+      "step": 6656
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 1.3961859599185324,
+      "learning_rate": 7.397896324343151e-07,
+      "loss": 0.2359,
+      "step": 6688
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 1.3110300825940397,
+      "learning_rate": 7.368034564187424e-07,
+      "loss": 0.2512,
+      "step": 6720
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 1.2757069881397953,
+      "learning_rate": 7.338063514133136e-07,
+      "loss": 0.2547,
+      "step": 6752
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.4074893254437457,
+      "learning_rate": 7.307984557408837e-07,
+      "loss": 0.2496,
+      "step": 6784
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.351839197713545,
+      "learning_rate": 7.277799082223204e-07,
+      "loss": 0.2353,
+      "step": 6816
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.2030842443572731,
+      "learning_rate": 7.24750848170097e-07,
+      "loss": 0.2559,
+      "step": 6848
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.324374188137303,
+      "learning_rate": 7.217114153818629e-07,
+      "loss": 0.2448,
+      "step": 6880
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.2343518311233508,
+      "learning_rate": 7.186617501339917e-07,
+      "loss": 0.2475,
+      "step": 6912
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 1.257477506253048,
+      "learning_rate": 7.156019931751071e-07,
+      "loss": 0.2529,
+      "step": 6944
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 1.3065578571620988,
+      "learning_rate": 7.125322857195867e-07,
+      "loss": 0.2439,
+      "step": 6976
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.491754680548748,
+      "learning_rate": 7.094527694410455e-07,
+      "loss": 0.2581,
+      "step": 7008
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.2313699652632502,
+      "learning_rate": 7.063635864657964e-07,
+      "loss": 0.2462,
+      "step": 7040
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 1.200487097478514,
+      "learning_rate": 7.032648793662912e-07,
+      "loss": 0.2422,
+      "step": 7072
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 1.3322942461823077,
+      "learning_rate": 7.001567911545406e-07,
+      "loss": 0.2456,
+      "step": 7104
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 1.4431169758144065,
+      "learning_rate": 6.970394652755144e-07,
+      "loss": 0.2482,
+      "step": 7136
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 1.261334251262187,
+      "learning_rate": 6.939130456005196e-07,
+      "loss": 0.2456,
+      "step": 7168
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 1.4803616635583337,
+      "learning_rate": 6.907776764205622e-07,
+      "loss": 0.2628,
+      "step": 7200
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.318319361538514,
+      "learning_rate": 6.876335024396871e-07,
+      "loss": 0.2408,
+      "step": 7232
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 1.2799133546143286,
+      "learning_rate": 6.844806687682996e-07,
+      "loss": 0.2445,
+      "step": 7264
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 1.2877655780208916,
+      "learning_rate": 6.813193209164683e-07,
+      "loss": 0.2406,
+      "step": 7296
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 1.344111445915826,
+      "learning_rate": 6.781496047872098e-07,
+      "loss": 0.2408,
+      "step": 7328
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 1.5226804349220626,
+      "learning_rate": 6.749716666697545e-07,
+      "loss": 0.2469,
+      "step": 7360
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 1.3170301342228112,
+      "learning_rate": 6.717856532327956e-07,
+      "loss": 0.2407,
+      "step": 7392
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 1.185336007297627,
+      "learning_rate": 6.685917115177193e-07,
+      "loss": 0.2445,
+      "step": 7424
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.3491930633425604,
+      "learning_rate": 6.653899889318192e-07,
+      "loss": 0.2562,
+      "step": 7456
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 1.160879383772545,
+      "learning_rate": 6.621806332414925e-07,
+      "loss": 0.2427,
+      "step": 7488
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 1.5333857134961049,
+      "learning_rate": 6.589637925654215e-07,
+      "loss": 0.251,
+      "step": 7520
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.5263236812468681,
+      "learning_rate": 6.557396153677356e-07,
+      "loss": 0.2543,
+      "step": 7552
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.0995345813700304,
+      "learning_rate": 6.525082504511612e-07,
+      "loss": 0.2493,
+      "step": 7584
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 1.4740647676869196,
+      "learning_rate": 6.492698469501532e-07,
+      "loss": 0.2414,
+      "step": 7616
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.4036985523166017,
+      "learning_rate": 6.460245543240123e-07,
+      "loss": 0.2373,
+      "step": 7648
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.4125143998119496,
+      "learning_rate": 6.427725223499871e-07,
+      "loss": 0.2427,
+      "step": 7680
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 1.195620693310162,
+      "learning_rate": 6.39513901116362e-07,
+      "loss": 0.2522,
+      "step": 7712
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 1.2679060414661505,
+      "learning_rate": 6.362488410155298e-07,
+      "loss": 0.2448,
+      "step": 7744
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.4675997129467317,
+      "learning_rate": 6.329774927370504e-07,
+      "loss": 0.2459,
+      "step": 7776
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.3511806562135458,
+      "learning_rate": 6.297000072606972e-07,
+      "loss": 0.257,
+      "step": 7808
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.272848715104825,
+      "learning_rate": 6.264165358494884e-07,
+      "loss": 0.246,
+      "step": 7840
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.4081103274783833,
+      "learning_rate": 6.231272300427059e-07,
+      "loss": 0.2485,
+      "step": 7872
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.2073750932804077,
+      "learning_rate": 6.198322416489016e-07,
+      "loss": 0.2354,
+      "step": 7904
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 1.3509938246652688,
+      "learning_rate": 6.165317227388911e-07,
+      "loss": 0.2423,
+      "step": 7936
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 1.8975854309012892,
+      "learning_rate": 6.132258256387348e-07,
+      "loss": 0.2422,
+      "step": 7968
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 1.616263805539082,
+      "learning_rate": 6.099147029227088e-07,
+      "loss": 0.2452,
+      "step": 8000
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.4581239370531887,
+      "learning_rate": 6.065985074062624e-07,
+      "loss": 0.2564,
+      "step": 8032
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.4107792940118344,
+      "learning_rate": 6.032773921389654e-07,
+      "loss": 0.2613,
+      "step": 8064
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.4254738015511745,
+      "learning_rate": 5.999515103974447e-07,
+      "loss": 0.2441,
+      "step": 8096
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.2694180719111068,
+      "learning_rate": 5.966210156783108e-07,
+      "loss": 0.2559,
+      "step": 8128
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.3375582532247023,
+      "learning_rate": 5.932860616910721e-07,
+      "loss": 0.2488,
+      "step": 8160
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.2586037041521065,
+      "learning_rate": 5.899468023510428e-07,
+      "loss": 0.2427,
+      "step": 8192
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.2896167720703278,
+      "learning_rate": 5.866033917722379e-07,
+      "loss": 0.2567,
+      "step": 8224
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 1.101067530433089,
+      "learning_rate": 5.832559842602608e-07,
+      "loss": 0.2342,
+      "step": 8256
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 1.1591181439961709,
+      "learning_rate": 5.799047343051827e-07,
+      "loss": 0.2411,
+      "step": 8288
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.2887740481533372,
+      "learning_rate": 5.765497965744111e-07,
+      "loss": 0.2433,
+      "step": 8320
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.1116096883871758,
+      "learning_rate": 5.731913259055527e-07,
+      "loss": 0.2435,
+      "step": 8352
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.3978304499588927,
+      "learning_rate": 5.698294772992669e-07,
+      "loss": 0.2485,
+      "step": 8384
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 1.1353060264434358,
+      "learning_rate": 5.664644059121121e-07,
+      "loss": 0.2508,
+      "step": 8416
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 1.337326494552789,
+      "learning_rate": 5.630962670493848e-07,
+      "loss": 0.2446,
+      "step": 8448
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 1.5497857023189168,
+      "learning_rate": 5.597252161579525e-07,
+      "loss": 0.2498,
+      "step": 8480
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 1.6735926212275043,
+      "learning_rate": 5.563514088190788e-07,
+      "loss": 0.2382,
+      "step": 8512
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.5802941502096313,
+      "learning_rate": 5.529750007412435e-07,
+      "loss": 0.24,
+      "step": 8544
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.434775976642666,
+      "learning_rate": 5.495961477529559e-07,
+      "loss": 0.2508,
+      "step": 8576
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.3871703235640929,
+      "learning_rate": 5.462150057955633e-07,
+      "loss": 0.24,
+      "step": 8608
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 1.3448291807441222,
+      "learning_rate": 5.428317309160538e-07,
+      "loss": 0.2484,
+      "step": 8640
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 1.3157038644549268,
+      "learning_rate": 5.394464792598545e-07,
+      "loss": 0.2409,
+      "step": 8672
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 1.2008640772377304,
+      "learning_rate": 5.360594070636248e-07,
+      "loss": 0.2454,
+      "step": 8704
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 1.3073489027432128,
+      "learning_rate": 5.326706706480467e-07,
+      "loss": 0.2446,
+      "step": 8736
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.5955373808274311,
+      "learning_rate": 5.292804264106083e-07,
+      "loss": 0.2433,
+      "step": 8768
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 1.2901907823242207,
+      "learning_rate": 5.25888830818388e-07,
+      "loss": 0.2426,
+      "step": 8800
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 1.4454540634426136,
+      "learning_rate": 5.224960404008319e-07,
+      "loss": 0.2487,
+      "step": 8832
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 1.3252857725269103,
+      "learning_rate": 5.19102211742529e-07,
+      "loss": 0.242,
+      "step": 8864
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 1.3963560963709287,
+      "learning_rate": 5.157075014759866e-07,
+      "loss": 0.2333,
+      "step": 8896
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 1.7474842902023573,
+      "learning_rate": 5.123120662743993e-07,
+      "loss": 0.2397,
+      "step": 8928
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 1.463552241271405,
+      "learning_rate": 5.089160628444193e-07,
+      "loss": 0.2475,
+      "step": 8960
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 1.4711904387458636,
+      "learning_rate": 5.055196479189237e-07,
+      "loss": 0.2468,
+      "step": 8992
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.1486741329450094,
+      "learning_rate": 5.021229782497811e-07,
+      "loss": 0.2474,
+      "step": 9024
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.465014768579321,
+      "learning_rate": 4.987262106006171e-07,
+      "loss": 0.2437,
+      "step": 9056
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 1.6572146980799467,
+      "learning_rate": 4.953295017395788e-07,
+      "loss": 0.2358,
+      "step": 9088
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 1.1497400773353195,
+      "learning_rate": 4.919330084321009e-07,
+      "loss": 0.2459,
+      "step": 9120
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.4973289494569486,
+      "learning_rate": 4.885368874336694e-07,
+      "loss": 0.2497,
+      "step": 9152
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.375218554438502,
+      "learning_rate": 4.851412954825874e-07,
+      "loss": 0.2508,
+      "step": 9184
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.3780517501267755,
+      "learning_rate": 4.817463892927411e-07,
+      "loss": 0.2567,
+      "step": 9216
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 1.4504412670024611,
+      "learning_rate": 4.783523255463679e-07,
+      "loss": 0.2409,
+      "step": 9248
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 1.2870854505712077,
+      "learning_rate": 4.7495926088682436e-07,
+      "loss": 0.2423,
+      "step": 9280
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.3985153319949002,
+      "learning_rate": 4.71567351911357e-07,
+      "loss": 0.251,
+      "step": 9312
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.0349716694291753,
+      "learning_rate": 4.681767551638751e-07,
+      "loss": 0.2404,
+      "step": 9344
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 1.428114124678113,
+      "learning_rate": 4.647876271277257e-07,
+      "loss": 0.2391,
+      "step": 9376
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 1.3200951440851763,
+      "learning_rate": 4.6140012421847136e-07,
+      "loss": 0.2535,
+      "step": 9408
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 1.3868492152964986,
+      "learning_rate": 4.5801440277667235e-07,
+      "loss": 0.2483,
+      "step": 9440
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.2729900579595428,
+      "learning_rate": 4.5463061906066965e-07,
+      "loss": 0.2512,
+      "step": 9472
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.315198823460812,
+      "learning_rate": 4.5124892923937416e-07,
+      "loss": 0.2417,
+      "step": 9504
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 1.7120982404617975,
+      "learning_rate": 4.478694893850593e-07,
+      "loss": 0.2362,
+      "step": 9536
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.412290074923546,
+      "learning_rate": 4.4449245546615753e-07,
+      "loss": 0.2483,
+      "step": 9568
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.2470698026793279,
+      "learning_rate": 4.411179833400619e-07,
+      "loss": 0.2432,
+      "step": 9600
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.268429893461802,
+      "learning_rate": 4.377462287459337e-07,
+      "loss": 0.2428,
+      "step": 9632
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.2455579800684395,
+      "learning_rate": 4.343773472975139e-07,
+      "loss": 0.2508,
+      "step": 9664
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.228328713009981,
+      "learning_rate": 4.3101149447594163e-07,
+      "loss": 0.2551,
+      "step": 9696
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.2042503922389745,
+      "learning_rate": 4.276488256225787e-07,
+      "loss": 0.2541,
+      "step": 9728
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 1.2346699498129847,
+      "learning_rate": 4.242894959318395e-07,
+      "loss": 0.2461,
+      "step": 9760
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 1.3489561185627454,
+      "learning_rate": 4.209336604440294e-07,
+      "loss": 0.2477,
+      "step": 9792
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 1.6713827739937024,
+      "learning_rate": 4.175814740381879e-07,
+      "loss": 0.2458,
+      "step": 9824
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.3796544902936816,
+      "learning_rate": 4.1423309142494236e-07,
+      "loss": 0.2517,
+      "step": 9856
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.6289046211602507,
+      "learning_rate": 4.1088866713936633e-07,
+      "loss": 0.2411,
+      "step": 9888
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 1.4906278025262827,
+      "learning_rate": 4.0754835553384864e-07,
+      "loss": 0.2425,
+      "step": 9920
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.1884900865492198,
+      "learning_rate": 4.0421231077096844e-07,
+      "loss": 0.2587,
+      "step": 9952
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.329339394262938,
+      "learning_rate": 4.008806868163814e-07,
+      "loss": 0.2391,
+      "step": 9984
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 1.2186411235918218,
+      "learning_rate": 3.9755363743171265e-07,
+      "loss": 0.253,
+      "step": 10016
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 2.0559660633265047,
+      "learning_rate": 3.9423131616746187e-07,
+      "loss": 0.2566,
+      "step": 10048
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.255138693515569,
+      "learning_rate": 3.9091387635591533e-07,
+      "loss": 0.2404,
+      "step": 10080
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.5524707973995229,
+      "learning_rate": 3.8760147110406995e-07,
+      "loss": 0.2519,
+      "step": 10112
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 1.2244273291645265,
+      "learning_rate": 3.8429425328656674e-07,
+      "loss": 0.2388,
+      "step": 10144
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 1.438386617275495,
+      "learning_rate": 3.809923755386355e-07,
+      "loss": 0.25,
+      "step": 10176
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 1.5262712808405177,
+      "learning_rate": 3.7769599024905004e-07,
+      "loss": 0.2299,
+      "step": 10208
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 1.0721875435698476,
+      "learning_rate": 3.744052495530959e-07,
+      "loss": 0.2375,
+      "step": 10240
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 1.1626282358875817,
+      "learning_rate": 3.7112030532554806e-07,
+      "loss": 0.2497,
+      "step": 10272
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 1.3954184625846942,
+      "learning_rate": 3.6784130917366195e-07,
+      "loss": 0.242,
+      "step": 10304
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 1.3259939974154864,
+      "learning_rate": 3.64568412430177e-07,
+      "loss": 0.2516,
+      "step": 10336
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 1.73086784272557,
+      "learning_rate": 3.613017661463313e-07,
+      "loss": 0.2483,
+      "step": 10368
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 1.188961288223144,
+      "learning_rate": 3.5804152108489065e-07,
+      "loss": 0.2391,
+      "step": 10400
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 1.1246493355621157,
+      "learning_rate": 3.547878277131913e-07,
+      "loss": 0.2383,
+      "step": 10432
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 1.059964023169643,
+      "learning_rate": 3.515408361961941e-07,
+      "loss": 0.2404,
+      "step": 10464
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 1.70561149747635,
+      "learning_rate": 3.483006963895555e-07,
+      "loss": 0.2452,
+      "step": 10496
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.2969563700400484,
+      "learning_rate": 3.4506755783271045e-07,
+      "loss": 0.2324,
+      "step": 10528
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 1.2846755096320104,
+      "learning_rate": 3.418415697419712e-07,
+      "loss": 0.244,
+      "step": 10560
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 1.7188757741977305,
+      "learning_rate": 3.386228810036408e-07,
+      "loss": 0.2369,
+      "step": 10592
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 1.362077199933714,
+      "learning_rate": 3.3541164016714065e-07,
+      "loss": 0.2458,
+      "step": 10624
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 1.354641295840275,
+      "learning_rate": 3.3220799543815634e-07,
+      "loss": 0.2397,
+      "step": 10656
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 1.3277536016021265,
+      "learning_rate": 3.2901209467179637e-07,
+      "loss": 0.2458,
+      "step": 10688
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 1.3886060047726545,
+      "learning_rate": 3.2582408536576877e-07,
+      "loss": 0.2344,
+      "step": 10720
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 1.3601591408784948,
+      "learning_rate": 3.2264411465357335e-07,
+      "loss": 0.2343,
+      "step": 10752
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.1017573737076742,
+      "learning_rate": 3.194723292977123e-07,
+      "loss": 0.2442,
+      "step": 10784
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.4213916209193176,
+      "learning_rate": 3.1630887568291465e-07,
+      "loss": 0.2364,
+      "step": 10816
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 1.3035008616357522,
+      "learning_rate": 3.131538998093828e-07,
+      "loss": 0.2458,
+      "step": 10848
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 1.218412032577656,
+      "learning_rate": 3.1000754728605256e-07,
+      "loss": 0.2413,
+      "step": 10880
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 1.2325820939927188,
+      "learning_rate": 3.068699633238738e-07,
+      "loss": 0.2511,
+      "step": 10912
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5401850018534633,
+      "learning_rate": 3.037412927291083e-07,
+      "loss": 0.2461,
+      "step": 10944
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3586152389713673,
+      "learning_rate": 3.006216798966468e-07,
+      "loss": 0.2358,
+      "step": 10976
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 1.4011774529220307,
+      "learning_rate": 2.975112688033442e-07,
+      "loss": 0.2169,
+      "step": 11008
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 1.2241897731555507,
+      "learning_rate": 2.944102030013763e-07,
+      "loss": 0.2108,
+      "step": 11040
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 1.4027474158874935,
+      "learning_rate": 2.9131862561161293e-07,
+      "loss": 0.2293,
+      "step": 11072
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 1.4670817911133367,
+      "learning_rate": 2.882366793170133e-07,
+      "loss": 0.2244,
+      "step": 11104
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 1.3153219602513937,
+      "learning_rate": 2.8516450635604086e-07,
+      "loss": 0.22,
+      "step": 11136
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 1.2976761125367386,
+      "learning_rate": 2.821022485160991e-07,
+      "loss": 0.2097,
+      "step": 11168
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 1.3625162799781199,
+      "learning_rate": 2.7905004712698645e-07,
+      "loss": 0.2199,
+      "step": 11200
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 1.232550115651448,
+      "learning_rate": 2.7600804305437474e-07,
+      "loss": 0.2239,
+      "step": 11232
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 1.4796643786771864,
+      "learning_rate": 2.7297637669330847e-07,
+      "loss": 0.222,
+      "step": 11264
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 1.2946736681294901,
+      "learning_rate": 2.699551879617235e-07,
+      "loss": 0.2246,
+      "step": 11296
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 1.2068473533560813,
+      "learning_rate": 2.669446162939909e-07,
+      "loss": 0.2229,
+      "step": 11328
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 1.4805315280685087,
+      "learning_rate": 2.639448006344812e-07,
+      "loss": 0.2131,
+      "step": 11360
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.1871137311489093,
+      "learning_rate": 2.6095587943115227e-07,
+      "loss": 0.2235,
+      "step": 11392
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.088896036136479,
+      "learning_rate": 2.57977990629159e-07,
+      "loss": 0.2073,
+      "step": 11424
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 1.2960712344910867,
+      "learning_rate": 2.550112716644875e-07,
+      "loss": 0.2197,
+      "step": 11456
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 1.2204092718307542,
+      "learning_rate": 2.520558594576115e-07,
+      "loss": 0.2282,
+      "step": 11488
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 1.2693877027082432,
+      "learning_rate": 2.4911189040717357e-07,
+      "loss": 0.225,
+      "step": 11520
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 1.2846435895566266,
+      "learning_rate": 2.4617950038369035e-07,
+      "loss": 0.2234,
+      "step": 11552
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 1.2777271226205853,
+      "learning_rate": 2.432588247232811e-07,
+      "loss": 0.2211,
+      "step": 11584
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 1.528372242529096,
+      "learning_rate": 2.4034999822142166e-07,
+      "loss": 0.22,
+      "step": 11616
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 1.3339829276713877,
+      "learning_rate": 2.3745315512672397e-07,
+      "loss": 0.2195,
+      "step": 11648
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 1.3101509979598953,
+      "learning_rate": 2.345684291347403e-07,
+      "loss": 0.2159,
+      "step": 11680
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 1.3071577674707573,
+      "learning_rate": 2.3169595338179192e-07,
+      "loss": 0.2295,
+      "step": 11712
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 1.3186809416500118,
+      "learning_rate": 2.2883586043882548e-07,
+      "loss": 0.2133,
+      "step": 11744
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 1.5867314938269408,
+      "learning_rate": 2.259882823052941e-07,
+      "loss": 0.2316,
+      "step": 11776
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 1.1557431014242034,
+      "learning_rate": 2.2315335040306554e-07,
+      "loss": 0.2189,
+      "step": 11808
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.2736258434323458,
+      "learning_rate": 2.203311955703568e-07,
+      "loss": 0.2199,
+      "step": 11840
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 1.302216300423092,
+      "learning_rate": 2.1752194805569552e-07,
+      "loss": 0.229,
+      "step": 11872
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 1.3128201457087052,
+      "learning_rate": 2.147257375119087e-07,
+      "loss": 0.236,
+      "step": 11904
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 1.3748881212985564,
+      "learning_rate": 2.119426929901391e-07,
+      "loss": 0.2206,
+      "step": 11936
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 2.0921207372413435,
+      "learning_rate": 2.0917294293388966e-07,
+      "loss": 0.2117,
+      "step": 11968
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 1.2949118526726222,
+      "learning_rate": 2.0641661517309417e-07,
+      "loss": 0.2135,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.3415735498836403,
+      "learning_rate": 2.03673836918219e-07,
+      "loss": 0.2259,
+      "step": 12032
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.55429350265861,
+      "learning_rate": 2.00944734754392e-07,
+      "loss": 0.2279,
+      "step": 12064
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 1.2935837103909433,
+      "learning_rate": 1.9822943463555948e-07,
+      "loss": 0.2308,
+      "step": 12096
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 1.642310611966749,
+      "learning_rate": 1.9552806187867372e-07,
+      "loss": 0.2144,
+      "step": 12128
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 1.2465970815408216,
+      "learning_rate": 1.9284074115790932e-07,
+      "loss": 0.2198,
+      "step": 12160
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 1.6894912323452993,
+      "learning_rate": 1.9016759649890895e-07,
+      "loss": 0.2147,
+      "step": 12192
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 1.1571001402696899,
+      "learning_rate": 1.8750875127305977e-07,
+      "loss": 0.2149,
+      "step": 12224
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.311070700271489,
+      "learning_rate": 1.8486432819179892e-07,
+      "loss": 0.2135,
+      "step": 12256
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.358941411906666,
+      "learning_rate": 1.822344493009509e-07,
+      "loss": 0.2291,
+      "step": 12288
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 1.2572126595123219,
+      "learning_rate": 1.7961923597509387e-07,
+      "loss": 0.2253,
+      "step": 12320
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 1.4204877616087515,
+      "learning_rate": 1.7701880891195942e-07,
+      "loss": 0.212,
+      "step": 12352
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 1.3082239260119037,
+      "learning_rate": 1.744332881268607e-07,
+      "loss": 0.2258,
+      "step": 12384
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 1.3818606595114133,
+      "learning_rate": 1.7186279294715382e-07,
+      "loss": 0.2186,
+      "step": 12416
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 1.344313917268325,
+      "learning_rate": 1.6930744200673104e-07,
+      "loss": 0.2309,
+      "step": 12448
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 1.2849788562306779,
+      "learning_rate": 1.667673532405457e-07,
+      "loss": 0.2119,
+      "step": 12480
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 1.048703241818117,
+      "learning_rate": 1.6424264387916842e-07,
+      "loss": 0.2175,
+      "step": 12512
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 1.643116827546219,
+      "learning_rate": 1.6173343044337734e-07,
+      "loss": 0.2264,
+      "step": 12544
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 1.2754388516106783,
+      "learning_rate": 1.5923982873878012e-07,
+      "loss": 0.2296,
+      "step": 12576
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 1.2217192268295975,
+      "learning_rate": 1.567619538504696e-07,
+      "loss": 0.2281,
+      "step": 12608
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 1.4770776525365248,
+      "learning_rate": 1.542999201377119e-07,
+      "loss": 0.2277,
+      "step": 12640
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 1.642064071179986,
+      "learning_rate": 1.5185384122866897e-07,
+      "loss": 0.218,
+      "step": 12672
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.237204280837322,
+      "learning_rate": 1.4942383001515386e-07,
+      "loss": 0.2079,
+      "step": 12704
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.1715182674707414,
+      "learning_rate": 1.4700999864742136e-07,
+      "loss": 0.2124,
+      "step": 12736
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 1.770494939875621,
+      "learning_rate": 1.4461245852899128e-07,
+      "loss": 0.2046,
+      "step": 12768
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 1.2181121499687988,
+      "learning_rate": 1.4223132031150676e-07,
+      "loss": 0.2179,
+      "step": 12800
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 1.2327845797316905,
+      "learning_rate": 1.3986669388962819e-07,
+      "loss": 0.2202,
+      "step": 12832
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 1.5192364095540325,
+      "learning_rate": 1.375186883959613e-07,
+      "loss": 0.2187,
+      "step": 12864
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 1.1447367117093976,
+      "learning_rate": 1.3518741219601988e-07,
+      "loss": 0.2267,
+      "step": 12896
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.374708110513197,
+      "learning_rate": 1.3287297288322458e-07,
+      "loss": 0.2192,
+      "step": 12928
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.1547706075025737,
+      "learning_rate": 1.305754772739377e-07,
+      "loss": 0.2101,
+      "step": 12960
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 1.350330342693555,
+      "learning_rate": 1.2829503140253296e-07,
+      "loss": 0.2169,
+      "step": 12992
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 1.416668233872815,
+      "learning_rate": 1.2603174051650207e-07,
+      "loss": 0.2181,
+      "step": 13024
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 1.2796831245124296,
+      "learning_rate": 1.2378570907159697e-07,
+      "loss": 0.2264,
+      "step": 13056
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 1.5438983104227264,
+      "learning_rate": 1.215570407270095e-07,
+      "loss": 0.2233,
+      "step": 13088
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 1.7803269270190754,
+      "learning_rate": 1.1934583834058658e-07,
+      "loss": 0.2241,
+      "step": 13120
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.5471141725466007,
+      "learning_rate": 1.1715220396408426e-07,
+      "loss": 0.2124,
+      "step": 13152
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 1.1206628903783873,
+      "learning_rate": 1.1497623883845614e-07,
+      "loss": 0.2127,
+      "step": 13184
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 2.5095477739496967,
+      "learning_rate": 1.1281804338918239e-07,
+      "loss": 0.2282,
+      "step": 13216
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 1.3128197458740387,
+      "learning_rate": 1.1067771722163404e-07,
+      "loss": 0.2185,
+      "step": 13248
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 1.2471858850247612,
+      "learning_rate": 1.0855535911647673e-07,
+      "loss": 0.2185,
+      "step": 13280
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 1.655671236852773,
+      "learning_rate": 1.064510670251108e-07,
+      "loss": 0.2246,
+      "step": 13312
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 1.2165519973679901,
+      "learning_rate": 1.0436493806515128e-07,
+      "loss": 0.223,
+      "step": 13344
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 1.1834223459074134,
+      "learning_rate": 1.0229706851594561e-07,
+      "loss": 0.2188,
+      "step": 13376
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 1.5035939672617133,
+      "learning_rate": 1.0024755381412997e-07,
+      "loss": 0.2204,
+      "step": 13408
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 1.362765323113097,
+      "learning_rate": 9.821648854922481e-08,
+      "loss": 0.2165,
+      "step": 13440
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 1.4329165569522946,
+      "learning_rate": 9.620396645926937e-08,
+      "loss": 0.2104,
+      "step": 13472
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 1.2794493917175387,
+      "learning_rate": 9.421008042649514e-08,
+      "loss": 0.2225,
+      "step": 13504
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 1.365469705607083,
+      "learning_rate": 9.223492247303999e-08,
+      "loss": 0.2166,
+      "step": 13536
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 1.3658393916273586,
+      "learning_rate": 9.027858375670005e-08,
+      "loss": 0.2244,
+      "step": 13568
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 1.6134388977737084,
+      "learning_rate": 8.834115456672314e-08,
+      "loss": 0.2238,
+      "step": 13600
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 1.2747001650429752,
+      "learning_rate": 8.642272431964171e-08,
+      "loss": 0.2117,
+      "step": 13632
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 1.4495915191793898,
+      "learning_rate": 8.452338155514644e-08,
+      "loss": 0.2153,
+      "step": 13664
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.704239796998396,
+      "learning_rate": 8.264321393199902e-08,
+      "loss": 0.214,
+      "step": 13696
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.1540455435637955,
+      "learning_rate": 8.078230822398735e-08,
+      "loss": 0.2189,
+      "step": 13728
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 1.4264481560916344,
+      "learning_rate": 7.894075031592029e-08,
+      "loss": 0.2142,
+      "step": 13760
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 1.2771622178109003,
+      "learning_rate": 7.711862519966416e-08,
+      "loss": 0.2238,
+      "step": 13792
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 1.4176109439678235,
+      "learning_rate": 7.531601697022e-08,
+      "loss": 0.2141,
+      "step": 13824
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 1.211872373307708,
+      "learning_rate": 7.353300882184238e-08,
+      "loss": 0.2094,
+      "step": 13856
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 1.6208090587491066,
+      "learning_rate": 7.176968304420006e-08,
+      "loss": 0.213,
+      "step": 13888
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 1.4294182508163742,
+      "learning_rate": 7.002612101857769e-08,
+      "loss": 0.2206,
+      "step": 13920
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 1.5238939549044208,
+      "learning_rate": 6.830240321412067e-08,
+      "loss": 0.2187,
+      "step": 13952
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 1.4817796496161193,
+      "learning_rate": 6.65986091841203e-08,
+      "loss": 0.223,
+      "step": 13984
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.4428543645745906,
+      "learning_rate": 6.491481756234296e-08,
+      "loss": 0.2178,
+      "step": 14016
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.3986608111205634,
+      "learning_rate": 6.32511060594007e-08,
+      "loss": 0.2244,
+      "step": 14048
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 1.1779478103336172,
+      "learning_rate": 6.160755145916518e-08,
+      "loss": 0.2326,
+      "step": 14080
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 1.4661784823721757,
+      "learning_rate": 5.99842296152231e-08,
+      "loss": 0.2257,
+      "step": 14112
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 1.3997989298044267,
+      "learning_rate": 5.8381215447376006e-08,
+      "loss": 0.218,
+      "step": 14144
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 1.1966150734513934,
+      "learning_rate": 5.679858293818257e-08,
+      "loss": 0.2139,
+      "step": 14176
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 1.2975301799355876,
+      "learning_rate": 5.523640512954375e-08,
+      "loss": 0.2298,
+      "step": 14208
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.1520772784392557,
+      "learning_rate": 5.369475411933222e-08,
+      "loss": 0.2086,
+      "step": 14240
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.4920063917973507,
+      "learning_rate": 5.2173701058064454e-08,
+      "loss": 0.215,
+      "step": 14272
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 1.4418059613129284,
+      "learning_rate": 5.067331614561726e-08,
+      "loss": 0.2108,
+      "step": 14304
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 1.122573143556837,
+      "learning_rate": 4.9193668627988073e-08,
+      "loss": 0.2156,
+      "step": 14336
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 1.169213395405146,
+      "learning_rate": 4.7734826794098624e-08,
+      "loss": 0.2155,
+      "step": 14368
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 1.4739891927117594,
+      "learning_rate": 4.629685797264338e-08,
+      "loss": 0.2197,
+      "step": 14400
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 1.1061529994285666,
+      "learning_rate": 4.487982852898248e-08,
+      "loss": 0.2161,
+      "step": 14432
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.2665429377042383,
+      "learning_rate": 4.348380386207884e-08,
+      "loss": 0.2293,
+      "step": 14464
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.4251977400136069,
+      "learning_rate": 4.210884840147927e-08,
+      "loss": 0.219,
+      "step": 14496
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 1.3125295629014255,
+      "learning_rate": 4.075502560434158e-08,
+      "loss": 0.2215,
+      "step": 14528
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 1.6114888474605462,
+      "learning_rate": 3.942239795250546e-08,
+      "loss": 0.2141,
+      "step": 14560
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 1.3415946209746852,
+      "learning_rate": 3.8111026949609045e-08,
+      "loss": 0.2145,
+      "step": 14592
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 1.5169187816349006,
+      "learning_rate": 3.682097311825033e-08,
+      "loss": 0.2241,
+      "step": 14624
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 1.3176284198519965,
+      "learning_rate": 3.5552295997193834e-08,
+      "loss": 0.2238,
+      "step": 14656
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 1.5611137018278904,
+      "learning_rate": 3.430505413862284e-08,
+      "loss": 0.2029,
+      "step": 14688
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 1.4814939062116772,
+      "learning_rate": 3.307930510543705e-08,
+      "loss": 0.2073,
+      "step": 14720
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 1.4585161010377092,
+      "learning_rate": 3.187510546859623e-08,
+      "loss": 0.2158,
+      "step": 14752
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 1.3111001801067392,
+      "learning_rate": 3.069251080450863e-08,
+      "loss": 0.2114,
+      "step": 14784
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 1.3748879882896838,
+      "learning_rate": 2.953157569246656e-08,
+      "loss": 0.2191,
+      "step": 14816
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 1.2458399054987248,
+      "learning_rate": 2.8392353712127615e-08,
+      "loss": 0.2226,
+      "step": 14848
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 1.183457902413645,
+      "learning_rate": 2.7274897441041223e-08,
+      "loss": 0.2276,
+      "step": 14880
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 1.3996675489557702,
+      "learning_rate": 2.6179258452222687e-08,
+      "loss": 0.2223,
+      "step": 14912
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 1.3797514575768821,
+      "learning_rate": 2.5105487311772478e-08,
+      "loss": 0.2346,
+      "step": 14944
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 1.3453274139513625,
+      "learning_rate": 2.4053633576542833e-08,
+      "loss": 0.2148,
+      "step": 14976
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 1.4296834231597417,
+      "learning_rate": 2.3023745791850623e-08,
+      "loss": 0.2252,
+      "step": 15008
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 1.5820604044938296,
+      "learning_rate": 2.201587148923656e-08,
+      "loss": 0.2203,
+      "step": 15040
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 1.3679161695840207,
+      "learning_rate": 2.103005718427181e-08,
+      "loss": 0.2096,
+      "step": 15072
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.2454498587173481,
+      "learning_rate": 2.0066348374411122e-08,
+      "loss": 0.228,
+      "step": 15104
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.094395180196629,
+      "learning_rate": 1.912478953689306e-08,
+      "loss": 0.2183,
+      "step": 15136
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 1.2797588189588773,
+      "learning_rate": 1.8205424126687187e-08,
+      "loss": 0.2218,
+      "step": 15168
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 1.4533835000058788,
+      "learning_rate": 1.7308294574488347e-08,
+      "loss": 0.2226,
+      "step": 15200
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.4492805126695452,
+      "learning_rate": 1.6433442284758902e-08,
+      "loss": 0.2274,
+      "step": 15232
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.4350039162599688,
+      "learning_rate": 1.5580907633817475e-08,
+      "loss": 0.2282,
+      "step": 15264
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 1.1810113931037964,
+      "learning_rate": 1.475072996797555e-08,
+      "loss": 0.2224,
+      "step": 15296
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.1286561070757017,
+      "learning_rate": 1.3942947601721488e-08,
+      "loss": 0.215,
+      "step": 15328
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.1871769686911617,
+      "learning_rate": 1.3157597815952382e-08,
+      "loss": 0.2214,
+      "step": 15360
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 1.2452370435442608,
+      "learning_rate": 1.2394716856253374e-08,
+      "loss": 0.2122,
+      "step": 15392
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 1.2518679025330413,
+      "learning_rate": 1.1654339931224887e-08,
+      "loss": 0.217,
+      "step": 15424
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 1.252731324308369,
+      "learning_rate": 1.0936501210857651e-08,
+      "loss": 0.2317,
+      "step": 15456
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 1.3386257390126015,
+      "learning_rate": 1.0241233824955509e-08,
+      "loss": 0.2256,
+      "step": 15488
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 1.1313351017583362,
+      "learning_rate": 9.568569861606868e-09,
+      "loss": 0.2341,
+      "step": 15520
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 1.4449940727667887,
+      "learning_rate": 8.918540365703331e-09,
+      "loss": 0.2166,
+      "step": 15552
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 1.4530241900991612,
+      "learning_rate": 8.291175337506894e-09,
+      "loss": 0.2408,
+      "step": 15584
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 1.2609793071770357,
+      "learning_rate": 7.68650373126567e-09,
+      "loss": 0.2046,
+      "step": 15616
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 1.1344728672758062,
+      "learning_rate": 7.10455345387756e-09,
+      "loss": 0.2196,
+      "step": 15648
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 1.5048112445610096,
+      "learning_rate": 6.545351363601959e-09,
+      "loss": 0.2214,
+      "step": 15680
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 1.4050748695357576,
+      "learning_rate": 6.00892326882052e-09,
+      "loss": 0.2265,
+      "step": 15712
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 1.1997477163250476,
+      "learning_rate": 5.495293926845834e-09,
+      "loss": 0.2163,
+      "step": 15744
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.3144891186853807,
+      "learning_rate": 5.00448704277906e-09,
+      "loss": 0.224,
+      "step": 15776
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.353851004486482,
+      "learning_rate": 4.536525268415581e-09,
+      "loss": 0.2127,
+      "step": 15808
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 1.4192328708826423,
+      "learning_rate": 4.091430201199841e-09,
+      "loss": 0.221,
+      "step": 15840
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 1.3274920629279923,
+      "learning_rate": 3.6692223832283653e-09,
+      "loss": 0.2137,
+      "step": 15872
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 1.2096820045248131,
+      "learning_rate": 3.2699213003019588e-09,
+      "loss": 0.2164,
+      "step": 15904
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 1.4949483678866275,
+      "learning_rate": 2.8935453810260413e-09,
+      "loss": 0.211,
+      "step": 15936
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 1.4480264990764071,
+      "learning_rate": 2.5401119959606033e-09,
+      "loss": 0.2219,
+      "step": 15968
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 1.3984591809802007,
+      "learning_rate": 2.209637456817848e-09,
+      "loss": 0.2187,
+      "step": 16000
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 1.2138235012481149,
+      "learning_rate": 1.9021370157100703e-09,
+      "loss": 0.2044,
+      "step": 16032
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 1.4196275071259965,
+      "learning_rate": 1.6176248644453883e-09,
+      "loss": 0.2206,
+      "step": 16064
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 1.4494340877185368,
+      "learning_rate": 1.3561141338726545e-09,
+      "loss": 0.2155,
+      "step": 16096
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 1.3684818624338524,
+      "learning_rate": 1.117616893275719e-09,
+      "loss": 0.228,
+      "step": 16128
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 4.300044658083074,
+      "learning_rate": 9.02144149816153e-10,
+      "loss": 0.2138,
+      "step": 16160
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 1.4879340606023383,
+      "learning_rate": 7.097058480255991e-10,
+      "loss": 0.2135,
+      "step": 16192
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.628757008031087,
+      "learning_rate": 5.403108693462499e-10,
+      "loss": 0.2169,
+      "step": 16224
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 1.355596318247962,
+      "learning_rate": 3.9396703172150936e-10,
+      "loss": 0.212,
+      "step": 16256
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 1.1638938575418796,
+      "learning_rate": 2.706810892348921e-10,
+      "loss": 0.2177,
+      "step": 16288
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 1.2545697493468788,
+      "learning_rate": 1.704587317983286e-10,
+      "loss": 0.2226,
+      "step": 16320
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 1.2958637026668016,
+      "learning_rate": 9.330458488959746e-11,
+      "loss": 0.2206,
+      "step": 16352
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 1.1646489691129969,
+      "learning_rate": 3.922220933882947e-11,
+      "loss": 0.2219,
+      "step": 16384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.126290495132723,
+      "learning_rate": 8.214101164305543e-12,
+      "loss": 0.2393,
+      "step": 16416
+    }
+  ],
+  "logging_steps": 32,
+  "max_steps": 16443,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 3289,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed319e0150314b9825b1146a55d7939664d34e1733940c4acd1556532142553
+size 7544