Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+0413-7B/tokenizer.json filter=lfs diff=lfs merge=lfs -text

0413-7B/added_tokens.json

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

0413-7B/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/home/xulilin/Qwen-2.5-coder-instruct-7b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

0413-7B/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": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.0"
+}

0413-7B/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d5c1ac52c19c6cd3a65868c1134922d47bed1890ee2ee702f8a383ad8753594
+size 4877660776

0413-7B/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784a5c49bc3dbbe13944d4dfbbd6e0abc2647292042cbc4627bc65a4f625f3b9
+size 4932751008

0413-7B/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e5657d34586ffe30be64e991a294edeb237eae675528a77274536908739267
+size 4330865200

0413-7B/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edab27d5f5d5d1469e4cd50bced27a9db02178f354e95ff9385cf72aeba48021
+size 1089994880

0413-7B/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

0413-7B/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}

0413-7B/tokenizer.json

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

0413-7B/tokenizer_config.json

@@ -0,0 +1,198 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_start|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation": true,
+  "unk_token": null
+}

0413-7B/trainer_state.json

@@ -0,0 +1,3318 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9952,
+  "eval_steps": 500,
+  "global_step": 468,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0064,
+      "grad_norm": 6.867237567901611,
+      "learning_rate": 0.0,
+      "loss": 0.9866,
+      "step": 1
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": 4.297928333282471,
+      "learning_rate": 7.525749891599529e-06,
+      "loss": 0.4356,
+      "step": 2
+    },
+    {
+      "epoch": 0.0192,
+      "grad_norm": 4.348770618438721,
+      "learning_rate": 1.192803136799156e-05,
+      "loss": 0.4451,
+      "step": 3
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 2.1662685871124268,
+      "learning_rate": 1.5051499783199057e-05,
+      "loss": 0.3057,
+      "step": 4
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 1.8455146551132202,
+      "learning_rate": 1.7474250108400467e-05,
+      "loss": 0.1382,
+      "step": 5
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 0.8519665598869324,
+      "learning_rate": 1.945378125959109e-05,
+      "loss": 0.0833,
+      "step": 6
+    },
+    {
+      "epoch": 0.0448,
+      "grad_norm": 0.9801745414733887,
+      "learning_rate": 2.1127451000356418e-05,
+      "loss": 0.0689,
+      "step": 7
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 0.7171750664710999,
+      "learning_rate": 2.2577249674798584e-05,
+      "loss": 0.0455,
+      "step": 8
+    },
+    {
+      "epoch": 0.0576,
+      "grad_norm": 0.6855205297470093,
+      "learning_rate": 2.385606273598312e-05,
+      "loss": 0.0393,
+      "step": 9
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.7904754877090454,
+      "learning_rate": 2.4999999999999998e-05,
+      "loss": 0.0292,
+      "step": 10
+    },
+    {
+      "epoch": 0.0704,
+      "grad_norm": 1.4618746042251587,
+      "learning_rate": 2.6034817128955623e-05,
+      "loss": 0.0263,
+      "step": 11
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 0.4559214413166046,
+      "learning_rate": 2.6979531151190617e-05,
+      "loss": 0.0192,
+      "step": 12
+    },
+    {
+      "epoch": 0.0832,
+      "grad_norm": 0.45592865347862244,
+      "learning_rate": 2.7848583807670913e-05,
+      "loss": 0.0163,
+      "step": 13
+    },
+    {
+      "epoch": 0.0896,
+      "grad_norm": 0.5701196193695068,
+      "learning_rate": 2.8653200891955945e-05,
+      "loss": 0.0141,
+      "step": 14
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.308474063873291,
+      "learning_rate": 2.940228147639203e-05,
+      "loss": 0.0105,
+      "step": 15
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 0.5183830261230469,
+      "learning_rate": 3.0102999566398115e-05,
+      "loss": 0.0105,
+      "step": 16
+    },
+    {
+      "epoch": 0.1088,
+      "grad_norm": 0.8100266456604004,
+      "learning_rate": 3.076122303445685e-05,
+      "loss": 0.0138,
+      "step": 17
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 0.44762006402015686,
+      "learning_rate": 3.1381812627582646e-05,
+      "loss": 0.0078,
+      "step": 18
+    },
+    {
+      "epoch": 0.1216,
+      "grad_norm": 0.2692151963710785,
+      "learning_rate": 3.1968840023820715e-05,
+      "loss": 0.0061,
+      "step": 19
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.2967744469642639,
+      "learning_rate": 3.2525749891599525e-05,
+      "loss": 0.0066,
+      "step": 20
+    },
+    {
+      "epoch": 0.1344,
+      "grad_norm": 0.3176949620246887,
+      "learning_rate": 3.305548236834798e-05,
+      "loss": 0.0051,
+      "step": 21
+    },
+    {
+      "epoch": 0.1408,
+      "grad_norm": 0.35775479674339294,
+      "learning_rate": 3.3560567020555153e-05,
+      "loss": 0.0039,
+      "step": 22
+    },
+    {
+      "epoch": 0.1472,
+      "grad_norm": 0.28370487689971924,
+      "learning_rate": 3.404319590043982e-05,
+      "loss": 0.0036,
+      "step": 23
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 0.3625766336917877,
+      "learning_rate": 3.450528104279015e-05,
+      "loss": 0.0018,
+      "step": 24
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8744438886642456,
+      "learning_rate": 3.4948500216800935e-05,
+      "loss": 0.0035,
+      "step": 25
+    },
+    {
+      "epoch": 0.1664,
+      "grad_norm": 0.34261637926101685,
+      "learning_rate": 3.537433369927044e-05,
+      "loss": 0.0036,
+      "step": 26
+    },
+    {
+      "epoch": 0.1728,
+      "grad_norm": 0.18783028423786163,
+      "learning_rate": 3.578409410397468e-05,
+      "loss": 0.0028,
+      "step": 27
+    },
+    {
+      "epoch": 0.1792,
+      "grad_norm": 0.4699239432811737,
+      "learning_rate": 3.6178950783555475e-05,
+      "loss": 0.0079,
+      "step": 28
+    },
+    {
+      "epoch": 0.1856,
+      "grad_norm": 1.2712277173995972,
+      "learning_rate": 3.65599499474739e-05,
+      "loss": 0.011,
+      "step": 29
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.3225037753582001,
+      "learning_rate": 3.6928031367991554e-05,
+      "loss": 0.0044,
+      "step": 30
+    },
+    {
+      "epoch": 0.1984,
+      "grad_norm": 1.0227000713348389,
+      "learning_rate": 3.728404234585681e-05,
+      "loss": 0.0152,
+      "step": 31
+    },
+    {
+      "epoch": 0.2048,
+      "grad_norm": 0.439948707818985,
+      "learning_rate": 3.762874945799765e-05,
+      "loss": 0.0049,
+      "step": 32
+    },
+    {
+      "epoch": 0.2112,
+      "grad_norm": 0.36300235986709595,
+      "learning_rate": 3.796284849694718e-05,
+      "loss": 0.0064,
+      "step": 33
+    },
+    {
+      "epoch": 0.2176,
+      "grad_norm": 0.7431035041809082,
+      "learning_rate": 3.8286972926056376e-05,
+      "loss": 0.0064,
+      "step": 34
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.5639030933380127,
+      "learning_rate": 3.8601701108756885e-05,
+      "loss": 0.0044,
+      "step": 35
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 2.061075448989868,
+      "learning_rate": 3.890756251918218e-05,
+      "loss": 0.0587,
+      "step": 36
+    },
+    {
+      "epoch": 0.2368,
+      "grad_norm": 0.2774636447429657,
+      "learning_rate": 3.920504310167487e-05,
+      "loss": 0.0037,
+      "step": 37
+    },
+    {
+      "epoch": 0.2432,
+      "grad_norm": 0.1626257449388504,
+      "learning_rate": 3.949458991542025e-05,
+      "loss": 0.0018,
+      "step": 38
+    },
+    {
+      "epoch": 0.2496,
+      "grad_norm": 0.21992048621177673,
+      "learning_rate": 3.977661517566247e-05,
+      "loss": 0.0023,
+      "step": 39
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.505625307559967,
+      "learning_rate": 4.005149978319905e-05,
+      "loss": 0.0038,
+      "step": 40
+    },
+    {
+      "epoch": 0.2624,
+      "grad_norm": 0.08550506085157394,
+      "learning_rate": 4.031959641799338e-05,
+      "loss": 0.0009,
+      "step": 41
+    },
+    {
+      "epoch": 0.2688,
+      "grad_norm": 0.25269952416419983,
+      "learning_rate": 4.058123225994751e-05,
+      "loss": 0.0018,
+      "step": 42
+    },
+    {
+      "epoch": 0.2752,
+      "grad_norm": 0.22432880103588104,
+      "learning_rate": 4.0836711389489654e-05,
+      "loss": 0.005,
+      "step": 43
+    },
+    {
+      "epoch": 0.2816,
+      "grad_norm": 0.07769381999969482,
+      "learning_rate": 4.108631691215468e-05,
+      "loss": 0.0008,
+      "step": 44
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.17553609609603882,
+      "learning_rate": 4.133031284438358e-05,
+      "loss": 0.0009,
+      "step": 45
+    },
+    {
+      "epoch": 0.2944,
+      "grad_norm": 0.18802885711193085,
+      "learning_rate": 4.156894579203935e-05,
+      "loss": 0.0019,
+      "step": 46
+    },
+    {
+      "epoch": 0.3008,
+      "grad_norm": 0.18790943920612335,
+      "learning_rate": 4.180244644839293e-05,
+      "loss": 0.0043,
+      "step": 47
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 0.271170973777771,
+      "learning_rate": 4.203103093438968e-05,
+      "loss": 0.0014,
+      "step": 48
+    },
+    {
+      "epoch": 0.3136,
+      "grad_norm": 0.16689293086528778,
+      "learning_rate": 4.2254902000712836e-05,
+      "loss": 0.0018,
+      "step": 49
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.22925345599651337,
+      "learning_rate": 4.247425010840046e-05,
+      "loss": 0.0032,
+      "step": 50
+    },
+    {
+      "epoch": 0.3264,
+      "grad_norm": 0.1010027527809143,
+      "learning_rate": 4.2689254402448405e-05,
+      "loss": 0.0013,
+      "step": 51
+    },
+    {
+      "epoch": 0.3328,
+      "grad_norm": 0.12347017228603363,
+      "learning_rate": 4.290008359086998e-05,
+      "loss": 0.0012,
+      "step": 52
+    },
+    {
+      "epoch": 0.3392,
+      "grad_norm": 0.11815085262060165,
+      "learning_rate": 4.310689674001973e-05,
+      "loss": 0.001,
+      "step": 53
+    },
+    {
+      "epoch": 0.3456,
+      "grad_norm": 0.06566538661718369,
+      "learning_rate": 4.330984399557421e-05,
+      "loss": 0.0005,
+      "step": 54
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.017934823408722878,
+      "learning_rate": 4.350906723735609e-05,
+      "loss": 0.0002,
+      "step": 55
+    },
+    {
+      "epoch": 0.3584,
+      "grad_norm": 0.03432954475283623,
+      "learning_rate": 4.370470067515501e-05,
+      "loss": 0.0002,
+      "step": 56
+    },
+    {
+      "epoch": 0.3648,
+      "grad_norm": 0.1542041003704071,
+      "learning_rate": 4.3896871391812285e-05,
+      "loss": 0.0007,
+      "step": 57
+    },
+    {
+      "epoch": 0.3712,
+      "grad_norm": 0.4286952018737793,
+      "learning_rate": 4.408569983907343e-05,
+      "loss": 0.0013,
+      "step": 58
+    },
+    {
+      "epoch": 0.3776,
+      "grad_norm": 0.14198176562786102,
+      "learning_rate": 4.42713002910536e-05,
+      "loss": 0.0007,
+      "step": 59
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.0563991442322731,
+      "learning_rate": 4.445378125959108e-05,
+      "loss": 0.0002,
+      "step": 60
+    },
+    {
+      "epoch": 0.3904,
+      "grad_norm": 0.10293157398700714,
+      "learning_rate": 4.463324587526917e-05,
+      "loss": 0.0005,
+      "step": 61
+    },
+    {
+      "epoch": 0.3968,
+      "grad_norm": 0.33900725841522217,
+      "learning_rate": 4.4809792237456346e-05,
+      "loss": 0.0005,
+      "step": 62
+    },
+    {
+      "epoch": 0.4032,
+      "grad_norm": 0.3335053622722626,
+      "learning_rate": 4.498351373633954e-05,
+      "loss": 0.0009,
+      "step": 63
+    },
+    {
+      "epoch": 0.4096,
+      "grad_norm": 0.025870727375149727,
+      "learning_rate": 4.515449934959717e-05,
+      "loss": 0.0002,
+      "step": 64
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 1.6030328273773193,
+      "learning_rate": 4.532283391607138e-05,
+      "loss": 0.0193,
+      "step": 65
+    },
+    {
+      "epoch": 0.4224,
+      "grad_norm": 0.7240369915962219,
+      "learning_rate": 4.548859838854671e-05,
+      "loss": 0.0074,
+      "step": 66
+    },
+    {
+      "epoch": 0.4288,
+      "grad_norm": 0.15157511830329895,
+      "learning_rate": 4.565187006752065e-05,
+      "loss": 0.0009,
+      "step": 67
+    },
+    {
+      "epoch": 0.4352,
+      "grad_norm": 0.13376882672309875,
+      "learning_rate": 4.581272281765591e-05,
+      "loss": 0.0024,
+      "step": 68
+    },
+    {
+      "epoch": 0.4416,
+      "grad_norm": 1.1460976600646973,
+      "learning_rate": 4.597122726843138e-05,
+      "loss": 0.0114,
+      "step": 69
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.10029949247837067,
+      "learning_rate": 4.612745100035642e-05,
+      "loss": 0.0006,
+      "step": 70
+    },
+    {
+      "epoch": 0.4544,
+      "grad_norm": 0.07657619565725327,
+      "learning_rate": 4.628145871797688e-05,
+      "loss": 0.0007,
+      "step": 71
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 5.547841548919678,
+      "learning_rate": 4.643331241078171e-05,
+      "loss": 0.0488,
+      "step": 72
+    },
+    {
+      "epoch": 0.4672,
+      "grad_norm": 0.2765743136405945,
+      "learning_rate": 4.658307150301139e-05,
+      "loss": 0.0026,
+      "step": 73
+    },
+    {
+      "epoch": 0.4736,
+      "grad_norm": 0.19510500133037567,
+      "learning_rate": 4.67307929932744e-05,
+      "loss": 0.0031,
+      "step": 74
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.43489667773246765,
+      "learning_rate": 4.687653158479249e-05,
+      "loss": 0.0095,
+      "step": 75
+    },
+    {
+      "epoch": 0.4864,
+      "grad_norm": 0.1395997703075409,
+      "learning_rate": 4.702033980701978e-05,
+      "loss": 0.0027,
+      "step": 76
+    },
+    {
+      "epoch": 0.4928,
+      "grad_norm": 0.3395584225654602,
+      "learning_rate": 4.716226812931204e-05,
+      "loss": 0.0043,
+      "step": 77
+    },
+    {
+      "epoch": 0.4992,
+      "grad_norm": 0.12132924795150757,
+      "learning_rate": 4.7302365067262006e-05,
+      "loss": 0.0026,
+      "step": 78
+    },
+    {
+      "epoch": 0.5056,
+      "grad_norm": 0.10817684978246689,
+      "learning_rate": 4.744067728226103e-05,
+      "loss": 0.0019,
+      "step": 79
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.14686818420886993,
+      "learning_rate": 4.757724967479858e-05,
+      "loss": 0.0021,
+      "step": 80
+    },
+    {
+      "epoch": 0.5184,
+      "grad_norm": 0.15216055512428284,
+      "learning_rate": 4.771212547196624e-05,
+      "loss": 0.0011,
+      "step": 81
+    },
+    {
+      "epoch": 0.5248,
+      "grad_norm": 0.0684371069073677,
+      "learning_rate": 4.7845346309592914e-05,
+      "loss": 0.0008,
+      "step": 82
+    },
+    {
+      "epoch": 0.5312,
+      "grad_norm": 0.0808420404791832,
+      "learning_rate": 4.7976952309401844e-05,
+      "loss": 0.0014,
+      "step": 83
+    },
+    {
+      "epoch": 0.5376,
+      "grad_norm": 0.10134042799472809,
+      "learning_rate": 4.810698215154703e-05,
+      "loss": 0.0005,
+      "step": 84
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.12530562281608582,
+      "learning_rate": 4.823547314285732e-05,
+      "loss": 0.0011,
+      "step": 85
+    },
+    {
+      "epoch": 0.5504,
+      "grad_norm": 0.04818332567811012,
+      "learning_rate": 4.836246128108918e-05,
+      "loss": 0.0002,
+      "step": 86
+    },
+    {
+      "epoch": 0.5568,
+      "grad_norm": 0.02247856929898262,
+      "learning_rate": 4.8487981315465456e-05,
+      "loss": 0.0002,
+      "step": 87
+    },
+    {
+      "epoch": 0.5632,
+      "grad_norm": 0.07910199463367462,
+      "learning_rate": 4.8612066803754214e-05,
+      "loss": 0.0013,
+      "step": 88
+    },
+    {
+      "epoch": 0.5696,
+      "grad_norm": 0.41085657477378845,
+      "learning_rate": 4.873475016612281e-05,
+      "loss": 0.0015,
+      "step": 89
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.04667409881949425,
+      "learning_rate": 4.885606273598312e-05,
+      "loss": 0.0004,
+      "step": 90
+    },
+    {
+      "epoch": 0.5824,
+      "grad_norm": 0.0651155561208725,
+      "learning_rate": 4.897603480802733e-05,
+      "loss": 0.0004,
+      "step": 91
+    },
+    {
+      "epoch": 0.5888,
+      "grad_norm": 0.653387188911438,
+      "learning_rate": 4.909469568363888e-05,
+      "loss": 0.0041,
+      "step": 92
+    },
+    {
+      "epoch": 0.5952,
+      "grad_norm": 0.6051435470581055,
+      "learning_rate": 4.9212073713848375e-05,
+      "loss": 0.0015,
+      "step": 93
+    },
+    {
+      "epoch": 0.6016,
+      "grad_norm": 2.0199849605560303,
+      "learning_rate": 4.932819633999246e-05,
+      "loss": 0.0214,
+      "step": 94
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.6304452419281006,
+      "learning_rate": 4.9443090132221186e-05,
+      "loss": 0.0286,
+      "step": 95
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 1.3716986179351807,
+      "learning_rate": 4.9556780825989205e-05,
+      "loss": 0.0332,
+      "step": 96
+    },
+    {
+      "epoch": 0.6208,
+      "grad_norm": 0.9438934922218323,
+      "learning_rate": 4.9669293356656114e-05,
+      "loss": 0.0168,
+      "step": 97
+    },
+    {
+      "epoch": 0.6272,
+      "grad_norm": 0.4411373436450958,
+      "learning_rate": 4.978065189231237e-05,
+      "loss": 0.0081,
+      "step": 98
+    },
+    {
+      "epoch": 0.6336,
+      "grad_norm": 0.23029357194900513,
+      "learning_rate": 4.989087986493874e-05,
+      "loss": 0.0047,
+      "step": 99
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.1586022675037384,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 0.0036,
+      "step": 100
+    },
+    {
+      "epoch": 0.6464,
+      "grad_norm": 0.20412147045135498,
+      "learning_rate": 5e-05,
+      "loss": 0.0042,
+      "step": 101
+    },
+    {
+      "epoch": 0.6528,
+      "grad_norm": 0.14534208178520203,
+      "learning_rate": 4.986413043478261e-05,
+      "loss": 0.0034,
+      "step": 102
+    },
+    {
+      "epoch": 0.6592,
+      "grad_norm": 0.20073381066322327,
+      "learning_rate": 4.9728260869565216e-05,
+      "loss": 0.004,
+      "step": 103
+    },
+    {
+      "epoch": 0.6656,
+      "grad_norm": 0.05340602621436119,
+      "learning_rate": 4.959239130434783e-05,
+      "loss": 0.0011,
+      "step": 104
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.14157666265964508,
+      "learning_rate": 4.945652173913044e-05,
+      "loss": 0.0017,
+      "step": 105
+    },
+    {
+      "epoch": 0.6784,
+      "grad_norm": 0.146461620926857,
+      "learning_rate": 4.932065217391305e-05,
+      "loss": 0.0015,
+      "step": 106
+    },
+    {
+      "epoch": 0.6848,
+      "grad_norm": 0.19775742292404175,
+      "learning_rate": 4.918478260869566e-05,
+      "loss": 0.0033,
+      "step": 107
+    },
+    {
+      "epoch": 0.6912,
+      "grad_norm": 0.09102778881788254,
+      "learning_rate": 4.904891304347826e-05,
+      "loss": 0.0021,
+      "step": 108
+    },
+    {
+      "epoch": 0.6976,
+      "grad_norm": 0.1514146775007248,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.001,
+      "step": 109
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.19479773938655853,
+      "learning_rate": 4.8777173913043476e-05,
+      "loss": 0.0007,
+      "step": 110
+    },
+    {
+      "epoch": 0.7104,
+      "grad_norm": 0.036175232380628586,
+      "learning_rate": 4.8641304347826086e-05,
+      "loss": 0.0003,
+      "step": 111
+    },
+    {
+      "epoch": 0.7168,
+      "grad_norm": 0.1777254194021225,
+      "learning_rate": 4.8505434782608696e-05,
+      "loss": 0.001,
+      "step": 112
+    },
+    {
+      "epoch": 0.7232,
+      "grad_norm": 0.10440216213464737,
+      "learning_rate": 4.836956521739131e-05,
+      "loss": 0.0007,
+      "step": 113
+    },
+    {
+      "epoch": 0.7296,
+      "grad_norm": 0.06505996733903885,
+      "learning_rate": 4.823369565217392e-05,
+      "loss": 0.0012,
+      "step": 114
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.1114392951130867,
+      "learning_rate": 4.809782608695653e-05,
+      "loss": 0.0019,
+      "step": 115
+    },
+    {
+      "epoch": 0.7424,
+      "grad_norm": 0.07420018315315247,
+      "learning_rate": 4.796195652173913e-05,
+      "loss": 0.0004,
+      "step": 116
+    },
+    {
+      "epoch": 0.7488,
+      "grad_norm": 0.1657446026802063,
+      "learning_rate": 4.782608695652174e-05,
+      "loss": 0.0007,
+      "step": 117
+    },
+    {
+      "epoch": 0.7552,
+      "grad_norm": 0.06575703620910645,
+      "learning_rate": 4.7690217391304345e-05,
+      "loss": 0.0005,
+      "step": 118
+    },
+    {
+      "epoch": 0.7616,
+      "grad_norm": 0.1363728791475296,
+      "learning_rate": 4.7554347826086956e-05,
+      "loss": 0.0022,
+      "step": 119
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.056244850158691406,
+      "learning_rate": 4.741847826086957e-05,
+      "loss": 0.0005,
+      "step": 120
+    },
+    {
+      "epoch": 0.7744,
+      "grad_norm": 0.051151975989341736,
+      "learning_rate": 4.7282608695652177e-05,
+      "loss": 0.0005,
+      "step": 121
+    },
+    {
+      "epoch": 0.7808,
+      "grad_norm": 0.1531762033700943,
+      "learning_rate": 4.714673913043479e-05,
+      "loss": 0.001,
+      "step": 122
+    },
+    {
+      "epoch": 0.7872,
+      "grad_norm": 0.054743390530347824,
+      "learning_rate": 4.701086956521739e-05,
+      "loss": 0.0012,
+      "step": 123
+    },
+    {
+      "epoch": 0.7936,
+      "grad_norm": 0.04762500151991844,
+      "learning_rate": 4.6875e-05,
+      "loss": 0.0021,
+      "step": 124
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2215579748153687,
+      "learning_rate": 4.673913043478261e-05,
+      "loss": 0.0003,
+      "step": 125
+    },
+    {
+      "epoch": 0.8064,
+      "grad_norm": 0.011630098335444927,
+      "learning_rate": 4.660326086956522e-05,
+      "loss": 0.0001,
+      "step": 126
+    },
+    {
+      "epoch": 0.8128,
+      "grad_norm": 0.03518148511648178,
+      "learning_rate": 4.646739130434783e-05,
+      "loss": 0.0003,
+      "step": 127
+    },
+    {
+      "epoch": 0.8192,
+      "grad_norm": 0.8202972412109375,
+      "learning_rate": 4.6331521739130436e-05,
+      "loss": 0.0015,
+      "step": 128
+    },
+    {
+      "epoch": 0.8256,
+      "grad_norm": 0.11286929994821548,
+      "learning_rate": 4.6195652173913046e-05,
+      "loss": 0.0065,
+      "step": 129
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.1009194478392601,
+      "learning_rate": 4.6059782608695657e-05,
+      "loss": 0.0013,
+      "step": 130
+    },
+    {
+      "epoch": 0.8384,
+      "grad_norm": 0.045929718762636185,
+      "learning_rate": 4.592391304347826e-05,
+      "loss": 0.0012,
+      "step": 131
+    },
+    {
+      "epoch": 0.8448,
+      "grad_norm": 0.12528342008590698,
+      "learning_rate": 4.578804347826087e-05,
+      "loss": 0.0024,
+      "step": 132
+    },
+    {
+      "epoch": 0.8512,
+      "grad_norm": 0.03925907239317894,
+      "learning_rate": 4.565217391304348e-05,
+      "loss": 0.0012,
+      "step": 133
+    },
+    {
+      "epoch": 0.8576,
+      "grad_norm": 0.0898917019367218,
+      "learning_rate": 4.551630434782609e-05,
+      "loss": 0.0028,
+      "step": 134
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.07810714095830917,
+      "learning_rate": 4.53804347826087e-05,
+      "loss": 0.0015,
+      "step": 135
+    },
+    {
+      "epoch": 0.8704,
+      "grad_norm": 1.106676459312439,
+      "learning_rate": 4.5244565217391305e-05,
+      "loss": 0.0021,
+      "step": 136
+    },
+    {
+      "epoch": 0.8768,
+      "grad_norm": 0.03257442265748978,
+      "learning_rate": 4.5108695652173916e-05,
+      "loss": 0.0005,
+      "step": 137
+    },
+    {
+      "epoch": 0.8832,
+      "grad_norm": 0.20705817639827728,
+      "learning_rate": 4.4972826086956526e-05,
+      "loss": 0.0012,
+      "step": 138
+    },
+    {
+      "epoch": 0.8896,
+      "grad_norm": 0.16381816565990448,
+      "learning_rate": 4.483695652173913e-05,
+      "loss": 0.004,
+      "step": 139
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.2158195823431015,
+      "learning_rate": 4.470108695652174e-05,
+      "loss": 0.0021,
+      "step": 140
+    },
+    {
+      "epoch": 0.9024,
+      "grad_norm": 0.2646850049495697,
+      "learning_rate": 4.456521739130435e-05,
+      "loss": 0.0015,
+      "step": 141
+    },
+    {
+      "epoch": 0.9088,
+      "grad_norm": 0.19215179979801178,
+      "learning_rate": 4.442934782608696e-05,
+      "loss": 0.0014,
+      "step": 142
+    },
+    {
+      "epoch": 0.9152,
+      "grad_norm": 0.021945759654045105,
+      "learning_rate": 4.429347826086957e-05,
+      "loss": 0.0007,
+      "step": 143
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 0.04152447730302811,
+      "learning_rate": 4.4157608695652175e-05,
+      "loss": 0.0009,
+      "step": 144
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.21016669273376465,
+      "learning_rate": 4.4021739130434786e-05,
+      "loss": 0.0016,
+      "step": 145
+    },
+    {
+      "epoch": 0.9344,
+      "grad_norm": 0.23413971066474915,
+      "learning_rate": 4.388586956521739e-05,
+      "loss": 0.0017,
+      "step": 146
+    },
+    {
+      "epoch": 0.9408,
+      "grad_norm": 0.05454641208052635,
+      "learning_rate": 4.375e-05,
+      "loss": 0.0012,
+      "step": 147
+    },
+    {
+      "epoch": 0.9472,
+      "grad_norm": 0.04505091905593872,
+      "learning_rate": 4.361413043478261e-05,
+      "loss": 0.0005,
+      "step": 148
+    },
+    {
+      "epoch": 0.9536,
+      "grad_norm": 0.025377271696925163,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.0005,
+      "step": 149
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.04593677818775177,
+      "learning_rate": 4.334239130434783e-05,
+      "loss": 0.0007,
+      "step": 150
+    },
+    {
+      "epoch": 0.9664,
+      "grad_norm": 0.12261521071195602,
+      "learning_rate": 4.3206521739130434e-05,
+      "loss": 0.0012,
+      "step": 151
+    },
+    {
+      "epoch": 0.9728,
+      "grad_norm": 0.14345598220825195,
+      "learning_rate": 4.3070652173913045e-05,
+      "loss": 0.0008,
+      "step": 152
+    },
+    {
+      "epoch": 0.9792,
+      "grad_norm": 0.2001795768737793,
+      "learning_rate": 4.2934782608695655e-05,
+      "loss": 0.0003,
+      "step": 153
+    },
+    {
+      "epoch": 0.9856,
+      "grad_norm": 0.11944042891263962,
+      "learning_rate": 4.279891304347826e-05,
+      "loss": 0.0004,
+      "step": 154
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.024381741881370544,
+      "learning_rate": 4.266304347826087e-05,
+      "loss": 0.0001,
+      "step": 155
+    },
+    {
+      "epoch": 0.9984,
+      "grad_norm": 0.019372552633285522,
+      "learning_rate": 4.252717391304348e-05,
+      "loss": 0.0002,
+      "step": 156
+    },
+    {
+      "epoch": 1.0048,
+      "grad_norm": 0.2507990002632141,
+      "learning_rate": 4.239130434782609e-05,
+      "loss": 0.0013,
+      "step": 157
+    },
+    {
+      "epoch": 1.0112,
+      "grad_norm": 0.08029130101203918,
+      "learning_rate": 4.22554347826087e-05,
+      "loss": 0.0003,
+      "step": 158
+    },
+    {
+      "epoch": 1.0176,
+      "grad_norm": 0.1314297467470169,
+      "learning_rate": 4.2119565217391304e-05,
+      "loss": 0.0007,
+      "step": 159
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.13849826157093048,
+      "learning_rate": 4.1983695652173914e-05,
+      "loss": 0.0005,
+      "step": 160
+    },
+    {
+      "epoch": 1.0304,
+      "grad_norm": 0.027670226991176605,
+      "learning_rate": 4.1847826086956525e-05,
+      "loss": 0.0002,
+      "step": 161
+    },
+    {
+      "epoch": 1.0368,
+      "grad_norm": 0.4569777250289917,
+      "learning_rate": 4.171195652173913e-05,
+      "loss": 0.0013,
+      "step": 162
+    },
+    {
+      "epoch": 1.0432,
+      "grad_norm": 0.010377855040133,
+      "learning_rate": 4.1576086956521746e-05,
+      "loss": 0.0001,
+      "step": 163
+    },
+    {
+      "epoch": 1.0496,
+      "grad_norm": 0.012270581908524036,
+      "learning_rate": 4.144021739130435e-05,
+      "loss": 0.0001,
+      "step": 164
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.13936170935630798,
+      "learning_rate": 4.130434782608696e-05,
+      "loss": 0.0015,
+      "step": 165
+    },
+    {
+      "epoch": 1.0624,
+      "grad_norm": 0.36448225378990173,
+      "learning_rate": 4.116847826086957e-05,
+      "loss": 0.0016,
+      "step": 166
+    },
+    {
+      "epoch": 1.0688,
+      "grad_norm": 0.09022914618253708,
+      "learning_rate": 4.1032608695652174e-05,
+      "loss": 0.0008,
+      "step": 167
+    },
+    {
+      "epoch": 1.0752,
+      "grad_norm": 0.06291306018829346,
+      "learning_rate": 4.0896739130434784e-05,
+      "loss": 0.0004,
+      "step": 168
+    },
+    {
+      "epoch": 1.0816,
+      "grad_norm": 0.25657492876052856,
+      "learning_rate": 4.076086956521739e-05,
+      "loss": 0.0021,
+      "step": 169
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.039311520755290985,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 0.0003,
+      "step": 170
+    },
+    {
+      "epoch": 1.0944,
+      "grad_norm": 0.28193387389183044,
+      "learning_rate": 4.0489130434782615e-05,
+      "loss": 0.0038,
+      "step": 171
+    },
+    {
+      "epoch": 1.1008,
+      "grad_norm": 0.1303289830684662,
+      "learning_rate": 4.035326086956522e-05,
+      "loss": 0.0011,
+      "step": 172
+    },
+    {
+      "epoch": 1.1072,
+      "grad_norm": 0.08918856829404831,
+      "learning_rate": 4.021739130434783e-05,
+      "loss": 0.0008,
+      "step": 173
+    },
+    {
+      "epoch": 1.1136,
+      "grad_norm": 0.06426343321800232,
+      "learning_rate": 4.008152173913043e-05,
+      "loss": 0.0004,
+      "step": 174
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.2408573478460312,
+      "learning_rate": 3.994565217391304e-05,
+      "loss": 0.002,
+      "step": 175
+    },
+    {
+      "epoch": 1.1264,
+      "grad_norm": 0.13324324786663055,
+      "learning_rate": 3.9809782608695654e-05,
+      "loss": 0.0013,
+      "step": 176
+    },
+    {
+      "epoch": 1.1328,
+      "grad_norm": 0.04643731191754341,
+      "learning_rate": 3.9673913043478264e-05,
+      "loss": 0.0003,
+      "step": 177
+    },
+    {
+      "epoch": 1.1392,
+      "grad_norm": 0.09086046367883682,
+      "learning_rate": 3.9538043478260875e-05,
+      "loss": 0.0008,
+      "step": 178
+    },
+    {
+      "epoch": 1.1456,
+      "grad_norm": 0.014365454204380512,
+      "learning_rate": 3.940217391304348e-05,
+      "loss": 0.0002,
+      "step": 179
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.12365403771400452,
+      "learning_rate": 3.926630434782609e-05,
+      "loss": 0.0011,
+      "step": 180
+    },
+    {
+      "epoch": 1.1584,
+      "grad_norm": 0.010294603183865547,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 0.0001,
+      "step": 181
+    },
+    {
+      "epoch": 1.1648,
+      "grad_norm": 0.008795629255473614,
+      "learning_rate": 3.89945652173913e-05,
+      "loss": 0.0001,
+      "step": 182
+    },
+    {
+      "epoch": 1.1712,
+      "grad_norm": 0.50337153673172,
+      "learning_rate": 3.885869565217391e-05,
+      "loss": 0.0016,
+      "step": 183
+    },
+    {
+      "epoch": 1.1776,
+      "grad_norm": 0.035984236747026443,
+      "learning_rate": 3.8722826086956523e-05,
+      "loss": 0.0001,
+      "step": 184
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.018940063193440437,
+      "learning_rate": 3.8586956521739134e-05,
+      "loss": 0.0001,
+      "step": 185
+    },
+    {
+      "epoch": 1.1904,
+      "grad_norm": 0.021163620054721832,
+      "learning_rate": 3.8451086956521744e-05,
+      "loss": 0.0002,
+      "step": 186
+    },
+    {
+      "epoch": 1.1968,
+      "grad_norm": 0.09009546041488647,
+      "learning_rate": 3.831521739130435e-05,
+      "loss": 0.001,
+      "step": 187
+    },
+    {
+      "epoch": 1.2032,
+      "grad_norm": 0.3210280239582062,
+      "learning_rate": 3.817934782608696e-05,
+      "loss": 0.0009,
+      "step": 188
+    },
+    {
+      "epoch": 1.2096,
+      "grad_norm": 0.09898710995912552,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 0.0006,
+      "step": 189
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.278512179851532,
+      "learning_rate": 3.790760869565217e-05,
+      "loss": 0.001,
+      "step": 190
+    },
+    {
+      "epoch": 1.2224,
+      "grad_norm": 0.04888198524713516,
+      "learning_rate": 3.777173913043478e-05,
+      "loss": 0.0002,
+      "step": 191
+    },
+    {
+      "epoch": 1.2288000000000001,
+      "grad_norm": 0.03749491274356842,
+      "learning_rate": 3.763586956521739e-05,
+      "loss": 0.0008,
+      "step": 192
+    },
+    {
+      "epoch": 1.2352,
+      "grad_norm": 0.15450237691402435,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0018,
+      "step": 193
+    },
+    {
+      "epoch": 1.2416,
+      "grad_norm": 0.0344979502260685,
+      "learning_rate": 3.7364130434782614e-05,
+      "loss": 0.0002,
+      "step": 194
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.08851481974124908,
+      "learning_rate": 3.722826086956522e-05,
+      "loss": 0.0018,
+      "step": 195
+    },
+    {
+      "epoch": 1.2544,
+      "grad_norm": 0.020585596561431885,
+      "learning_rate": 3.709239130434783e-05,
+      "loss": 0.0001,
+      "step": 196
+    },
+    {
+      "epoch": 1.2608,
+      "grad_norm": 0.031943075358867645,
+      "learning_rate": 3.695652173913043e-05,
+      "loss": 0.0002,
+      "step": 197
+    },
+    {
+      "epoch": 1.2671999999999999,
+      "grad_norm": 0.2928239405155182,
+      "learning_rate": 3.682065217391304e-05,
+      "loss": 0.001,
+      "step": 198
+    },
+    {
+      "epoch": 1.2736,
+      "grad_norm": 0.08164837211370468,
+      "learning_rate": 3.668478260869566e-05,
+      "loss": 0.0004,
+      "step": 199
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.020030736923217773,
+      "learning_rate": 3.654891304347826e-05,
+      "loss": 0.0002,
+      "step": 200
+    },
+    {
+      "epoch": 1.2864,
+      "grad_norm": 0.04537905007600784,
+      "learning_rate": 3.641304347826087e-05,
+      "loss": 0.0003,
+      "step": 201
+    },
+    {
+      "epoch": 1.2928,
+      "grad_norm": 0.19243448972702026,
+      "learning_rate": 3.627717391304348e-05,
+      "loss": 0.0016,
+      "step": 202
+    },
+    {
+      "epoch": 1.2992,
+      "grad_norm": 0.14951840043067932,
+      "learning_rate": 3.614130434782609e-05,
+      "loss": 0.0013,
+      "step": 203
+    },
+    {
+      "epoch": 1.3056,
+      "grad_norm": 0.014692369848489761,
+      "learning_rate": 3.60054347826087e-05,
+      "loss": 0.0002,
+      "step": 204
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.13063009083271027,
+      "learning_rate": 3.58695652173913e-05,
+      "loss": 0.0017,
+      "step": 205
+    },
+    {
+      "epoch": 1.3184,
+      "grad_norm": 0.03748347610235214,
+      "learning_rate": 3.573369565217392e-05,
+      "loss": 0.0003,
+      "step": 206
+    },
+    {
+      "epoch": 1.3248,
+      "grad_norm": 0.030132994055747986,
+      "learning_rate": 3.559782608695653e-05,
+      "loss": 0.0002,
+      "step": 207
+    },
+    {
+      "epoch": 1.3312,
+      "grad_norm": 0.014458767138421535,
+      "learning_rate": 3.546195652173913e-05,
+      "loss": 0.0001,
+      "step": 208
+    },
+    {
+      "epoch": 1.3376000000000001,
+      "grad_norm": 0.036101408302783966,
+      "learning_rate": 3.532608695652174e-05,
+      "loss": 0.0002,
+      "step": 209
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.09572253376245499,
+      "learning_rate": 3.5190217391304346e-05,
+      "loss": 0.0005,
+      "step": 210
+    },
+    {
+      "epoch": 1.3504,
+      "grad_norm": 0.023433014750480652,
+      "learning_rate": 3.505434782608696e-05,
+      "loss": 0.0002,
+      "step": 211
+    },
+    {
+      "epoch": 1.3568,
+      "grad_norm": 0.014219313859939575,
+      "learning_rate": 3.491847826086957e-05,
+      "loss": 0.0001,
+      "step": 212
+    },
+    {
+      "epoch": 1.3632,
+      "grad_norm": 0.001725648296996951,
+      "learning_rate": 3.478260869565218e-05,
+      "loss": 0.0,
+      "step": 213
+    },
+    {
+      "epoch": 1.3696,
+      "grad_norm": 0.030395980924367905,
+      "learning_rate": 3.464673913043479e-05,
+      "loss": 0.0002,
+      "step": 214
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.012103204615414143,
+      "learning_rate": 3.451086956521739e-05,
+      "loss": 0.0001,
+      "step": 215
+    },
+    {
+      "epoch": 1.3824,
+      "grad_norm": 0.19407542049884796,
+      "learning_rate": 3.4375e-05,
+      "loss": 0.0007,
+      "step": 216
+    },
+    {
+      "epoch": 1.3888,
+      "grad_norm": 0.005606107879430056,
+      "learning_rate": 3.423913043478261e-05,
+      "loss": 0.0001,
+      "step": 217
+    },
+    {
+      "epoch": 1.3952,
+      "grad_norm": 0.00301155517809093,
+      "learning_rate": 3.4103260869565216e-05,
+      "loss": 0.0,
+      "step": 218
+    },
+    {
+      "epoch": 1.4016,
+      "grad_norm": 0.1430584192276001,
+      "learning_rate": 3.3967391304347826e-05,
+      "loss": 0.0014,
+      "step": 219
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.002769470913335681,
+      "learning_rate": 3.383152173913044e-05,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.4144,
+      "grad_norm": 0.0030104191973805428,
+      "learning_rate": 3.369565217391305e-05,
+      "loss": 0.0,
+      "step": 221
+    },
+    {
+      "epoch": 1.4208,
+      "grad_norm": 0.004693497437983751,
+      "learning_rate": 3.355978260869566e-05,
+      "loss": 0.0,
+      "step": 222
+    },
+    {
+      "epoch": 1.4272,
+      "grad_norm": 0.004368111025542021,
+      "learning_rate": 3.342391304347826e-05,
+      "loss": 0.0,
+      "step": 223
+    },
+    {
+      "epoch": 1.4336,
+      "grad_norm": 0.0074515920132398605,
+      "learning_rate": 3.328804347826087e-05,
+      "loss": 0.0,
+      "step": 224
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.003589405445381999,
+      "learning_rate": 3.3152173913043475e-05,
+      "loss": 0.0,
+      "step": 225
+    },
+    {
+      "epoch": 1.4464000000000001,
+      "grad_norm": 0.02143501304090023,
+      "learning_rate": 3.3016304347826086e-05,
+      "loss": 0.0001,
+      "step": 226
+    },
+    {
+      "epoch": 1.4527999999999999,
+      "grad_norm": 0.038155898451805115,
+      "learning_rate": 3.2880434782608696e-05,
+      "loss": 0.0002,
+      "step": 227
+    },
+    {
+      "epoch": 1.4592,
+      "grad_norm": 0.002726404694840312,
+      "learning_rate": 3.2744565217391307e-05,
+      "loss": 0.0,
+      "step": 228
+    },
+    {
+      "epoch": 1.4656,
+      "grad_norm": 0.0024346138816326857,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.0,
+      "step": 229
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.004204713273793459,
+      "learning_rate": 3.247282608695653e-05,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.4784,
+      "grad_norm": 0.04501979425549507,
+      "learning_rate": 3.233695652173913e-05,
+      "loss": 0.001,
+      "step": 231
+    },
+    {
+      "epoch": 1.4848,
+      "grad_norm": 0.004568320699036121,
+      "learning_rate": 3.220108695652174e-05,
+      "loss": 0.0,
+      "step": 232
+    },
+    {
+      "epoch": 1.4912,
+      "grad_norm": 0.0007846603402867913,
+      "learning_rate": 3.2065217391304345e-05,
+      "loss": 0.0,
+      "step": 233
+    },
+    {
+      "epoch": 1.4976,
+      "grad_norm": 0.0011130376951768994,
+      "learning_rate": 3.1929347826086955e-05,
+      "loss": 0.0,
+      "step": 234
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.003330661216750741,
+      "learning_rate": 3.1793478260869566e-05,
+      "loss": 0.0,
+      "step": 235
+    },
+    {
+      "epoch": 1.5104,
+      "grad_norm": 0.049491036683321,
+      "learning_rate": 3.1657608695652176e-05,
+      "loss": 0.0001,
+      "step": 236
+    },
+    {
+      "epoch": 1.5168,
+      "grad_norm": 0.09919781237840652,
+      "learning_rate": 3.152173913043479e-05,
+      "loss": 0.0007,
+      "step": 237
+    },
+    {
+      "epoch": 1.5232,
+      "grad_norm": 0.00037122363573871553,
+      "learning_rate": 3.138586956521739e-05,
+      "loss": 0.0,
+      "step": 238
+    },
+    {
+      "epoch": 1.5295999999999998,
+      "grad_norm": 0.0010649310424923897,
+      "learning_rate": 3.125e-05,
+      "loss": 0.0,
+      "step": 239
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.0384141206741333,
+      "learning_rate": 3.111413043478261e-05,
+      "loss": 0.0001,
+      "step": 240
+    },
+    {
+      "epoch": 1.5424,
+      "grad_norm": 0.0012282953830435872,
+      "learning_rate": 3.0978260869565215e-05,
+      "loss": 0.0,
+      "step": 241
+    },
+    {
+      "epoch": 1.5488,
+      "grad_norm": 0.0006697564385831356,
+      "learning_rate": 3.084239130434783e-05,
+      "loss": 0.0,
+      "step": 242
+    },
+    {
+      "epoch": 1.5552000000000001,
+      "grad_norm": 0.0025741446297615767,
+      "learning_rate": 3.0706521739130435e-05,
+      "loss": 0.0,
+      "step": 243
+    },
+    {
+      "epoch": 1.5615999999999999,
+      "grad_norm": 0.005837108939886093,
+      "learning_rate": 3.0570652173913046e-05,
+      "loss": 0.0,
+      "step": 244
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.027215829119086266,
+      "learning_rate": 3.0434782608695656e-05,
+      "loss": 0.0002,
+      "step": 245
+    },
+    {
+      "epoch": 1.5744,
+      "grad_norm": 0.03534737229347229,
+      "learning_rate": 3.029891304347826e-05,
+      "loss": 0.0001,
+      "step": 246
+    },
+    {
+      "epoch": 1.5808,
+      "grad_norm": 0.004011994227766991,
+      "learning_rate": 3.016304347826087e-05,
+      "loss": 0.0,
+      "step": 247
+    },
+    {
+      "epoch": 1.5872000000000002,
+      "grad_norm": 0.0009578302269801497,
+      "learning_rate": 3.0027173913043477e-05,
+      "loss": 0.0,
+      "step": 248
+    },
+    {
+      "epoch": 1.5936,
+      "grad_norm": 0.0009435511892661452,
+      "learning_rate": 2.9891304347826088e-05,
+      "loss": 0.0,
+      "step": 249
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.001009692088700831,
+      "learning_rate": 2.9755434782608698e-05,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.6064,
+      "grad_norm": 0.2966485023498535,
+      "learning_rate": 2.9619565217391305e-05,
+      "loss": 0.0003,
+      "step": 251
+    },
+    {
+      "epoch": 1.6128,
+      "grad_norm": 0.008122624829411507,
+      "learning_rate": 2.9483695652173916e-05,
+      "loss": 0.0,
+      "step": 252
+    },
+    {
+      "epoch": 1.6192,
+      "grad_norm": 0.035515330731868744,
+      "learning_rate": 2.9347826086956526e-05,
+      "loss": 0.0003,
+      "step": 253
+    },
+    {
+      "epoch": 1.6256,
+      "grad_norm": 0.08122820407152176,
+      "learning_rate": 2.921195652173913e-05,
+      "loss": 0.0018,
+      "step": 254
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.15151779353618622,
+      "learning_rate": 2.9076086956521743e-05,
+      "loss": 0.0012,
+      "step": 255
+    },
+    {
+      "epoch": 1.6383999999999999,
+      "grad_norm": 0.0009511475218459964,
+      "learning_rate": 2.8940217391304347e-05,
+      "loss": 0.0,
+      "step": 256
+    },
+    {
+      "epoch": 1.6448,
+      "grad_norm": 0.005445484071969986,
+      "learning_rate": 2.8804347826086957e-05,
+      "loss": 0.0,
+      "step": 257
+    },
+    {
+      "epoch": 1.6512,
+      "grad_norm": 0.04518282413482666,
+      "learning_rate": 2.8668478260869568e-05,
+      "loss": 0.0007,
+      "step": 258
+    },
+    {
+      "epoch": 1.6576,
+      "grad_norm": 0.11256727576255798,
+      "learning_rate": 2.8532608695652175e-05,
+      "loss": 0.0006,
+      "step": 259
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.02736232616007328,
+      "learning_rate": 2.8396739130434785e-05,
+      "loss": 0.0002,
+      "step": 260
+    },
+    {
+      "epoch": 1.6703999999999999,
+      "grad_norm": 0.15258099138736725,
+      "learning_rate": 2.826086956521739e-05,
+      "loss": 0.0001,
+      "step": 261
+    },
+    {
+      "epoch": 1.6768,
+      "grad_norm": 0.036922965198755264,
+      "learning_rate": 2.8125000000000003e-05,
+      "loss": 0.0002,
+      "step": 262
+    },
+    {
+      "epoch": 1.6832,
+      "grad_norm": 0.015637921169400215,
+      "learning_rate": 2.7989130434782613e-05,
+      "loss": 0.0001,
+      "step": 263
+    },
+    {
+      "epoch": 1.6896,
+      "grad_norm": 0.05476976931095123,
+      "learning_rate": 2.7853260869565217e-05,
+      "loss": 0.0005,
+      "step": 264
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.0004676490498241037,
+      "learning_rate": 2.7717391304347827e-05,
+      "loss": 0.0,
+      "step": 265
+    },
+    {
+      "epoch": 1.7024,
+      "grad_norm": 0.0644228383898735,
+      "learning_rate": 2.7581521739130434e-05,
+      "loss": 0.0014,
+      "step": 266
+    },
+    {
+      "epoch": 1.7088,
+      "grad_norm": 0.03631878271698952,
+      "learning_rate": 2.7445652173913044e-05,
+      "loss": 0.0004,
+      "step": 267
+    },
+    {
+      "epoch": 1.7151999999999998,
+      "grad_norm": 0.020780308172106743,
+      "learning_rate": 2.7309782608695655e-05,
+      "loss": 0.0001,
+      "step": 268
+    },
+    {
+      "epoch": 1.7216,
+      "grad_norm": 0.028413992375135422,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 0.0004,
+      "step": 269
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.09412650763988495,
+      "learning_rate": 2.7038043478260872e-05,
+      "loss": 0.0001,
+      "step": 270
+    },
+    {
+      "epoch": 1.7344,
+      "grad_norm": 0.06533757597208023,
+      "learning_rate": 2.6902173913043476e-05,
+      "loss": 0.0005,
+      "step": 271
+    },
+    {
+      "epoch": 1.7408000000000001,
+      "grad_norm": 0.006138004828244448,
+      "learning_rate": 2.6766304347826086e-05,
+      "loss": 0.0,
+      "step": 272
+    },
+    {
+      "epoch": 1.7471999999999999,
+      "grad_norm": 0.01119806058704853,
+      "learning_rate": 2.66304347826087e-05,
+      "loss": 0.0001,
+      "step": 273
+    },
+    {
+      "epoch": 1.7536,
+      "grad_norm": 0.005970626603811979,
+      "learning_rate": 2.6494565217391304e-05,
+      "loss": 0.0001,
+      "step": 274
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.04662192240357399,
+      "learning_rate": 2.6358695652173914e-05,
+      "loss": 0.0003,
+      "step": 275
+    },
+    {
+      "epoch": 1.7664,
+      "grad_norm": 0.022092919796705246,
+      "learning_rate": 2.6222826086956525e-05,
+      "loss": 0.0001,
+      "step": 276
+    },
+    {
+      "epoch": 1.7728000000000002,
+      "grad_norm": 0.005273187533020973,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 0.0,
+      "step": 277
+    },
+    {
+      "epoch": 1.7792,
+      "grad_norm": 0.031516119837760925,
+      "learning_rate": 2.5951086956521742e-05,
+      "loss": 0.0001,
+      "step": 278
+    },
+    {
+      "epoch": 1.7856,
+      "grad_norm": 0.0022183710243552923,
+      "learning_rate": 2.5815217391304346e-05,
+      "loss": 0.0,
+      "step": 279
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.0009360455442219973,
+      "learning_rate": 2.567934782608696e-05,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 1.7984,
+      "grad_norm": 0.1700274795293808,
+      "learning_rate": 2.554347826086957e-05,
+      "loss": 0.0005,
+      "step": 281
+    },
+    {
+      "epoch": 1.8048,
+      "grad_norm": 0.002585944253951311,
+      "learning_rate": 2.5407608695652173e-05,
+      "loss": 0.0,
+      "step": 282
+    },
+    {
+      "epoch": 1.8112,
+      "grad_norm": 0.0011164086172357202,
+      "learning_rate": 2.5271739130434784e-05,
+      "loss": 0.0,
+      "step": 283
+    },
+    {
+      "epoch": 1.8176,
+      "grad_norm": 0.02267805114388466,
+      "learning_rate": 2.513586956521739e-05,
+      "loss": 0.0002,
+      "step": 284
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.015226287767291069,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 285
+    },
+    {
+      "epoch": 1.8304,
+      "grad_norm": 0.013317841105163097,
+      "learning_rate": 2.4864130434782608e-05,
+      "loss": 0.0001,
+      "step": 286
+    },
+    {
+      "epoch": 1.8368,
+      "grad_norm": 0.0646032840013504,
+      "learning_rate": 2.472826086956522e-05,
+      "loss": 0.0001,
+      "step": 287
+    },
+    {
+      "epoch": 1.8432,
+      "grad_norm": 0.003959594294428825,
+      "learning_rate": 2.459239130434783e-05,
+      "loss": 0.0,
+      "step": 288
+    },
+    {
+      "epoch": 1.8496000000000001,
+      "grad_norm": 0.002444010926410556,
+      "learning_rate": 2.4456521739130436e-05,
+      "loss": 0.0,
+      "step": 289
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.02925432287156582,
+      "learning_rate": 2.4320652173913043e-05,
+      "loss": 0.0001,
+      "step": 290
+    },
+    {
+      "epoch": 1.8624,
+      "grad_norm": 0.0098092220723629,
+      "learning_rate": 2.4184782608695653e-05,
+      "loss": 0.0,
+      "step": 291
+    },
+    {
+      "epoch": 1.8688,
+      "grad_norm": 0.00151850248221308,
+      "learning_rate": 2.4048913043478264e-05,
+      "loss": 0.0,
+      "step": 292
+    },
+    {
+      "epoch": 1.8752,
+      "grad_norm": 0.002206259872764349,
+      "learning_rate": 2.391304347826087e-05,
+      "loss": 0.0,
+      "step": 293
+    },
+    {
+      "epoch": 1.8816000000000002,
+      "grad_norm": 0.0205011498183012,
+      "learning_rate": 2.3777173913043478e-05,
+      "loss": 0.0001,
+      "step": 294
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.0016515238676220179,
+      "learning_rate": 2.3641304347826088e-05,
+      "loss": 0.0,
+      "step": 295
+    },
+    {
+      "epoch": 1.8944,
+      "grad_norm": 0.03133111447095871,
+      "learning_rate": 2.3505434782608695e-05,
+      "loss": 0.0002,
+      "step": 296
+    },
+    {
+      "epoch": 1.9008,
+      "grad_norm": 0.005767473019659519,
+      "learning_rate": 2.3369565217391306e-05,
+      "loss": 0.0,
+      "step": 297
+    },
+    {
+      "epoch": 1.9072,
+      "grad_norm": 0.0027142008766531944,
+      "learning_rate": 2.3233695652173916e-05,
+      "loss": 0.0,
+      "step": 298
+    },
+    {
+      "epoch": 1.9136,
+      "grad_norm": 0.0016964487731456757,
+      "learning_rate": 2.3097826086956523e-05,
+      "loss": 0.0,
+      "step": 299
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.0006552913109771907,
+      "learning_rate": 2.296195652173913e-05,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.9264000000000001,
+      "grad_norm": 0.0008631868404336274,
+      "learning_rate": 2.282608695652174e-05,
+      "loss": 0.0,
+      "step": 301
+    },
+    {
+      "epoch": 1.9327999999999999,
+      "grad_norm": 0.003397905034944415,
+      "learning_rate": 2.269021739130435e-05,
+      "loss": 0.0,
+      "step": 302
+    },
+    {
+      "epoch": 1.9392,
+      "grad_norm": 0.004106289707124233,
+      "learning_rate": 2.2554347826086958e-05,
+      "loss": 0.0,
+      "step": 303
+    },
+    {
+      "epoch": 1.9456,
+      "grad_norm": 0.001950149075128138,
+      "learning_rate": 2.2418478260869565e-05,
+      "loss": 0.0,
+      "step": 304
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.10530714690685272,
+      "learning_rate": 2.2282608695652175e-05,
+      "loss": 0.0008,
+      "step": 305
+    },
+    {
+      "epoch": 1.9584000000000001,
+      "grad_norm": 0.0003630653955042362,
+      "learning_rate": 2.2146739130434786e-05,
+      "loss": 0.0,
+      "step": 306
+    },
+    {
+      "epoch": 1.9647999999999999,
+      "grad_norm": 0.0065023344941437244,
+      "learning_rate": 2.2010869565217393e-05,
+      "loss": 0.0,
+      "step": 307
+    },
+    {
+      "epoch": 1.9712,
+      "grad_norm": 0.01203858107328415,
+      "learning_rate": 2.1875e-05,
+      "loss": 0.0,
+      "step": 308
+    },
+    {
+      "epoch": 1.9776,
+      "grad_norm": 0.03935980424284935,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.0001,
+      "step": 309
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.00022823851031716913,
+      "learning_rate": 2.1603260869565217e-05,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 1.9904,
+      "grad_norm": 0.0002564598398748785,
+      "learning_rate": 2.1467391304347828e-05,
+      "loss": 0.0,
+      "step": 311
+    },
+    {
+      "epoch": 1.9968,
+      "grad_norm": 0.0005882303230464458,
+      "learning_rate": 2.1331521739130435e-05,
+      "loss": 0.0,
+      "step": 312
+    },
+    {
+      "epoch": 2.0032,
+      "grad_norm": 0.031509771943092346,
+      "learning_rate": 2.1195652173913045e-05,
+      "loss": 0.0002,
+      "step": 313
+    },
+    {
+      "epoch": 2.0096,
+      "grad_norm": 0.00021469846251420677,
+      "learning_rate": 2.1059782608695652e-05,
+      "loss": 0.0,
+      "step": 314
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.10628461092710495,
+      "learning_rate": 2.0923913043478262e-05,
+      "loss": 0.0004,
+      "step": 315
+    },
+    {
+      "epoch": 2.0224,
+      "grad_norm": 0.00871970970183611,
+      "learning_rate": 2.0788043478260873e-05,
+      "loss": 0.0,
+      "step": 316
+    },
+    {
+      "epoch": 2.0288,
+      "grad_norm": 0.12848307192325592,
+      "learning_rate": 2.065217391304348e-05,
+      "loss": 0.0001,
+      "step": 317
+    },
+    {
+      "epoch": 2.0352,
+      "grad_norm": 0.023954277858138084,
+      "learning_rate": 2.0516304347826087e-05,
+      "loss": 0.0001,
+      "step": 318
+    },
+    {
+      "epoch": 2.0416,
+      "grad_norm": 0.0002188335347454995,
+      "learning_rate": 2.0380434782608694e-05,
+      "loss": 0.0,
+      "step": 319
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.0005644243792630732,
+      "learning_rate": 2.0244565217391308e-05,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.0544,
+      "grad_norm": 0.08943594992160797,
+      "learning_rate": 2.0108695652173915e-05,
+      "loss": 0.0005,
+      "step": 321
+    },
+    {
+      "epoch": 2.0608,
+      "grad_norm": 0.002636589575558901,
+      "learning_rate": 1.997282608695652e-05,
+      "loss": 0.0,
+      "step": 322
+    },
+    {
+      "epoch": 2.0672,
+      "grad_norm": 0.003091091988608241,
+      "learning_rate": 1.9836956521739132e-05,
+      "loss": 0.0,
+      "step": 323
+    },
+    {
+      "epoch": 2.0736,
+      "grad_norm": 0.04709108546376228,
+      "learning_rate": 1.970108695652174e-05,
+      "loss": 0.0006,
+      "step": 324
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.054577283561229706,
+      "learning_rate": 1.956521739130435e-05,
+      "loss": 0.0004,
+      "step": 325
+    },
+    {
+      "epoch": 2.0864,
+      "grad_norm": 0.08327251672744751,
+      "learning_rate": 1.9429347826086957e-05,
+      "loss": 0.0007,
+      "step": 326
+    },
+    {
+      "epoch": 2.0928,
+      "grad_norm": 0.0005219040904194117,
+      "learning_rate": 1.9293478260869567e-05,
+      "loss": 0.0,
+      "step": 327
+    },
+    {
+      "epoch": 2.0992,
+      "grad_norm": 0.013275478035211563,
+      "learning_rate": 1.9157608695652174e-05,
+      "loss": 0.0001,
+      "step": 328
+    },
+    {
+      "epoch": 2.1056,
+      "grad_norm": 0.002039135666564107,
+      "learning_rate": 1.9021739130434784e-05,
+      "loss": 0.0,
+      "step": 329
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.00036628072848543525,
+      "learning_rate": 1.888586956521739e-05,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 2.1184,
+      "grad_norm": 0.0005863333353772759,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.0,
+      "step": 331
+    },
+    {
+      "epoch": 2.1248,
+      "grad_norm": 0.0012312327744439244,
+      "learning_rate": 1.861413043478261e-05,
+      "loss": 0.0,
+      "step": 332
+    },
+    {
+      "epoch": 2.1312,
+      "grad_norm": 0.04584371671080589,
+      "learning_rate": 1.8478260869565216e-05,
+      "loss": 0.0006,
+      "step": 333
+    },
+    {
+      "epoch": 2.1376,
+      "grad_norm": 0.0013530978467315435,
+      "learning_rate": 1.834239130434783e-05,
+      "loss": 0.0,
+      "step": 334
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.021959273144602776,
+      "learning_rate": 1.8206521739130437e-05,
+      "loss": 0.0002,
+      "step": 335
+    },
+    {
+      "epoch": 2.1504,
+      "grad_norm": 0.0004987395950593054,
+      "learning_rate": 1.8070652173913044e-05,
+      "loss": 0.0,
+      "step": 336
+    },
+    {
+      "epoch": 2.1568,
+      "grad_norm": 0.0836053192615509,
+      "learning_rate": 1.793478260869565e-05,
+      "loss": 0.001,
+      "step": 337
+    },
+    {
+      "epoch": 2.1632,
+      "grad_norm": 0.01392176654189825,
+      "learning_rate": 1.7798913043478264e-05,
+      "loss": 0.0001,
+      "step": 338
+    },
+    {
+      "epoch": 2.1696,
+      "grad_norm": 0.020961252972483635,
+      "learning_rate": 1.766304347826087e-05,
+      "loss": 0.0001,
+      "step": 339
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.0009171417914330959,
+      "learning_rate": 1.752717391304348e-05,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.1824,
+      "grad_norm": 0.018709851428866386,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.0002,
+      "step": 341
+    },
+    {
+      "epoch": 2.1888,
+      "grad_norm": 0.012070205062627792,
+      "learning_rate": 1.7255434782608696e-05,
+      "loss": 0.0001,
+      "step": 342
+    },
+    {
+      "epoch": 2.1952,
+      "grad_norm": 0.019241344183683395,
+      "learning_rate": 1.7119565217391306e-05,
+      "loss": 0.0001,
+      "step": 343
+    },
+    {
+      "epoch": 2.2016,
+      "grad_norm": 0.003757551545277238,
+      "learning_rate": 1.6983695652173913e-05,
+      "loss": 0.0,
+      "step": 344
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.019551070407032967,
+      "learning_rate": 1.6847826086956524e-05,
+      "loss": 0.0001,
+      "step": 345
+    },
+    {
+      "epoch": 2.2144,
+      "grad_norm": 0.006138879340142012,
+      "learning_rate": 1.671195652173913e-05,
+      "loss": 0.0,
+      "step": 346
+    },
+    {
+      "epoch": 2.2208,
+      "grad_norm": 0.006268091965466738,
+      "learning_rate": 1.6576086956521738e-05,
+      "loss": 0.0,
+      "step": 347
+    },
+    {
+      "epoch": 2.2272,
+      "grad_norm": 0.0025931093841791153,
+      "learning_rate": 1.6440217391304348e-05,
+      "loss": 0.0,
+      "step": 348
+    },
+    {
+      "epoch": 2.2336,
+      "grad_norm": 0.011823219247162342,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 0.0,
+      "step": 349
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.0008455697679892182,
+      "learning_rate": 1.6168478260869565e-05,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.2464,
+      "grad_norm": 0.0038918645586818457,
+      "learning_rate": 1.6032608695652173e-05,
+      "loss": 0.0,
+      "step": 351
+    },
+    {
+      "epoch": 2.2528,
+      "grad_norm": 0.0021595454309135675,
+      "learning_rate": 1.5896739130434783e-05,
+      "loss": 0.0,
+      "step": 352
+    },
+    {
+      "epoch": 2.2592,
+      "grad_norm": 0.00034974791924469173,
+      "learning_rate": 1.5760869565217393e-05,
+      "loss": 0.0,
+      "step": 353
+    },
+    {
+      "epoch": 2.2656,
+      "grad_norm": 0.0028160507790744305,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.0,
+      "step": 354
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.0002821324742399156,
+      "learning_rate": 1.5489130434782607e-05,
+      "loss": 0.0,
+      "step": 355
+    },
+    {
+      "epoch": 2.2784,
+      "grad_norm": 0.0027674513403326273,
+      "learning_rate": 1.5353260869565218e-05,
+      "loss": 0.0,
+      "step": 356
+    },
+    {
+      "epoch": 2.2848,
+      "grad_norm": 0.0006794423097744584,
+      "learning_rate": 1.5217391304347828e-05,
+      "loss": 0.0,
+      "step": 357
+    },
+    {
+      "epoch": 2.2912,
+      "grad_norm": 0.006305163726210594,
+      "learning_rate": 1.5081521739130435e-05,
+      "loss": 0.0,
+      "step": 358
+    },
+    {
+      "epoch": 2.2976,
+      "grad_norm": 0.0008437309297733009,
+      "learning_rate": 1.4945652173913044e-05,
+      "loss": 0.0,
+      "step": 359
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.11048416793346405,
+      "learning_rate": 1.4809782608695653e-05,
+      "loss": 0.0004,
+      "step": 360
+    },
+    {
+      "epoch": 2.3104,
+      "grad_norm": 0.06330271065235138,
+      "learning_rate": 1.4673913043478263e-05,
+      "loss": 0.0003,
+      "step": 361
+    },
+    {
+      "epoch": 2.3168,
+      "grad_norm": 0.00016434816643595695,
+      "learning_rate": 1.4538043478260872e-05,
+      "loss": 0.0,
+      "step": 362
+    },
+    {
+      "epoch": 2.3232,
+      "grad_norm": 0.007731410209089518,
+      "learning_rate": 1.4402173913043479e-05,
+      "loss": 0.0,
+      "step": 363
+    },
+    {
+      "epoch": 2.3296,
+      "grad_norm": 0.0016059301560744643,
+      "learning_rate": 1.4266304347826087e-05,
+      "loss": 0.0,
+      "step": 364
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.00022593283210881054,
+      "learning_rate": 1.4130434782608694e-05,
+      "loss": 0.0,
+      "step": 365
+    },
+    {
+      "epoch": 2.3424,
+      "grad_norm": 0.05906170979142189,
+      "learning_rate": 1.3994565217391307e-05,
+      "loss": 0.0002,
+      "step": 366
+    },
+    {
+      "epoch": 2.3487999999999998,
+      "grad_norm": 0.03806007653474808,
+      "learning_rate": 1.3858695652173914e-05,
+      "loss": 0.0003,
+      "step": 367
+    },
+    {
+      "epoch": 2.3552,
+      "grad_norm": 0.006718638353049755,
+      "learning_rate": 1.3722826086956522e-05,
+      "loss": 0.0,
+      "step": 368
+    },
+    {
+      "epoch": 2.3616,
+      "grad_norm": 0.029729636386036873,
+      "learning_rate": 1.3586956521739131e-05,
+      "loss": 0.0001,
+      "step": 369
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.003214767901226878,
+      "learning_rate": 1.3451086956521738e-05,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 2.3744,
+      "grad_norm": 0.006212338805198669,
+      "learning_rate": 1.331521739130435e-05,
+      "loss": 0.0,
+      "step": 371
+    },
+    {
+      "epoch": 2.3808,
+      "grad_norm": 0.0008076957892626524,
+      "learning_rate": 1.3179347826086957e-05,
+      "loss": 0.0,
+      "step": 372
+    },
+    {
+      "epoch": 2.3872,
+      "grad_norm": 0.0005326943937689066,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.0,
+      "step": 373
+    },
+    {
+      "epoch": 2.3936,
+      "grad_norm": 0.0004142646794207394,
+      "learning_rate": 1.2907608695652173e-05,
+      "loss": 0.0,
+      "step": 374
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.00038568780291825533,
+      "learning_rate": 1.2771739130434785e-05,
+      "loss": 0.0,
+      "step": 375
+    },
+    {
+      "epoch": 2.4064,
+      "grad_norm": 0.008295689709484577,
+      "learning_rate": 1.2635869565217392e-05,
+      "loss": 0.0,
+      "step": 376
+    },
+    {
+      "epoch": 2.4128,
+      "grad_norm": 0.00012209192209411412,
+      "learning_rate": 1.25e-05,
+      "loss": 0.0,
+      "step": 377
+    },
+    {
+      "epoch": 2.4192,
+      "grad_norm": 0.002289616037160158,
+      "learning_rate": 1.236413043478261e-05,
+      "loss": 0.0,
+      "step": 378
+    },
+    {
+      "epoch": 2.4256,
+      "grad_norm": 0.0006718016811646521,
+      "learning_rate": 1.2228260869565218e-05,
+      "loss": 0.0,
+      "step": 379
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.000206793294637464,
+      "learning_rate": 1.2092391304347827e-05,
+      "loss": 0.0,
+      "step": 380
+    },
+    {
+      "epoch": 2.4384,
+      "grad_norm": 0.0003030790248885751,
+      "learning_rate": 1.1956521739130435e-05,
+      "loss": 0.0,
+      "step": 381
+    },
+    {
+      "epoch": 2.4448,
+      "grad_norm": 0.02157384157180786,
+      "learning_rate": 1.1820652173913044e-05,
+      "loss": 0.0001,
+      "step": 382
+    },
+    {
+      "epoch": 2.4512,
+      "grad_norm": 0.00044968881411477923,
+      "learning_rate": 1.1684782608695653e-05,
+      "loss": 0.0,
+      "step": 383
+    },
+    {
+      "epoch": 2.4576000000000002,
+      "grad_norm": 0.00021569991076830775,
+      "learning_rate": 1.1548913043478262e-05,
+      "loss": 0.0,
+      "step": 384
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.0004299252468626946,
+      "learning_rate": 1.141304347826087e-05,
+      "loss": 0.0,
+      "step": 385
+    },
+    {
+      "epoch": 2.4704,
+      "grad_norm": 0.0014320369809865952,
+      "learning_rate": 1.1277173913043479e-05,
+      "loss": 0.0,
+      "step": 386
+    },
+    {
+      "epoch": 2.4768,
+      "grad_norm": 0.00015258396160788834,
+      "learning_rate": 1.1141304347826088e-05,
+      "loss": 0.0,
+      "step": 387
+    },
+    {
+      "epoch": 2.4832,
+      "grad_norm": 0.0002189869264839217,
+      "learning_rate": 1.1005434782608696e-05,
+      "loss": 0.0,
+      "step": 388
+    },
+    {
+      "epoch": 2.4896,
+      "grad_norm": 0.00018207654647994787,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.0,
+      "step": 389
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.03701590374112129,
+      "learning_rate": 1.0733695652173914e-05,
+      "loss": 0.0003,
+      "step": 390
+    },
+    {
+      "epoch": 2.5023999999999997,
+      "grad_norm": 0.0008836943889036775,
+      "learning_rate": 1.0597826086956523e-05,
+      "loss": 0.0,
+      "step": 391
+    },
+    {
+      "epoch": 2.5088,
+      "grad_norm": 0.003796490840613842,
+      "learning_rate": 1.0461956521739131e-05,
+      "loss": 0.0,
+      "step": 392
+    },
+    {
+      "epoch": 2.5152,
+      "grad_norm": 0.0001544107944937423,
+      "learning_rate": 1.032608695652174e-05,
+      "loss": 0.0,
+      "step": 393
+    },
+    {
+      "epoch": 2.5216,
+      "grad_norm": 0.0011832360178232193,
+      "learning_rate": 1.0190217391304347e-05,
+      "loss": 0.0,
+      "step": 394
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.04718249663710594,
+      "learning_rate": 1.0054347826086957e-05,
+      "loss": 0.0002,
+      "step": 395
+    },
+    {
+      "epoch": 2.5343999999999998,
+      "grad_norm": 0.058300986886024475,
+      "learning_rate": 9.918478260869566e-06,
+      "loss": 0.0001,
+      "step": 396
+    },
+    {
+      "epoch": 2.5408,
+      "grad_norm": 0.00014710660616401583,
+      "learning_rate": 9.782608695652175e-06,
+      "loss": 0.0,
+      "step": 397
+    },
+    {
+      "epoch": 2.5472,
+      "grad_norm": 0.00016318142297677696,
+      "learning_rate": 9.646739130434783e-06,
+      "loss": 0.0,
+      "step": 398
+    },
+    {
+      "epoch": 2.5536,
+      "grad_norm": 0.0010715242242440581,
+      "learning_rate": 9.510869565217392e-06,
+      "loss": 0.0,
+      "step": 399
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.00015468985657207668,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.5664,
+      "grad_norm": 0.0011912648333236575,
+      "learning_rate": 9.239130434782608e-06,
+      "loss": 0.0,
+      "step": 401
+    },
+    {
+      "epoch": 2.5728,
+      "grad_norm": 0.009426996111869812,
+      "learning_rate": 9.103260869565218e-06,
+      "loss": 0.0001,
+      "step": 402
+    },
+    {
+      "epoch": 2.5792,
+      "grad_norm": 0.0003489768714644015,
+      "learning_rate": 8.967391304347825e-06,
+      "loss": 0.0,
+      "step": 403
+    },
+    {
+      "epoch": 2.5856,
+      "grad_norm": 0.02787749283015728,
+      "learning_rate": 8.831521739130436e-06,
+      "loss": 0.0003,
+      "step": 404
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.00013534349272958934,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.0,
+      "step": 405
+    },
+    {
+      "epoch": 2.5984,
+      "grad_norm": 0.0007696665124967694,
+      "learning_rate": 8.559782608695653e-06,
+      "loss": 0.0,
+      "step": 406
+    },
+    {
+      "epoch": 2.6048,
+      "grad_norm": 0.0002082609134959057,
+      "learning_rate": 8.423913043478262e-06,
+      "loss": 0.0,
+      "step": 407
+    },
+    {
+      "epoch": 2.6112,
+      "grad_norm": 0.00028427859069779515,
+      "learning_rate": 8.288043478260869e-06,
+      "loss": 0.0,
+      "step": 408
+    },
+    {
+      "epoch": 2.6176,
+      "grad_norm": 0.0015449513448402286,
+      "learning_rate": 8.15217391304348e-06,
+      "loss": 0.0,
+      "step": 409
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.00013916725583840162,
+      "learning_rate": 8.016304347826086e-06,
+      "loss": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 2.6304,
+      "grad_norm": 0.0001490354334237054,
+      "learning_rate": 7.880434782608697e-06,
+      "loss": 0.0,
+      "step": 411
+    },
+    {
+      "epoch": 2.6368,
+      "grad_norm": 0.00043823281885124743,
+      "learning_rate": 7.744565217391304e-06,
+      "loss": 0.0,
+      "step": 412
+    },
+    {
+      "epoch": 2.6432,
+      "grad_norm": 0.4344710111618042,
+      "learning_rate": 7.608695652173914e-06,
+      "loss": 0.0003,
+      "step": 413
+    },
+    {
+      "epoch": 2.6496,
+      "grad_norm": 0.00015445360622834414,
+      "learning_rate": 7.472826086956522e-06,
+      "loss": 0.0,
+      "step": 414
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.01644268073141575,
+      "learning_rate": 7.3369565217391315e-06,
+      "loss": 0.0,
+      "step": 415
+    },
+    {
+      "epoch": 2.6624,
+      "grad_norm": 0.005493068136274815,
+      "learning_rate": 7.201086956521739e-06,
+      "loss": 0.0,
+      "step": 416
+    },
+    {
+      "epoch": 2.6688,
+      "grad_norm": 0.0002792974701151252,
+      "learning_rate": 7.065217391304347e-06,
+      "loss": 0.0,
+      "step": 417
+    },
+    {
+      "epoch": 2.6752000000000002,
+      "grad_norm": 0.0357564315199852,
+      "learning_rate": 6.929347826086957e-06,
+      "loss": 0.0002,
+      "step": 418
+    },
+    {
+      "epoch": 2.6816,
+      "grad_norm": 0.00029837293550372124,
+      "learning_rate": 6.7934782608695655e-06,
+      "loss": 0.0,
+      "step": 419
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.00031187469721771777,
+      "learning_rate": 6.657608695652175e-06,
+      "loss": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 2.6944,
+      "grad_norm": 0.00027027365285903215,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.0,
+      "step": 421
+    },
+    {
+      "epoch": 2.7008,
+      "grad_norm": 0.01826370880007744,
+      "learning_rate": 6.3858695652173924e-06,
+      "loss": 0.0001,
+      "step": 422
+    },
+    {
+      "epoch": 2.7072000000000003,
+      "grad_norm": 0.00048121585859917104,
+      "learning_rate": 6.25e-06,
+      "loss": 0.0,
+      "step": 423
+    },
+    {
+      "epoch": 2.7136,
+      "grad_norm": 0.00014375981118064374,
+      "learning_rate": 6.114130434782609e-06,
+      "loss": 0.0,
+      "step": 424
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.008497480303049088,
+      "learning_rate": 5.978260869565218e-06,
+      "loss": 0.0,
+      "step": 425
+    },
+    {
+      "epoch": 2.7264,
+      "grad_norm": 0.0037359774578362703,
+      "learning_rate": 5.842391304347826e-06,
+      "loss": 0.0,
+      "step": 426
+    },
+    {
+      "epoch": 2.7328,
+      "grad_norm": 0.0001621334085939452,
+      "learning_rate": 5.706521739130435e-06,
+      "loss": 0.0,
+      "step": 427
+    },
+    {
+      "epoch": 2.7392,
+      "grad_norm": 0.00036656871088780463,
+      "learning_rate": 5.570652173913044e-06,
+      "loss": 0.0,
+      "step": 428
+    },
+    {
+      "epoch": 2.7456,
+      "grad_norm": 0.0002693533606361598,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.0,
+      "step": 429
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.001102575333788991,
+      "learning_rate": 5.298913043478261e-06,
+      "loss": 0.0,
+      "step": 430
+    },
+    {
+      "epoch": 2.7584,
+      "grad_norm": 0.000412663328461349,
+      "learning_rate": 5.16304347826087e-06,
+      "loss": 0.0,
+      "step": 431
+    },
+    {
+      "epoch": 2.7648,
+      "grad_norm": 0.001067288569174707,
+      "learning_rate": 5.027173913043479e-06,
+      "loss": 0.0,
+      "step": 432
+    },
+    {
+      "epoch": 2.7712,
+      "grad_norm": 0.08458250015974045,
+      "learning_rate": 4.891304347826087e-06,
+      "loss": 0.0001,
+      "step": 433
+    },
+    {
+      "epoch": 2.7776,
+      "grad_norm": 0.0002504325530026108,
+      "learning_rate": 4.755434782608696e-06,
+      "loss": 0.0,
+      "step": 434
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.0001957175409188494,
+      "learning_rate": 4.619565217391304e-06,
+      "loss": 0.0,
+      "step": 435
+    },
+    {
+      "epoch": 2.7904,
+      "grad_norm": 0.0002998160489369184,
+      "learning_rate": 4.483695652173913e-06,
+      "loss": 0.0,
+      "step": 436
+    },
+    {
+      "epoch": 2.7968,
+      "grad_norm": 0.0002802670351229608,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.0,
+      "step": 437
+    },
+    {
+      "epoch": 2.8032,
+      "grad_norm": 0.0006581236375495791,
+      "learning_rate": 4.211956521739131e-06,
+      "loss": 0.0,
+      "step": 438
+    },
+    {
+      "epoch": 2.8096,
+      "grad_norm": 0.0002182146126870066,
+      "learning_rate": 4.07608695652174e-06,
+      "loss": 0.0,
+      "step": 439
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 0.0006341098342090845,
+      "learning_rate": 3.940217391304348e-06,
+      "loss": 0.0,
+      "step": 440
+    },
+    {
+      "epoch": 2.8224,
+      "grad_norm": 0.0006998185999691486,
+      "learning_rate": 3.804347826086957e-06,
+      "loss": 0.0,
+      "step": 441
+    },
+    {
+      "epoch": 2.8288,
+      "grad_norm": 0.014809445478022099,
+      "learning_rate": 3.6684782608695657e-06,
+      "loss": 0.0001,
+      "step": 442
+    },
+    {
+      "epoch": 2.8352,
+      "grad_norm": 0.0004117899516131729,
+      "learning_rate": 3.5326086956521736e-06,
+      "loss": 0.0,
+      "step": 443
+    },
+    {
+      "epoch": 2.8416,
+      "grad_norm": 0.00038962496910244226,
+      "learning_rate": 3.3967391304347827e-06,
+      "loss": 0.0,
+      "step": 444
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.00036083502345718443,
+      "learning_rate": 3.2608695652173914e-06,
+      "loss": 0.0,
+      "step": 445
+    },
+    {
+      "epoch": 2.8544,
+      "grad_norm": 0.009668043814599514,
+      "learning_rate": 3.125e-06,
+      "loss": 0.0,
+      "step": 446
+    },
+    {
+      "epoch": 2.8608000000000002,
+      "grad_norm": 0.0002053407224593684,
+      "learning_rate": 2.989130434782609e-06,
+      "loss": 0.0,
+      "step": 447
+    },
+    {
+      "epoch": 2.8672,
+      "grad_norm": 0.0004010727861896157,
+      "learning_rate": 2.8532608695652176e-06,
+      "loss": 0.0,
+      "step": 448
+    },
+    {
+      "epoch": 2.8736,
+      "grad_norm": 0.09909164160490036,
+      "learning_rate": 2.7173913043478263e-06,
+      "loss": 0.0002,
+      "step": 449
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.007802205625921488,
+      "learning_rate": 2.581521739130435e-06,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 2.8864,
+      "grad_norm": 0.0001857558818301186,
+      "learning_rate": 2.4456521739130437e-06,
+      "loss": 0.0,
+      "step": 451
+    },
+    {
+      "epoch": 2.8928000000000003,
+      "grad_norm": 0.0010579280788078904,
+      "learning_rate": 2.309782608695652e-06,
+      "loss": 0.0,
+      "step": 452
+    },
+    {
+      "epoch": 2.8992,
+      "grad_norm": 0.00030143753974698484,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 0.0,
+      "step": 453
+    },
+    {
+      "epoch": 2.9055999999999997,
+      "grad_norm": 0.035255249589681625,
+      "learning_rate": 2.03804347826087e-06,
+      "loss": 0.0002,
+      "step": 454
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 0.0001441791100660339,
+      "learning_rate": 1.9021739130434785e-06,
+      "loss": 0.0,
+      "step": 455
+    },
+    {
+      "epoch": 2.9184,
+      "grad_norm": 0.00859628152102232,
+      "learning_rate": 1.7663043478260868e-06,
+      "loss": 0.0,
+      "step": 456
+    },
+    {
+      "epoch": 2.9248,
+      "grad_norm": 0.0001247439649887383,
+      "learning_rate": 1.6304347826086957e-06,
+      "loss": 0.0,
+      "step": 457
+    },
+    {
+      "epoch": 2.9312,
+      "grad_norm": 0.00029591823113150895,
+      "learning_rate": 1.4945652173913044e-06,
+      "loss": 0.0,
+      "step": 458
+    },
+    {
+      "epoch": 2.9375999999999998,
+      "grad_norm": 0.013217011466622353,
+      "learning_rate": 1.3586956521739131e-06,
+      "loss": 0.0,
+      "step": 459
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.031071484088897705,
+      "learning_rate": 1.2228260869565218e-06,
+      "loss": 0.0002,
+      "step": 460
+    },
+    {
+      "epoch": 2.9504,
+      "grad_norm": 0.00017143131117336452,
+      "learning_rate": 1.0869565217391306e-06,
+      "loss": 0.0,
+      "step": 461
+    },
+    {
+      "epoch": 2.9568,
+      "grad_norm": 0.002029558876529336,
+      "learning_rate": 9.510869565217393e-07,
+      "loss": 0.0,
+      "step": 462
+    },
+    {
+      "epoch": 2.9632,
+      "grad_norm": 0.0007615351933054626,
+      "learning_rate": 8.152173913043479e-07,
+      "loss": 0.0,
+      "step": 463
+    },
+    {
+      "epoch": 2.9696,
+      "grad_norm": 0.062321167439222336,
+      "learning_rate": 6.793478260869566e-07,
+      "loss": 0.0004,
+      "step": 464
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.00020992898498661816,
+      "learning_rate": 5.434782608695653e-07,
+      "loss": 0.0,
+      "step": 465
+    },
+    {
+      "epoch": 2.9824,
+      "grad_norm": 0.1477876901626587,
+      "learning_rate": 4.0760869565217393e-07,
+      "loss": 0.0011,
+      "step": 466
+    },
+    {
+      "epoch": 2.9888,
+      "grad_norm": 0.0001347493234788999,
+      "learning_rate": 2.7173913043478264e-07,
+      "loss": 0.0,
+      "step": 467
+    },
+    {
+      "epoch": 2.9952,
+      "grad_norm": 0.00010070588177768514,
+      "learning_rate": 1.3586956521739132e-07,
+      "loss": 0.0,
+      "step": 468
+    },
+    {
+      "epoch": 2.9952,
+      "step": 468,
+      "total_flos": 21600731410432.0,
+      "train_loss": 0.007046422320498982,
+      "train_runtime": 72687.7581,
+      "train_samples_per_second": 0.206,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 468,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 21600731410432.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

0413-7B/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6477218028d49818b20ae2f8827a09d6a56371efaa1ecfb3ac101526d8d6948e
+size 7736