Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* 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
 link-0501-7B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+0523-7B/tokenizer.json filter=lfs diff=lfs merge=lfs -text

0523-7B/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
+}

0523-7B/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
+}

0523-7B/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"
+}

0523-7B/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272fae276174ea05deb18abec7e0a3493df48f4d9096b9cac721b3e01c4fa320
+size 4877660776

0523-7B/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791ad394425df07bc571be4c740aec13c0306b9b360bd2e63a8907a083668e66
+size 4932751008

0523-7B/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b72a2c7f8a61f3b88ca79df7f5590f4603f128f100f89caea60c4329827e38
+size 4330865200

0523-7B/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18993d6ac835a9bda8944ac84265acfd545a1c6dc975d6c21164241845e36bb1
+size 1089994880

0523-7B/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"
+  }
+}

0523-7B/runs/May22_23-28-59_ubuntu-Super-Server/events.out.tfevents.1747927804.ubuntu-Super-Server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7251c274e38f1572b3f99bc9941352f8e26cde969e12b71430f35741a3237e86
+size 84082

0523-7B/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
+  }
+}

0523-7B/tokenizer.json

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

0523-7B/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
+}

0523-7B/trainer_state.json

@@ -0,0 +1,2660 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9946666666666668,
+  "eval_steps": 500,
+  "global_step": 374,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005333333333333333,
+      "grad_norm": 2.9413187503814697,
+      "learning_rate": 0.0,
+      "loss": 0.4429,
+      "step": 1
+    },
+    {
+      "epoch": 0.010666666666666666,
+      "grad_norm": 2.446303129196167,
+      "learning_rate": 7.525749891599529e-06,
+      "loss": 0.3432,
+      "step": 2
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 2.5631747245788574,
+      "learning_rate": 1.192803136799156e-05,
+      "loss": 0.2816,
+      "step": 3
+    },
+    {
+      "epoch": 0.021333333333333333,
+      "grad_norm": 1.3190467357635498,
+      "learning_rate": 1.5051499783199057e-05,
+      "loss": 0.1846,
+      "step": 4
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 1.2335262298583984,
+      "learning_rate": 1.7474250108400467e-05,
+      "loss": 0.0968,
+      "step": 5
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.7208054065704346,
+      "learning_rate": 1.945378125959109e-05,
+      "loss": 0.0681,
+      "step": 6
+    },
+    {
+      "epoch": 0.037333333333333336,
+      "grad_norm": 0.690483033657074,
+      "learning_rate": 2.1127451000356418e-05,
+      "loss": 0.0648,
+      "step": 7
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 0.4134688377380371,
+      "learning_rate": 2.2577249674798584e-05,
+      "loss": 0.0361,
+      "step": 8
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.4609494209289551,
+      "learning_rate": 2.385606273598312e-05,
+      "loss": 0.0328,
+      "step": 9
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.2978796362876892,
+      "learning_rate": 2.4999999999999998e-05,
+      "loss": 0.0208,
+      "step": 10
+    },
+    {
+      "epoch": 0.058666666666666666,
+      "grad_norm": 0.324186772108078,
+      "learning_rate": 2.6034817128955623e-05,
+      "loss": 0.0182,
+      "step": 11
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.23935289680957794,
+      "learning_rate": 2.6979531151190617e-05,
+      "loss": 0.0131,
+      "step": 12
+    },
+    {
+      "epoch": 0.06933333333333333,
+      "grad_norm": 0.2540365755558014,
+      "learning_rate": 2.7848583807670913e-05,
+      "loss": 0.0125,
+      "step": 13
+    },
+    {
+      "epoch": 0.07466666666666667,
+      "grad_norm": 0.24316681921482086,
+      "learning_rate": 2.8653200891955945e-05,
+      "loss": 0.012,
+      "step": 14
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.26236456632614136,
+      "learning_rate": 2.940228147639203e-05,
+      "loss": 0.0102,
+      "step": 15
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 0.3058443069458008,
+      "learning_rate": 3.0102999566398115e-05,
+      "loss": 0.0086,
+      "step": 16
+    },
+    {
+      "epoch": 0.09066666666666667,
+      "grad_norm": 0.3217167854309082,
+      "learning_rate": 3.076122303445685e-05,
+      "loss": 0.0093,
+      "step": 17
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.2659943997859955,
+      "learning_rate": 3.1381812627582646e-05,
+      "loss": 0.009,
+      "step": 18
+    },
+    {
+      "epoch": 0.10133333333333333,
+      "grad_norm": 0.6819332838058472,
+      "learning_rate": 3.1968840023820715e-05,
+      "loss": 0.0154,
+      "step": 19
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.1675225496292114,
+      "learning_rate": 3.2525749891599525e-05,
+      "loss": 0.0103,
+      "step": 20
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.4382905066013336,
+      "learning_rate": 3.305548236834798e-05,
+      "loss": 0.0106,
+      "step": 21
+    },
+    {
+      "epoch": 0.11733333333333333,
+      "grad_norm": 0.7392712235450745,
+      "learning_rate": 3.3560567020555153e-05,
+      "loss": 0.0102,
+      "step": 22
+    },
+    {
+      "epoch": 0.12266666666666666,
+      "grad_norm": 0.38396182656288147,
+      "learning_rate": 3.404319590043982e-05,
+      "loss": 0.0107,
+      "step": 23
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.6184232234954834,
+      "learning_rate": 3.450528104279015e-05,
+      "loss": 0.0138,
+      "step": 24
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.7903351783752441,
+      "learning_rate": 3.4948500216800935e-05,
+      "loss": 0.0114,
+      "step": 25
+    },
+    {
+      "epoch": 0.13866666666666666,
+      "grad_norm": 0.34555312991142273,
+      "learning_rate": 3.537433369927044e-05,
+      "loss": 0.0153,
+      "step": 26
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.3668071925640106,
+      "learning_rate": 3.578409410397468e-05,
+      "loss": 0.0134,
+      "step": 27
+    },
+    {
+      "epoch": 0.14933333333333335,
+      "grad_norm": 0.36643746495246887,
+      "learning_rate": 3.6178950783555475e-05,
+      "loss": 0.0094,
+      "step": 28
+    },
+    {
+      "epoch": 0.15466666666666667,
+      "grad_norm": 0.28532880544662476,
+      "learning_rate": 3.65599499474739e-05,
+      "loss": 0.0069,
+      "step": 29
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.6890357732772827,
+      "learning_rate": 3.6928031367991554e-05,
+      "loss": 0.0098,
+      "step": 30
+    },
+    {
+      "epoch": 0.16533333333333333,
+      "grad_norm": 0.14323797821998596,
+      "learning_rate": 3.728404234585681e-05,
+      "loss": 0.0043,
+      "step": 31
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 0.20452919602394104,
+      "learning_rate": 3.762874945799765e-05,
+      "loss": 0.0042,
+      "step": 32
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.42185941338539124,
+      "learning_rate": 3.796284849694718e-05,
+      "loss": 0.0074,
+      "step": 33
+    },
+    {
+      "epoch": 0.18133333333333335,
+      "grad_norm": 0.19324161112308502,
+      "learning_rate": 3.8286972926056376e-05,
+      "loss": 0.0047,
+      "step": 34
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.243539959192276,
+      "learning_rate": 3.8601701108756885e-05,
+      "loss": 0.0061,
+      "step": 35
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.2372148483991623,
+      "learning_rate": 3.890756251918218e-05,
+      "loss": 0.0076,
+      "step": 36
+    },
+    {
+      "epoch": 0.19733333333333333,
+      "grad_norm": 0.216740682721138,
+      "learning_rate": 3.920504310167487e-05,
+      "loss": 0.0059,
+      "step": 37
+    },
+    {
+      "epoch": 0.20266666666666666,
+      "grad_norm": 0.688544750213623,
+      "learning_rate": 3.949458991542025e-05,
+      "loss": 0.004,
+      "step": 38
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.9698823094367981,
+      "learning_rate": 3.977661517566247e-05,
+      "loss": 0.01,
+      "step": 39
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.2954489290714264,
+      "learning_rate": 4.005149978319905e-05,
+      "loss": 0.0049,
+      "step": 40
+    },
+    {
+      "epoch": 0.21866666666666668,
+      "grad_norm": 0.22238951921463013,
+      "learning_rate": 4.031959641799338e-05,
+      "loss": 0.0075,
+      "step": 41
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.7678313255310059,
+      "learning_rate": 4.058123225994751e-05,
+      "loss": 0.0088,
+      "step": 42
+    },
+    {
+      "epoch": 0.22933333333333333,
+      "grad_norm": 2.2891924381256104,
+      "learning_rate": 4.0836711389489654e-05,
+      "loss": 0.0187,
+      "step": 43
+    },
+    {
+      "epoch": 0.23466666666666666,
+      "grad_norm": 0.1324312686920166,
+      "learning_rate": 4.108631691215468e-05,
+      "loss": 0.0016,
+      "step": 44
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.32060351967811584,
+      "learning_rate": 4.133031284438358e-05,
+      "loss": 0.0041,
+      "step": 45
+    },
+    {
+      "epoch": 0.24533333333333332,
+      "grad_norm": 0.6070859432220459,
+      "learning_rate": 4.156894579203935e-05,
+      "loss": 0.0081,
+      "step": 46
+    },
+    {
+      "epoch": 0.25066666666666665,
+      "grad_norm": 0.16598281264305115,
+      "learning_rate": 4.180244644839293e-05,
+      "loss": 0.0044,
+      "step": 47
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.7388269901275635,
+      "learning_rate": 4.203103093438968e-05,
+      "loss": 0.0109,
+      "step": 48
+    },
+    {
+      "epoch": 0.2613333333333333,
+      "grad_norm": 0.1603352576494217,
+      "learning_rate": 4.2254902000712836e-05,
+      "loss": 0.0041,
+      "step": 49
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.29616779088974,
+      "learning_rate": 4.247425010840046e-05,
+      "loss": 0.0037,
+      "step": 50
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.7053483724594116,
+      "learning_rate": 4.2689254402448405e-05,
+      "loss": 0.0047,
+      "step": 51
+    },
+    {
+      "epoch": 0.2773333333333333,
+      "grad_norm": 0.1470181792974472,
+      "learning_rate": 4.290008359086998e-05,
+      "loss": 0.0032,
+      "step": 52
+    },
+    {
+      "epoch": 0.2826666666666667,
+      "grad_norm": 0.18102477490901947,
+      "learning_rate": 4.310689674001973e-05,
+      "loss": 0.0037,
+      "step": 53
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.2504118084907532,
+      "learning_rate": 4.330984399557421e-05,
+      "loss": 0.0077,
+      "step": 54
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.29302382469177246,
+      "learning_rate": 4.350906723735609e-05,
+      "loss": 0.0034,
+      "step": 55
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": 0.24058617651462555,
+      "learning_rate": 4.370470067515501e-05,
+      "loss": 0.006,
+      "step": 56
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.3615986406803131,
+      "learning_rate": 4.3896871391812285e-05,
+      "loss": 0.0058,
+      "step": 57
+    },
+    {
+      "epoch": 0.30933333333333335,
+      "grad_norm": 0.2254834622144699,
+      "learning_rate": 4.408569983907343e-05,
+      "loss": 0.0038,
+      "step": 58
+    },
+    {
+      "epoch": 0.31466666666666665,
+      "grad_norm": 0.22524742782115936,
+      "learning_rate": 4.42713002910536e-05,
+      "loss": 0.004,
+      "step": 59
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.19852247834205627,
+      "learning_rate": 4.445378125959108e-05,
+      "loss": 0.0062,
+      "step": 60
+    },
+    {
+      "epoch": 0.3253333333333333,
+      "grad_norm": 0.06762774288654327,
+      "learning_rate": 4.463324587526917e-05,
+      "loss": 0.0019,
+      "step": 61
+    },
+    {
+      "epoch": 0.33066666666666666,
+      "grad_norm": 0.18688730895519257,
+      "learning_rate": 4.4809792237456346e-05,
+      "loss": 0.0054,
+      "step": 62
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.243905171751976,
+      "learning_rate": 4.498351373633954e-05,
+      "loss": 0.0046,
+      "step": 63
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 0.2549966871738434,
+      "learning_rate": 4.515449934959717e-05,
+      "loss": 0.0067,
+      "step": 64
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.18205155432224274,
+      "learning_rate": 4.532283391607138e-05,
+      "loss": 0.005,
+      "step": 65
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.1726597249507904,
+      "learning_rate": 4.548859838854671e-05,
+      "loss": 0.0013,
+      "step": 66
+    },
+    {
+      "epoch": 0.35733333333333334,
+      "grad_norm": 0.14692839980125427,
+      "learning_rate": 4.565187006752065e-05,
+      "loss": 0.0037,
+      "step": 67
+    },
+    {
+      "epoch": 0.3626666666666667,
+      "grad_norm": 0.10036856681108475,
+      "learning_rate": 4.581272281765591e-05,
+      "loss": 0.0012,
+      "step": 68
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.24854883551597595,
+      "learning_rate": 4.597122726843138e-05,
+      "loss": 0.0034,
+      "step": 69
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.6048113107681274,
+      "learning_rate": 4.612745100035642e-05,
+      "loss": 0.0072,
+      "step": 70
+    },
+    {
+      "epoch": 0.37866666666666665,
+      "grad_norm": 0.0997704416513443,
+      "learning_rate": 4.628145871797688e-05,
+      "loss": 0.0025,
+      "step": 71
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.4034624695777893,
+      "learning_rate": 4.643331241078171e-05,
+      "loss": 0.0018,
+      "step": 72
+    },
+    {
+      "epoch": 0.3893333333333333,
+      "grad_norm": 0.21421776711940765,
+      "learning_rate": 4.658307150301139e-05,
+      "loss": 0.0061,
+      "step": 73
+    },
+    {
+      "epoch": 0.39466666666666667,
+      "grad_norm": 0.4393751919269562,
+      "learning_rate": 4.67307929932744e-05,
+      "loss": 0.0048,
+      "step": 74
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.0990038812160492,
+      "learning_rate": 4.687653158479249e-05,
+      "loss": 0.0037,
+      "step": 75
+    },
+    {
+      "epoch": 0.4053333333333333,
+      "grad_norm": 0.31288838386535645,
+      "learning_rate": 4.702033980701978e-05,
+      "loss": 0.0024,
+      "step": 76
+    },
+    {
+      "epoch": 0.4106666666666667,
+      "grad_norm": 0.17511579394340515,
+      "learning_rate": 4.716226812931204e-05,
+      "loss": 0.0027,
+      "step": 77
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.4094139635562897,
+      "learning_rate": 4.7302365067262006e-05,
+      "loss": 0.0053,
+      "step": 78
+    },
+    {
+      "epoch": 0.42133333333333334,
+      "grad_norm": 0.2607367932796478,
+      "learning_rate": 4.744067728226103e-05,
+      "loss": 0.006,
+      "step": 79
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.04099046811461449,
+      "learning_rate": 4.757724967479858e-05,
+      "loss": 0.0005,
+      "step": 80
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.06899389624595642,
+      "learning_rate": 4.771212547196624e-05,
+      "loss": 0.001,
+      "step": 81
+    },
+    {
+      "epoch": 0.43733333333333335,
+      "grad_norm": 0.23175401985645294,
+      "learning_rate": 4.7845346309592914e-05,
+      "loss": 0.004,
+      "step": 82
+    },
+    {
+      "epoch": 0.44266666666666665,
+      "grad_norm": 0.14652466773986816,
+      "learning_rate": 4.7976952309401844e-05,
+      "loss": 0.003,
+      "step": 83
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.22168171405792236,
+      "learning_rate": 4.810698215154703e-05,
+      "loss": 0.0018,
+      "step": 84
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.1058434471487999,
+      "learning_rate": 4.823547314285732e-05,
+      "loss": 0.0013,
+      "step": 85
+    },
+    {
+      "epoch": 0.45866666666666667,
+      "grad_norm": 0.0505114309489727,
+      "learning_rate": 4.836246128108918e-05,
+      "loss": 0.0006,
+      "step": 86
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.08828063309192657,
+      "learning_rate": 4.8487981315465456e-05,
+      "loss": 0.0005,
+      "step": 87
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": 0.03805112466216087,
+      "learning_rate": 4.8612066803754214e-05,
+      "loss": 0.0005,
+      "step": 88
+    },
+    {
+      "epoch": 0.4746666666666667,
+      "grad_norm": 0.23209308087825775,
+      "learning_rate": 4.873475016612281e-05,
+      "loss": 0.0019,
+      "step": 89
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.09479185938835144,
+      "learning_rate": 4.885606273598312e-05,
+      "loss": 0.0014,
+      "step": 90
+    },
+    {
+      "epoch": 0.48533333333333334,
+      "grad_norm": 0.23439030349254608,
+      "learning_rate": 4.897603480802733e-05,
+      "loss": 0.0043,
+      "step": 91
+    },
+    {
+      "epoch": 0.49066666666666664,
+      "grad_norm": 0.06992974132299423,
+      "learning_rate": 4.909469568363888e-05,
+      "loss": 0.0005,
+      "step": 92
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.2401672601699829,
+      "learning_rate": 4.9212073713848375e-05,
+      "loss": 0.002,
+      "step": 93
+    },
+    {
+      "epoch": 0.5013333333333333,
+      "grad_norm": 0.023669244721531868,
+      "learning_rate": 4.932819633999246e-05,
+      "loss": 0.0002,
+      "step": 94
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.16149063408374786,
+      "learning_rate": 4.9443090132221186e-05,
+      "loss": 0.0007,
+      "step": 95
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.13521939516067505,
+      "learning_rate": 4.9556780825989205e-05,
+      "loss": 0.0015,
+      "step": 96
+    },
+    {
+      "epoch": 0.5173333333333333,
+      "grad_norm": 0.16658346354961395,
+      "learning_rate": 4.9669293356656114e-05,
+      "loss": 0.0023,
+      "step": 97
+    },
+    {
+      "epoch": 0.5226666666666666,
+      "grad_norm": 0.20741115510463715,
+      "learning_rate": 4.978065189231237e-05,
+      "loss": 0.0023,
+      "step": 98
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5959545969963074,
+      "learning_rate": 4.989087986493874e-05,
+      "loss": 0.0026,
+      "step": 99
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.0525498390197754,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 0.0024,
+      "step": 100
+    },
+    {
+      "epoch": 0.5386666666666666,
+      "grad_norm": 0.49121907353401184,
+      "learning_rate": 5e-05,
+      "loss": 0.0068,
+      "step": 101
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.1075739711523056,
+      "learning_rate": 4.981751824817518e-05,
+      "loss": 0.0032,
+      "step": 102
+    },
+    {
+      "epoch": 0.5493333333333333,
+      "grad_norm": 0.47708404064178467,
+      "learning_rate": 4.963503649635037e-05,
+      "loss": 0.0063,
+      "step": 103
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 0.8345000743865967,
+      "learning_rate": 4.945255474452555e-05,
+      "loss": 0.0108,
+      "step": 104
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.5016416311264038,
+      "learning_rate": 4.927007299270073e-05,
+      "loss": 0.0106,
+      "step": 105
+    },
+    {
+      "epoch": 0.5653333333333334,
+      "grad_norm": 0.2646836042404175,
+      "learning_rate": 4.908759124087591e-05,
+      "loss": 0.0031,
+      "step": 106
+    },
+    {
+      "epoch": 0.5706666666666667,
+      "grad_norm": 0.2920669913291931,
+      "learning_rate": 4.89051094890511e-05,
+      "loss": 0.005,
+      "step": 107
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.29464277625083923,
+      "learning_rate": 4.872262773722628e-05,
+      "loss": 0.0031,
+      "step": 108
+    },
+    {
+      "epoch": 0.5813333333333334,
+      "grad_norm": 0.1755901575088501,
+      "learning_rate": 4.854014598540147e-05,
+      "loss": 0.0026,
+      "step": 109
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.16949675977230072,
+      "learning_rate": 4.835766423357664e-05,
+      "loss": 0.0022,
+      "step": 110
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.11515118926763535,
+      "learning_rate": 4.817518248175183e-05,
+      "loss": 0.0018,
+      "step": 111
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 0.15377497673034668,
+      "learning_rate": 4.799270072992701e-05,
+      "loss": 0.0015,
+      "step": 112
+    },
+    {
+      "epoch": 0.6026666666666667,
+      "grad_norm": 0.13871601223945618,
+      "learning_rate": 4.7810218978102196e-05,
+      "loss": 0.0025,
+      "step": 113
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.1464899629354477,
+      "learning_rate": 4.762773722627738e-05,
+      "loss": 0.0026,
+      "step": 114
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.2561844289302826,
+      "learning_rate": 4.744525547445256e-05,
+      "loss": 0.003,
+      "step": 115
+    },
+    {
+      "epoch": 0.6186666666666667,
+      "grad_norm": 0.060167670249938965,
+      "learning_rate": 4.726277372262774e-05,
+      "loss": 0.0008,
+      "step": 116
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.24895896017551422,
+      "learning_rate": 4.708029197080292e-05,
+      "loss": 0.0054,
+      "step": 117
+    },
+    {
+      "epoch": 0.6293333333333333,
+      "grad_norm": 0.25536859035491943,
+      "learning_rate": 4.6897810218978106e-05,
+      "loss": 0.0041,
+      "step": 118
+    },
+    {
+      "epoch": 0.6346666666666667,
+      "grad_norm": 0.11634501814842224,
+      "learning_rate": 4.6715328467153287e-05,
+      "loss": 0.0017,
+      "step": 119
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.0891045480966568,
+      "learning_rate": 4.6532846715328474e-05,
+      "loss": 0.0027,
+      "step": 120
+    },
+    {
+      "epoch": 0.6453333333333333,
+      "grad_norm": 0.22870613634586334,
+      "learning_rate": 4.635036496350365e-05,
+      "loss": 0.0025,
+      "step": 121
+    },
+    {
+      "epoch": 0.6506666666666666,
+      "grad_norm": 0.16444182395935059,
+      "learning_rate": 4.6167883211678835e-05,
+      "loss": 0.0018,
+      "step": 122
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.736554741859436,
+      "learning_rate": 4.5985401459854016e-05,
+      "loss": 0.0035,
+      "step": 123
+    },
+    {
+      "epoch": 0.6613333333333333,
+      "grad_norm": 0.07803163677453995,
+      "learning_rate": 4.58029197080292e-05,
+      "loss": 0.0011,
+      "step": 124
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.23748189210891724,
+      "learning_rate": 4.5620437956204383e-05,
+      "loss": 0.0028,
+      "step": 125
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.21093794703483582,
+      "learning_rate": 4.5437956204379564e-05,
+      "loss": 0.0072,
+      "step": 126
+    },
+    {
+      "epoch": 0.6773333333333333,
+      "grad_norm": 0.15632648766040802,
+      "learning_rate": 4.5255474452554745e-05,
+      "loss": 0.0034,
+      "step": 127
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 0.16710951924324036,
+      "learning_rate": 4.5072992700729925e-05,
+      "loss": 0.0034,
+      "step": 128
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.42606690526008606,
+      "learning_rate": 4.489051094890511e-05,
+      "loss": 0.0057,
+      "step": 129
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.2917795777320862,
+      "learning_rate": 4.470802919708029e-05,
+      "loss": 0.004,
+      "step": 130
+    },
+    {
+      "epoch": 0.6986666666666667,
+      "grad_norm": 0.20603737235069275,
+      "learning_rate": 4.452554744525548e-05,
+      "loss": 0.0038,
+      "step": 131
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.13243572413921356,
+      "learning_rate": 4.434306569343066e-05,
+      "loss": 0.0016,
+      "step": 132
+    },
+    {
+      "epoch": 0.7093333333333334,
+      "grad_norm": 0.09980319440364838,
+      "learning_rate": 4.416058394160584e-05,
+      "loss": 0.002,
+      "step": 133
+    },
+    {
+      "epoch": 0.7146666666666667,
+      "grad_norm": 0.030429158359766006,
+      "learning_rate": 4.397810218978102e-05,
+      "loss": 0.0006,
+      "step": 134
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.14878709614276886,
+      "learning_rate": 4.379562043795621e-05,
+      "loss": 0.0009,
+      "step": 135
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 0.06722039729356766,
+      "learning_rate": 4.361313868613139e-05,
+      "loss": 0.0014,
+      "step": 136
+    },
+    {
+      "epoch": 0.7306666666666667,
+      "grad_norm": 0.15758465230464935,
+      "learning_rate": 4.343065693430657e-05,
+      "loss": 0.0016,
+      "step": 137
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.09762876480817795,
+      "learning_rate": 4.324817518248175e-05,
+      "loss": 0.0007,
+      "step": 138
+    },
+    {
+      "epoch": 0.7413333333333333,
+      "grad_norm": 0.07396102696657181,
+      "learning_rate": 4.306569343065693e-05,
+      "loss": 0.001,
+      "step": 139
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.07269494980573654,
+      "learning_rate": 4.288321167883212e-05,
+      "loss": 0.0008,
+      "step": 140
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.026683906093239784,
+      "learning_rate": 4.27007299270073e-05,
+      "loss": 0.0003,
+      "step": 141
+    },
+    {
+      "epoch": 0.7573333333333333,
+      "grad_norm": 0.08903524279594421,
+      "learning_rate": 4.251824817518249e-05,
+      "loss": 0.0017,
+      "step": 142
+    },
+    {
+      "epoch": 0.7626666666666667,
+      "grad_norm": 0.11091341078281403,
+      "learning_rate": 4.233576642335767e-05,
+      "loss": 0.0031,
+      "step": 143
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.05621659755706787,
+      "learning_rate": 4.215328467153285e-05,
+      "loss": 0.0004,
+      "step": 144
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.04461882263422012,
+      "learning_rate": 4.197080291970803e-05,
+      "loss": 0.0004,
+      "step": 145
+    },
+    {
+      "epoch": 0.7786666666666666,
+      "grad_norm": 0.035506390035152435,
+      "learning_rate": 4.1788321167883216e-05,
+      "loss": 0.0003,
+      "step": 146
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.11772796511650085,
+      "learning_rate": 4.16058394160584e-05,
+      "loss": 0.0018,
+      "step": 147
+    },
+    {
+      "epoch": 0.7893333333333333,
+      "grad_norm": 0.024260057136416435,
+      "learning_rate": 4.1423357664233584e-05,
+      "loss": 0.0005,
+      "step": 148
+    },
+    {
+      "epoch": 0.7946666666666666,
+      "grad_norm": 0.07729806751012802,
+      "learning_rate": 4.124087591240876e-05,
+      "loss": 0.0026,
+      "step": 149
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.1422155350446701,
+      "learning_rate": 4.1058394160583945e-05,
+      "loss": 0.0005,
+      "step": 150
+    },
+    {
+      "epoch": 0.8053333333333333,
+      "grad_norm": 0.23396533727645874,
+      "learning_rate": 4.0875912408759126e-05,
+      "loss": 0.0016,
+      "step": 151
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 0.05502787232398987,
+      "learning_rate": 4.0693430656934306e-05,
+      "loss": 0.0004,
+      "step": 152
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.07522756606340408,
+      "learning_rate": 4.0510948905109494e-05,
+      "loss": 0.0008,
+      "step": 153
+    },
+    {
+      "epoch": 0.8213333333333334,
+      "grad_norm": 0.060790009796619415,
+      "learning_rate": 4.0328467153284674e-05,
+      "loss": 0.0003,
+      "step": 154
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.06975127011537552,
+      "learning_rate": 4.0145985401459855e-05,
+      "loss": 0.0002,
+      "step": 155
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.040823861956596375,
+      "learning_rate": 3.9963503649635035e-05,
+      "loss": 0.0002,
+      "step": 156
+    },
+    {
+      "epoch": 0.8373333333333334,
+      "grad_norm": 0.0562555305659771,
+      "learning_rate": 3.978102189781022e-05,
+      "loss": 0.0003,
+      "step": 157
+    },
+    {
+      "epoch": 0.8426666666666667,
+      "grad_norm": 0.009089924395084381,
+      "learning_rate": 3.95985401459854e-05,
+      "loss": 0.0001,
+      "step": 158
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.13992078602313995,
+      "learning_rate": 3.941605839416059e-05,
+      "loss": 0.0005,
+      "step": 159
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.050887301564216614,
+      "learning_rate": 3.9233576642335764e-05,
+      "loss": 0.0002,
+      "step": 160
+    },
+    {
+      "epoch": 0.8586666666666667,
+      "grad_norm": 0.12812073528766632,
+      "learning_rate": 3.905109489051095e-05,
+      "loss": 0.0014,
+      "step": 161
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.07695231586694717,
+      "learning_rate": 3.886861313868613e-05,
+      "loss": 0.0003,
+      "step": 162
+    },
+    {
+      "epoch": 0.8693333333333333,
+      "grad_norm": 0.012387621216475964,
+      "learning_rate": 3.868613138686132e-05,
+      "loss": 0.0,
+      "step": 163
+    },
+    {
+      "epoch": 0.8746666666666667,
+      "grad_norm": 0.04443414509296417,
+      "learning_rate": 3.85036496350365e-05,
+      "loss": 0.0002,
+      "step": 164
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.025295278057456017,
+      "learning_rate": 3.832116788321168e-05,
+      "loss": 0.0001,
+      "step": 165
+    },
+    {
+      "epoch": 0.8853333333333333,
+      "grad_norm": 0.0721285492181778,
+      "learning_rate": 3.813868613138686e-05,
+      "loss": 0.0002,
+      "step": 166
+    },
+    {
+      "epoch": 0.8906666666666667,
+      "grad_norm": 0.24604493379592896,
+      "learning_rate": 3.795620437956204e-05,
+      "loss": 0.0003,
+      "step": 167
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.07480332255363464,
+      "learning_rate": 3.777372262773723e-05,
+      "loss": 0.0006,
+      "step": 168
+    },
+    {
+      "epoch": 0.9013333333333333,
+      "grad_norm": 0.06691287457942963,
+      "learning_rate": 3.759124087591241e-05,
+      "loss": 0.0004,
+      "step": 169
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.006208790000528097,
+      "learning_rate": 3.74087591240876e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.22023215889930725,
+      "learning_rate": 3.722627737226278e-05,
+      "loss": 0.0019,
+      "step": 171
+    },
+    {
+      "epoch": 0.9173333333333333,
+      "grad_norm": 0.01856170780956745,
+      "learning_rate": 3.704379562043796e-05,
+      "loss": 0.0,
+      "step": 172
+    },
+    {
+      "epoch": 0.9226666666666666,
+      "grad_norm": 0.13964107632637024,
+      "learning_rate": 3.686131386861314e-05,
+      "loss": 0.0007,
+      "step": 173
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.14954520761966705,
+      "learning_rate": 3.6678832116788326e-05,
+      "loss": 0.0027,
+      "step": 174
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.15485315024852753,
+      "learning_rate": 3.649635036496351e-05,
+      "loss": 0.0015,
+      "step": 175
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 0.07000021636486053,
+      "learning_rate": 3.631386861313869e-05,
+      "loss": 0.0005,
+      "step": 176
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.02640976756811142,
+      "learning_rate": 3.613138686131387e-05,
+      "loss": 0.0007,
+      "step": 177
+    },
+    {
+      "epoch": 0.9493333333333334,
+      "grad_norm": 0.03009864129126072,
+      "learning_rate": 3.594890510948905e-05,
+      "loss": 0.0002,
+      "step": 178
+    },
+    {
+      "epoch": 0.9546666666666667,
+      "grad_norm": 0.009256584569811821,
+      "learning_rate": 3.5766423357664236e-05,
+      "loss": 0.0,
+      "step": 179
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.004564735107123852,
+      "learning_rate": 3.5583941605839416e-05,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.9653333333333334,
+      "grad_norm": 0.02988441474735737,
+      "learning_rate": 3.5401459854014604e-05,
+      "loss": 0.0002,
+      "step": 181
+    },
+    {
+      "epoch": 0.9706666666666667,
+      "grad_norm": 0.07743508368730545,
+      "learning_rate": 3.5218978102189784e-05,
+      "loss": 0.0019,
+      "step": 182
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.3144683241844177,
+      "learning_rate": 3.5036496350364965e-05,
+      "loss": 0.0012,
+      "step": 183
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 0.033418331295251846,
+      "learning_rate": 3.4854014598540145e-05,
+      "loss": 0.0003,
+      "step": 184
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 0.08263418823480606,
+      "learning_rate": 3.467153284671533e-05,
+      "loss": 0.0004,
+      "step": 185
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.0285032968968153,
+      "learning_rate": 3.448905109489051e-05,
+      "loss": 0.0001,
+      "step": 186
+    },
+    {
+      "epoch": 0.9973333333333333,
+      "grad_norm": 0.04995943233370781,
+      "learning_rate": 3.43065693430657e-05,
+      "loss": 0.0014,
+      "step": 187
+    },
+    {
+      "epoch": 1.0026666666666666,
+      "grad_norm": 0.4158555567264557,
+      "learning_rate": 3.4124087591240875e-05,
+      "loss": 0.0069,
+      "step": 188
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.005976259242743254,
+      "learning_rate": 3.3941605839416055e-05,
+      "loss": 0.0,
+      "step": 189
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.0074442625045776,
+      "learning_rate": 3.375912408759124e-05,
+      "loss": 0.003,
+      "step": 190
+    },
+    {
+      "epoch": 1.0186666666666666,
+      "grad_norm": 0.07213623821735382,
+      "learning_rate": 3.357664233576642e-05,
+      "loss": 0.0013,
+      "step": 191
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.25851497054100037,
+      "learning_rate": 3.339416058394161e-05,
+      "loss": 0.0085,
+      "step": 192
+    },
+    {
+      "epoch": 1.0293333333333334,
+      "grad_norm": 0.2206096351146698,
+      "learning_rate": 3.321167883211679e-05,
+      "loss": 0.0062,
+      "step": 193
+    },
+    {
+      "epoch": 1.0346666666666666,
+      "grad_norm": 0.15963461995124817,
+      "learning_rate": 3.302919708029197e-05,
+      "loss": 0.0027,
+      "step": 194
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.0987771525979042,
+      "learning_rate": 3.284671532846715e-05,
+      "loss": 0.0025,
+      "step": 195
+    },
+    {
+      "epoch": 1.0453333333333332,
+      "grad_norm": 0.22656488418579102,
+      "learning_rate": 3.266423357664234e-05,
+      "loss": 0.0041,
+      "step": 196
+    },
+    {
+      "epoch": 1.0506666666666666,
+      "grad_norm": 0.09620988368988037,
+      "learning_rate": 3.248175182481752e-05,
+      "loss": 0.002,
+      "step": 197
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.1066923439502716,
+      "learning_rate": 3.229927007299271e-05,
+      "loss": 0.0014,
+      "step": 198
+    },
+    {
+      "epoch": 1.0613333333333332,
+      "grad_norm": 0.11614212393760681,
+      "learning_rate": 3.211678832116788e-05,
+      "loss": 0.0033,
+      "step": 199
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.08868183195590973,
+      "learning_rate": 3.193430656934307e-05,
+      "loss": 0.0021,
+      "step": 200
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.1411479264497757,
+      "learning_rate": 3.175182481751825e-05,
+      "loss": 0.0028,
+      "step": 201
+    },
+    {
+      "epoch": 1.0773333333333333,
+      "grad_norm": 0.09516854584217072,
+      "learning_rate": 3.156934306569343e-05,
+      "loss": 0.0018,
+      "step": 202
+    },
+    {
+      "epoch": 1.0826666666666667,
+      "grad_norm": 0.13133355975151062,
+      "learning_rate": 3.138686131386862e-05,
+      "loss": 0.0023,
+      "step": 203
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.07525645196437836,
+      "learning_rate": 3.12043795620438e-05,
+      "loss": 0.0006,
+      "step": 204
+    },
+    {
+      "epoch": 1.0933333333333333,
+      "grad_norm": 0.01906648278236389,
+      "learning_rate": 3.102189781021898e-05,
+      "loss": 0.0004,
+      "step": 205
+    },
+    {
+      "epoch": 1.0986666666666667,
+      "grad_norm": 0.039688821882009506,
+      "learning_rate": 3.083941605839416e-05,
+      "loss": 0.0015,
+      "step": 206
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.16845063865184784,
+      "learning_rate": 3.0656934306569346e-05,
+      "loss": 0.0009,
+      "step": 207
+    },
+    {
+      "epoch": 1.1093333333333333,
+      "grad_norm": 0.09683395177125931,
+      "learning_rate": 3.0474452554744527e-05,
+      "loss": 0.0006,
+      "step": 208
+    },
+    {
+      "epoch": 1.1146666666666667,
+      "grad_norm": 0.10101410746574402,
+      "learning_rate": 3.029197080291971e-05,
+      "loss": 0.0012,
+      "step": 209
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.023283949121832848,
+      "learning_rate": 3.010948905109489e-05,
+      "loss": 0.0004,
+      "step": 210
+    },
+    {
+      "epoch": 1.1253333333333333,
+      "grad_norm": 0.0136113241314888,
+      "learning_rate": 2.992700729927008e-05,
+      "loss": 0.0002,
+      "step": 211
+    },
+    {
+      "epoch": 1.1306666666666667,
+      "grad_norm": 0.01744314469397068,
+      "learning_rate": 2.9744525547445256e-05,
+      "loss": 0.0002,
+      "step": 212
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.11486854404211044,
+      "learning_rate": 2.9562043795620443e-05,
+      "loss": 0.0005,
+      "step": 213
+    },
+    {
+      "epoch": 1.1413333333333333,
+      "grad_norm": 0.014912755228579044,
+      "learning_rate": 2.9379562043795624e-05,
+      "loss": 0.0001,
+      "step": 214
+    },
+    {
+      "epoch": 1.1466666666666667,
+      "grad_norm": 0.06912944465875626,
+      "learning_rate": 2.91970802919708e-05,
+      "loss": 0.0009,
+      "step": 215
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.016298551112413406,
+      "learning_rate": 2.9014598540145988e-05,
+      "loss": 0.0001,
+      "step": 216
+    },
+    {
+      "epoch": 1.1573333333333333,
+      "grad_norm": 0.05211088806390762,
+      "learning_rate": 2.883211678832117e-05,
+      "loss": 0.0005,
+      "step": 217
+    },
+    {
+      "epoch": 1.1626666666666667,
+      "grad_norm": 0.11012383550405502,
+      "learning_rate": 2.8649635036496353e-05,
+      "loss": 0.0006,
+      "step": 218
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.04871580749750137,
+      "learning_rate": 2.8467153284671533e-05,
+      "loss": 0.0003,
+      "step": 219
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 0.021775316447019577,
+      "learning_rate": 2.8284671532846717e-05,
+      "loss": 0.0002,
+      "step": 220
+    },
+    {
+      "epoch": 1.1786666666666668,
+      "grad_norm": 0.07081250846385956,
+      "learning_rate": 2.8102189781021898e-05,
+      "loss": 0.001,
+      "step": 221
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.025569811463356018,
+      "learning_rate": 2.7919708029197085e-05,
+      "loss": 0.0011,
+      "step": 222
+    },
+    {
+      "epoch": 1.1893333333333334,
+      "grad_norm": 0.00547533156350255,
+      "learning_rate": 2.7737226277372262e-05,
+      "loss": 0.0001,
+      "step": 223
+    },
+    {
+      "epoch": 1.1946666666666665,
+      "grad_norm": 0.013466394506394863,
+      "learning_rate": 2.755474452554745e-05,
+      "loss": 0.0001,
+      "step": 224
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.10368271917104721,
+      "learning_rate": 2.737226277372263e-05,
+      "loss": 0.0003,
+      "step": 225
+    },
+    {
+      "epoch": 1.2053333333333334,
+      "grad_norm": 0.021985536441206932,
+      "learning_rate": 2.7189781021897807e-05,
+      "loss": 0.0001,
+      "step": 226
+    },
+    {
+      "epoch": 1.2106666666666666,
+      "grad_norm": 0.05518456548452377,
+      "learning_rate": 2.7007299270072995e-05,
+      "loss": 0.0006,
+      "step": 227
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.06858678162097931,
+      "learning_rate": 2.6824817518248175e-05,
+      "loss": 0.0005,
+      "step": 228
+    },
+    {
+      "epoch": 1.2213333333333334,
+      "grad_norm": 0.0051900409162044525,
+      "learning_rate": 2.664233576642336e-05,
+      "loss": 0.0,
+      "step": 229
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 0.006526219192892313,
+      "learning_rate": 2.645985401459854e-05,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.03130416199564934,
+      "learning_rate": 2.6277372262773724e-05,
+      "loss": 0.0008,
+      "step": 231
+    },
+    {
+      "epoch": 1.2373333333333334,
+      "grad_norm": 0.10826513916254044,
+      "learning_rate": 2.6094890510948904e-05,
+      "loss": 0.0007,
+      "step": 232
+    },
+    {
+      "epoch": 1.2426666666666666,
+      "grad_norm": 0.04443765804171562,
+      "learning_rate": 2.591240875912409e-05,
+      "loss": 0.0001,
+      "step": 233
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.15472383797168732,
+      "learning_rate": 2.572992700729927e-05,
+      "loss": 0.0003,
+      "step": 234
+    },
+    {
+      "epoch": 1.2533333333333334,
+      "grad_norm": 0.02203129604458809,
+      "learning_rate": 2.5547445255474456e-05,
+      "loss": 0.0001,
+      "step": 235
+    },
+    {
+      "epoch": 1.2586666666666666,
+      "grad_norm": 0.06961119920015335,
+      "learning_rate": 2.5364963503649637e-05,
+      "loss": 0.0003,
+      "step": 236
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.002264423994347453,
+      "learning_rate": 2.518248175182482e-05,
+      "loss": 0.0,
+      "step": 237
+    },
+    {
+      "epoch": 1.2693333333333334,
+      "grad_norm": 0.04599235579371452,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0013,
+      "step": 238
+    },
+    {
+      "epoch": 1.2746666666666666,
+      "grad_norm": 0.019364362582564354,
+      "learning_rate": 2.4817518248175185e-05,
+      "loss": 0.001,
+      "step": 239
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.01742694340646267,
+      "learning_rate": 2.4635036496350366e-05,
+      "loss": 0.0001,
+      "step": 240
+    },
+    {
+      "epoch": 1.2853333333333334,
+      "grad_norm": 0.001203986699692905,
+      "learning_rate": 2.445255474452555e-05,
+      "loss": 0.0,
+      "step": 241
+    },
+    {
+      "epoch": 1.2906666666666666,
+      "grad_norm": 0.040978461503982544,
+      "learning_rate": 2.4270072992700734e-05,
+      "loss": 0.0003,
+      "step": 242
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.07201758772134781,
+      "learning_rate": 2.4087591240875914e-05,
+      "loss": 0.0005,
+      "step": 243
+    },
+    {
+      "epoch": 1.3013333333333335,
+      "grad_norm": 0.0022849412634968758,
+      "learning_rate": 2.3905109489051098e-05,
+      "loss": 0.0,
+      "step": 244
+    },
+    {
+      "epoch": 1.3066666666666666,
+      "grad_norm": 0.13902343809604645,
+      "learning_rate": 2.372262773722628e-05,
+      "loss": 0.0015,
+      "step": 245
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.1383124440908432,
+      "learning_rate": 2.354014598540146e-05,
+      "loss": 0.0005,
+      "step": 246
+    },
+    {
+      "epoch": 1.3173333333333335,
+      "grad_norm": 0.041491296142339706,
+      "learning_rate": 2.3357664233576643e-05,
+      "loss": 0.0001,
+      "step": 247
+    },
+    {
+      "epoch": 1.3226666666666667,
+      "grad_norm": 0.001538380398415029,
+      "learning_rate": 2.3175182481751824e-05,
+      "loss": 0.0,
+      "step": 248
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.0005762208602391183,
+      "learning_rate": 2.2992700729927008e-05,
+      "loss": 0.0,
+      "step": 249
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.02000562660396099,
+      "learning_rate": 2.2810218978102192e-05,
+      "loss": 0.0012,
+      "step": 250
+    },
+    {
+      "epoch": 1.3386666666666667,
+      "grad_norm": 0.0015275335172191262,
+      "learning_rate": 2.2627737226277372e-05,
+      "loss": 0.0,
+      "step": 251
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.024008644744753838,
+      "learning_rate": 2.2445255474452556e-05,
+      "loss": 0.0012,
+      "step": 252
+    },
+    {
+      "epoch": 1.3493333333333333,
+      "grad_norm": 0.009711493737995625,
+      "learning_rate": 2.226277372262774e-05,
+      "loss": 0.0001,
+      "step": 253
+    },
+    {
+      "epoch": 1.3546666666666667,
+      "grad_norm": 0.14969904720783234,
+      "learning_rate": 2.208029197080292e-05,
+      "loss": 0.0013,
+      "step": 254
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.0006140850600786507,
+      "learning_rate": 2.1897810218978105e-05,
+      "loss": 0.0,
+      "step": 255
+    },
+    {
+      "epoch": 1.3653333333333333,
+      "grad_norm": 0.07702767103910446,
+      "learning_rate": 2.1715328467153285e-05,
+      "loss": 0.0011,
+      "step": 256
+    },
+    {
+      "epoch": 1.3706666666666667,
+      "grad_norm": 0.02910340391099453,
+      "learning_rate": 2.1532846715328466e-05,
+      "loss": 0.001,
+      "step": 257
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.024688445031642914,
+      "learning_rate": 2.135036496350365e-05,
+      "loss": 0.0001,
+      "step": 258
+    },
+    {
+      "epoch": 1.3813333333333333,
+      "grad_norm": 0.002812020480632782,
+      "learning_rate": 2.1167883211678834e-05,
+      "loss": 0.0,
+      "step": 259
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 0.004634685814380646,
+      "learning_rate": 2.0985401459854014e-05,
+      "loss": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.03992787003517151,
+      "learning_rate": 2.08029197080292e-05,
+      "loss": 0.0002,
+      "step": 261
+    },
+    {
+      "epoch": 1.3973333333333333,
+      "grad_norm": 0.15847791731357574,
+      "learning_rate": 2.062043795620438e-05,
+      "loss": 0.0015,
+      "step": 262
+    },
+    {
+      "epoch": 1.4026666666666667,
+      "grad_norm": 0.12543199956417084,
+      "learning_rate": 2.0437956204379563e-05,
+      "loss": 0.0002,
+      "step": 263
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.26353874802589417,
+      "learning_rate": 2.0255474452554747e-05,
+      "loss": 0.0021,
+      "step": 264
+    },
+    {
+      "epoch": 1.4133333333333333,
+      "grad_norm": 0.022708145901560783,
+      "learning_rate": 2.0072992700729927e-05,
+      "loss": 0.0001,
+      "step": 265
+    },
+    {
+      "epoch": 1.4186666666666667,
+      "grad_norm": 0.0019064097432419658,
+      "learning_rate": 1.989051094890511e-05,
+      "loss": 0.0,
+      "step": 266
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.001142073655501008,
+      "learning_rate": 1.9708029197080295e-05,
+      "loss": 0.0,
+      "step": 267
+    },
+    {
+      "epoch": 1.4293333333333333,
+      "grad_norm": 0.010808148421347141,
+      "learning_rate": 1.9525547445255476e-05,
+      "loss": 0.0,
+      "step": 268
+    },
+    {
+      "epoch": 1.4346666666666668,
+      "grad_norm": 0.02784203737974167,
+      "learning_rate": 1.934306569343066e-05,
+      "loss": 0.0018,
+      "step": 269
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.0008549782214686275,
+      "learning_rate": 1.916058394160584e-05,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.4453333333333334,
+      "grad_norm": 0.0007196843507699668,
+      "learning_rate": 1.897810218978102e-05,
+      "loss": 0.0,
+      "step": 271
+    },
+    {
+      "epoch": 1.4506666666666668,
+      "grad_norm": 0.00560079887509346,
+      "learning_rate": 1.8795620437956205e-05,
+      "loss": 0.0,
+      "step": 272
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.0021808978635817766,
+      "learning_rate": 1.861313868613139e-05,
+      "loss": 0.0,
+      "step": 273
+    },
+    {
+      "epoch": 1.4613333333333334,
+      "grad_norm": 0.01360512338578701,
+      "learning_rate": 1.843065693430657e-05,
+      "loss": 0.0004,
+      "step": 274
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.0007049081032164395,
+      "learning_rate": 1.8248175182481753e-05,
+      "loss": 0.0,
+      "step": 275
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.01267162710428238,
+      "learning_rate": 1.8065693430656934e-05,
+      "loss": 0.0,
+      "step": 276
+    },
+    {
+      "epoch": 1.4773333333333334,
+      "grad_norm": 0.014657084830105305,
+      "learning_rate": 1.7883211678832118e-05,
+      "loss": 0.0001,
+      "step": 277
+    },
+    {
+      "epoch": 1.4826666666666668,
+      "grad_norm": 0.04004383459687233,
+      "learning_rate": 1.7700729927007302e-05,
+      "loss": 0.0001,
+      "step": 278
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.017648771405220032,
+      "learning_rate": 1.7518248175182482e-05,
+      "loss": 0.0001,
+      "step": 279
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 0.01729322038590908,
+      "learning_rate": 1.7335766423357666e-05,
+      "loss": 0.0005,
+      "step": 280
+    },
+    {
+      "epoch": 1.4986666666666666,
+      "grad_norm": 0.004418115131556988,
+      "learning_rate": 1.715328467153285e-05,
+      "loss": 0.0,
+      "step": 281
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.00042153280810453,
+      "learning_rate": 1.6970802919708028e-05,
+      "loss": 0.0,
+      "step": 282
+    },
+    {
+      "epoch": 1.5093333333333332,
+      "grad_norm": 0.0053863199427723885,
+      "learning_rate": 1.678832116788321e-05,
+      "loss": 0.0,
+      "step": 283
+    },
+    {
+      "epoch": 1.5146666666666668,
+      "grad_norm": 0.14487409591674805,
+      "learning_rate": 1.6605839416058395e-05,
+      "loss": 0.0002,
+      "step": 284
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.04025112837553024,
+      "learning_rate": 1.6423357664233576e-05,
+      "loss": 0.0002,
+      "step": 285
+    },
+    {
+      "epoch": 1.5253333333333332,
+      "grad_norm": 0.018686264753341675,
+      "learning_rate": 1.624087591240876e-05,
+      "loss": 0.0,
+      "step": 286
+    },
+    {
+      "epoch": 1.5306666666666666,
+      "grad_norm": 0.01479147095233202,
+      "learning_rate": 1.605839416058394e-05,
+      "loss": 0.0007,
+      "step": 287
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.06299349665641785,
+      "learning_rate": 1.5875912408759125e-05,
+      "loss": 0.0007,
+      "step": 288
+    },
+    {
+      "epoch": 1.5413333333333332,
+      "grad_norm": 0.009090033359825611,
+      "learning_rate": 1.569343065693431e-05,
+      "loss": 0.0,
+      "step": 289
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 0.0031799913849681616,
+      "learning_rate": 1.551094890510949e-05,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.016930807381868362,
+      "learning_rate": 1.5328467153284673e-05,
+      "loss": 0.0004,
+      "step": 291
+    },
+    {
+      "epoch": 1.5573333333333332,
+      "grad_norm": 0.0020872405730187893,
+      "learning_rate": 1.5145985401459855e-05,
+      "loss": 0.0,
+      "step": 292
+    },
+    {
+      "epoch": 1.5626666666666666,
+      "grad_norm": 0.02441079169511795,
+      "learning_rate": 1.496350364963504e-05,
+      "loss": 0.0,
+      "step": 293
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.009169725701212883,
+      "learning_rate": 1.4781021897810221e-05,
+      "loss": 0.0,
+      "step": 294
+    },
+    {
+      "epoch": 1.5733333333333333,
+      "grad_norm": 0.002519815694540739,
+      "learning_rate": 1.45985401459854e-05,
+      "loss": 0.0,
+      "step": 295
+    },
+    {
+      "epoch": 1.5786666666666667,
+      "grad_norm": 0.01676744595170021,
+      "learning_rate": 1.4416058394160584e-05,
+      "loss": 0.0,
+      "step": 296
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.0009162573842331767,
+      "learning_rate": 1.4233576642335767e-05,
+      "loss": 0.0,
+      "step": 297
+    },
+    {
+      "epoch": 1.5893333333333333,
+      "grad_norm": 0.2286107838153839,
+      "learning_rate": 1.4051094890510949e-05,
+      "loss": 0.0007,
+      "step": 298
+    },
+    {
+      "epoch": 1.5946666666666667,
+      "grad_norm": 0.017723295837640762,
+      "learning_rate": 1.3868613138686131e-05,
+      "loss": 0.0005,
+      "step": 299
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.0007409326499328017,
+      "learning_rate": 1.3686131386861315e-05,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.6053333333333333,
+      "grad_norm": 0.09116298705339432,
+      "learning_rate": 1.3503649635036497e-05,
+      "loss": 0.0006,
+      "step": 301
+    },
+    {
+      "epoch": 1.6106666666666667,
+      "grad_norm": 0.010178130120038986,
+      "learning_rate": 1.332116788321168e-05,
+      "loss": 0.0001,
+      "step": 302
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.01456406433135271,
+      "learning_rate": 1.3138686131386862e-05,
+      "loss": 0.0,
+      "step": 303
+    },
+    {
+      "epoch": 1.6213333333333333,
+      "grad_norm": 0.0030016032978892326,
+      "learning_rate": 1.2956204379562046e-05,
+      "loss": 0.0,
+      "step": 304
+    },
+    {
+      "epoch": 1.6266666666666667,
+      "grad_norm": 0.15502622723579407,
+      "learning_rate": 1.2773722627737228e-05,
+      "loss": 0.0009,
+      "step": 305
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.004204445984214544,
+      "learning_rate": 1.259124087591241e-05,
+      "loss": 0.0,
+      "step": 306
+    },
+    {
+      "epoch": 1.6373333333333333,
+      "grad_norm": 0.0014404612593352795,
+      "learning_rate": 1.2408759124087593e-05,
+      "loss": 0.0,
+      "step": 307
+    },
+    {
+      "epoch": 1.6426666666666667,
+      "grad_norm": 0.0011513563804328442,
+      "learning_rate": 1.2226277372262775e-05,
+      "loss": 0.0,
+      "step": 308
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.027202218770980835,
+      "learning_rate": 1.2043795620437957e-05,
+      "loss": 0.0015,
+      "step": 309
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 0.01641668751835823,
+      "learning_rate": 1.186131386861314e-05,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 1.6586666666666665,
+      "grad_norm": 0.02343578264117241,
+      "learning_rate": 1.1678832116788322e-05,
+      "loss": 0.0,
+      "step": 311
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.01905711553990841,
+      "learning_rate": 1.1496350364963504e-05,
+      "loss": 0.0006,
+      "step": 312
+    },
+    {
+      "epoch": 1.6693333333333333,
+      "grad_norm": 0.010036816820502281,
+      "learning_rate": 1.1313868613138686e-05,
+      "loss": 0.0,
+      "step": 313
+    },
+    {
+      "epoch": 1.6746666666666665,
+      "grad_norm": 0.0003811994392890483,
+      "learning_rate": 1.113138686131387e-05,
+      "loss": 0.0,
+      "step": 314
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.005581065081059933,
+      "learning_rate": 1.0948905109489052e-05,
+      "loss": 0.0,
+      "step": 315
+    },
+    {
+      "epoch": 1.6853333333333333,
+      "grad_norm": 0.00306635070592165,
+      "learning_rate": 1.0766423357664233e-05,
+      "loss": 0.0,
+      "step": 316
+    },
+    {
+      "epoch": 1.6906666666666665,
+      "grad_norm": 0.00040708977030590177,
+      "learning_rate": 1.0583941605839417e-05,
+      "loss": 0.0,
+      "step": 317
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.01735386997461319,
+      "learning_rate": 1.04014598540146e-05,
+      "loss": 0.0001,
+      "step": 318
+    },
+    {
+      "epoch": 1.7013333333333334,
+      "grad_norm": 0.01934914104640484,
+      "learning_rate": 1.0218978102189781e-05,
+      "loss": 0.0,
+      "step": 319
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 0.0042274221777915955,
+      "learning_rate": 1.0036496350364964e-05,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.025710001587867737,
+      "learning_rate": 9.854014598540148e-06,
+      "loss": 0.0004,
+      "step": 321
+    },
+    {
+      "epoch": 1.7173333333333334,
+      "grad_norm": 0.0074539752677083015,
+      "learning_rate": 9.67153284671533e-06,
+      "loss": 0.0,
+      "step": 322
+    },
+    {
+      "epoch": 1.7226666666666666,
+      "grad_norm": 0.03569052368402481,
+      "learning_rate": 9.48905109489051e-06,
+      "loss": 0.0002,
+      "step": 323
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.028168275952339172,
+      "learning_rate": 9.306569343065694e-06,
+      "loss": 0.001,
+      "step": 324
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.04901032894849777,
+      "learning_rate": 9.124087591240877e-06,
+      "loss": 0.0003,
+      "step": 325
+    },
+    {
+      "epoch": 1.7386666666666666,
+      "grad_norm": 0.027970319613814354,
+      "learning_rate": 8.941605839416059e-06,
+      "loss": 0.0,
+      "step": 326
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.0004777342837769538,
+      "learning_rate": 8.759124087591241e-06,
+      "loss": 0.0,
+      "step": 327
+    },
+    {
+      "epoch": 1.7493333333333334,
+      "grad_norm": 0.0010001097107306123,
+      "learning_rate": 8.576642335766425e-06,
+      "loss": 0.0,
+      "step": 328
+    },
+    {
+      "epoch": 1.7546666666666666,
+      "grad_norm": 0.01761973462998867,
+      "learning_rate": 8.394160583941606e-06,
+      "loss": 0.0,
+      "step": 329
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.0010678698308765888,
+      "learning_rate": 8.211678832116788e-06,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 1.7653333333333334,
+      "grad_norm": 0.0009921437595039606,
+      "learning_rate": 8.02919708029197e-06,
+      "loss": 0.0,
+      "step": 331
+    },
+    {
+      "epoch": 1.7706666666666666,
+      "grad_norm": 0.05064305290579796,
+      "learning_rate": 7.846715328467154e-06,
+      "loss": 0.0005,
+      "step": 332
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.006894893478602171,
+      "learning_rate": 7.664233576642336e-06,
+      "loss": 0.0,
+      "step": 333
+    },
+    {
+      "epoch": 1.7813333333333334,
+      "grad_norm": 0.016337955370545387,
+      "learning_rate": 7.48175182481752e-06,
+      "loss": 0.0001,
+      "step": 334
+    },
+    {
+      "epoch": 1.7866666666666666,
+      "grad_norm": 0.010748608037829399,
+      "learning_rate": 7.2992700729927e-06,
+      "loss": 0.0,
+      "step": 335
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.0008429877343587577,
+      "learning_rate": 7.116788321167883e-06,
+      "loss": 0.0,
+      "step": 336
+    },
+    {
+      "epoch": 1.7973333333333334,
+      "grad_norm": 0.0003417197149246931,
+      "learning_rate": 6.9343065693430655e-06,
+      "loss": 0.0,
+      "step": 337
+    },
+    {
+      "epoch": 1.8026666666666666,
+      "grad_norm": 0.00042090704664587975,
+      "learning_rate": 6.751824817518249e-06,
+      "loss": 0.0,
+      "step": 338
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.0006689835572615266,
+      "learning_rate": 6.569343065693431e-06,
+      "loss": 0.0,
+      "step": 339
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 0.006064795423299074,
+      "learning_rate": 6.386861313868614e-06,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 1.8186666666666667,
+      "grad_norm": 0.00045723479706794024,
+      "learning_rate": 6.204379562043796e-06,
+      "loss": 0.0,
+      "step": 341
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.02724609151482582,
+      "learning_rate": 6.0218978102189786e-06,
+      "loss": 0.0003,
+      "step": 342
+    },
+    {
+      "epoch": 1.8293333333333335,
+      "grad_norm": 0.0006413186783902347,
+      "learning_rate": 5.839416058394161e-06,
+      "loss": 0.0,
+      "step": 343
+    },
+    {
+      "epoch": 1.8346666666666667,
+      "grad_norm": 0.07486186176538467,
+      "learning_rate": 5.656934306569343e-06,
+      "loss": 0.0002,
+      "step": 344
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.00033135409466922283,
+      "learning_rate": 5.474452554744526e-06,
+      "loss": 0.0,
+      "step": 345
+    },
+    {
+      "epoch": 1.8453333333333335,
+      "grad_norm": 0.1818641573190689,
+      "learning_rate": 5.2919708029197084e-06,
+      "loss": 0.0018,
+      "step": 346
+    },
+    {
+      "epoch": 1.8506666666666667,
+      "grad_norm": 0.00031088246032595634,
+      "learning_rate": 5.109489051094891e-06,
+      "loss": 0.0,
+      "step": 347
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.0008156157564371824,
+      "learning_rate": 4.927007299270074e-06,
+      "loss": 0.0,
+      "step": 348
+    },
+    {
+      "epoch": 1.8613333333333333,
+      "grad_norm": 0.02040432207286358,
+      "learning_rate": 4.744525547445255e-06,
+      "loss": 0.0001,
+      "step": 349
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.01873834989964962,
+      "learning_rate": 4.562043795620438e-06,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.06707525253295898,
+      "learning_rate": 4.379562043795621e-06,
+      "loss": 0.0011,
+      "step": 351
+    },
+    {
+      "epoch": 1.8773333333333333,
+      "grad_norm": 0.0007396309520117939,
+      "learning_rate": 4.197080291970803e-06,
+      "loss": 0.0,
+      "step": 352
+    },
+    {
+      "epoch": 1.8826666666666667,
+      "grad_norm": 0.0020301148761063814,
+      "learning_rate": 4.014598540145985e-06,
+      "loss": 0.0,
+      "step": 353
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.0011450459714978933,
+      "learning_rate": 3.832116788321168e-06,
+      "loss": 0.0,
+      "step": 354
+    },
+    {
+      "epoch": 1.8933333333333333,
+      "grad_norm": 0.0017821722431108356,
+      "learning_rate": 3.64963503649635e-06,
+      "loss": 0.0,
+      "step": 355
+    },
+    {
+      "epoch": 1.8986666666666667,
+      "grad_norm": 0.00048125500325113535,
+      "learning_rate": 3.4671532846715328e-06,
+      "loss": 0.0,
+      "step": 356
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.002369426190853119,
+      "learning_rate": 3.2846715328467155e-06,
+      "loss": 0.0,
+      "step": 357
+    },
+    {
+      "epoch": 1.9093333333333333,
+      "grad_norm": 0.0031667123548686504,
+      "learning_rate": 3.102189781021898e-06,
+      "loss": 0.0,
+      "step": 358
+    },
+    {
+      "epoch": 1.9146666666666667,
+      "grad_norm": 0.001041563693434,
+      "learning_rate": 2.9197080291970804e-06,
+      "loss": 0.0,
+      "step": 359
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.008618980646133423,
+      "learning_rate": 2.737226277372263e-06,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 1.9253333333333333,
+      "grad_norm": 0.01731414534151554,
+      "learning_rate": 2.5547445255474454e-06,
+      "loss": 0.0,
+      "step": 361
+    },
+    {
+      "epoch": 1.9306666666666668,
+      "grad_norm": 0.0012004224117845297,
+      "learning_rate": 2.3722627737226276e-06,
+      "loss": 0.0,
+      "step": 362
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.0008345829555764794,
+      "learning_rate": 2.1897810218978103e-06,
+      "loss": 0.0,
+      "step": 363
+    },
+    {
+      "epoch": 1.9413333333333334,
+      "grad_norm": 0.02537546120584011,
+      "learning_rate": 2.0072992700729926e-06,
+      "loss": 0.0001,
+      "step": 364
+    },
+    {
+      "epoch": 1.9466666666666668,
+      "grad_norm": 0.001495170989073813,
+      "learning_rate": 1.824817518248175e-06,
+      "loss": 0.0,
+      "step": 365
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.00026738637825474143,
+      "learning_rate": 1.6423357664233577e-06,
+      "loss": 0.0,
+      "step": 366
+    },
+    {
+      "epoch": 1.9573333333333334,
+      "grad_norm": 0.0014998159604147077,
+      "learning_rate": 1.4598540145985402e-06,
+      "loss": 0.0,
+      "step": 367
+    },
+    {
+      "epoch": 1.9626666666666668,
+      "grad_norm": 0.03254641965031624,
+      "learning_rate": 1.2773722627737227e-06,
+      "loss": 0.0009,
+      "step": 368
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 0.028693141415715218,
+      "learning_rate": 1.0948905109489052e-06,
+      "loss": 0.0017,
+      "step": 369
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 0.008891824632883072,
+      "learning_rate": 9.124087591240875e-07,
+      "loss": 0.0001,
+      "step": 370
+    },
+    {
+      "epoch": 1.9786666666666668,
+      "grad_norm": 0.00040042444015853107,
+      "learning_rate": 7.299270072992701e-07,
+      "loss": 0.0,
+      "step": 371
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.0017654062248766422,
+      "learning_rate": 5.474452554744526e-07,
+      "loss": 0.0,
+      "step": 372
+    },
+    {
+      "epoch": 1.9893333333333332,
+      "grad_norm": 0.04212335869669914,
+      "learning_rate": 3.6496350364963505e-07,
+      "loss": 0.0001,
+      "step": 373
+    },
+    {
+      "epoch": 1.9946666666666668,
+      "grad_norm": 0.009376861155033112,
+      "learning_rate": 1.8248175182481753e-07,
+      "loss": 0.0,
+      "step": 374
+    },
+    {
+      "epoch": 1.9946666666666668,
+      "step": 374,
+      "total_flos": 22488518631424.0,
+      "train_loss": 0.006301866256624265,
+      "train_runtime": 57978.5955,
+      "train_samples_per_second": 0.207,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 374,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 22488518631424.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

0523-7B/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c73b3f27fcc28075e9a0412f821ee7be8461bb7c68056308ea88affc8d0ded
+size 7736