Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,26 @@
+{
+  "</think>": 151666,
+  "</tool_call>": 151658,
+  "<think>": 151665,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "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_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

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

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75bc7b7a5dfbf0cd89ec50098108408fd2e0199401196b5a840bb7d8ae88ba6a
+size 9979257128

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7147b98838e4949f98aef5111d424e51cd811b301780d6562dd62ca4a1253d
+size 5252014776

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,223 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2427 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 3643,
+  "global_step": 10929,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 54.208412170410156,
+      "learning_rate": 4.574565416285453e-09,
+      "loss": 3.1538,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 67.83907318115234,
+      "learning_rate": 1.463860933211345e-07,
+      "loss": 3.1254,
+      "step": 32
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 51.09539794921875,
+      "learning_rate": 2.92772186642269e-07,
+      "loss": 2.9875,
+      "step": 64
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 28.961633682250977,
+      "learning_rate": 4.391582799634035e-07,
+      "loss": 1.9756,
+      "step": 96
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 43.88395309448242,
+      "learning_rate": 5.85544373284538e-07,
+      "loss": 1.2465,
+      "step": 128
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.8834291696548462,
+      "learning_rate": 7.319304666056726e-07,
+      "loss": 0.543,
+      "step": 160
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.2911040782928467,
+      "learning_rate": 8.78316559926807e-07,
+      "loss": 0.4762,
+      "step": 192
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.6260019540786743,
+      "learning_rate": 1.0247026532479415e-06,
+      "loss": 0.465,
+      "step": 224
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.6339985132217407,
+      "learning_rate": 1.171088746569076e-06,
+      "loss": 0.4286,
+      "step": 256
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.2695084810256958,
+      "learning_rate": 1.3174748398902104e-06,
+      "loss": 0.4318,
+      "step": 288
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.2813961505889893,
+      "learning_rate": 1.4638609332113452e-06,
+      "loss": 0.4261,
+      "step": 320
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.778540015220642,
+      "learning_rate": 1.6102470265324796e-06,
+      "loss": 0.4075,
+      "step": 352
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.3420789241790771,
+      "learning_rate": 1.756633119853614e-06,
+      "loss": 0.4063,
+      "step": 384
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.3378902673721313,
+      "learning_rate": 1.9030192131747486e-06,
+      "loss": 0.4029,
+      "step": 416
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.274935245513916,
+      "learning_rate": 2.049405306495883e-06,
+      "loss": 0.39,
+      "step": 448
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.3001614809036255,
+      "learning_rate": 2.1957913998170175e-06,
+      "loss": 0.3863,
+      "step": 480
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.2205229997634888,
+      "learning_rate": 2.342177493138152e-06,
+      "loss": 0.3662,
+      "step": 512
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.496649980545044,
+      "learning_rate": 2.4885635864592867e-06,
+      "loss": 0.382,
+      "step": 544
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.3435134887695312,
+      "learning_rate": 2.634949679780421e-06,
+      "loss": 0.3557,
+      "step": 576
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.3864662647247314,
+      "learning_rate": 2.7813357731015555e-06,
+      "loss": 0.3656,
+      "step": 608
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.2134894132614136,
+      "learning_rate": 2.9277218664226905e-06,
+      "loss": 0.3573,
+      "step": 640
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.184622049331665,
+      "learning_rate": 3.0741079597438246e-06,
+      "loss": 0.353,
+      "step": 672
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.2790993452072144,
+      "learning_rate": 3.2204940530649592e-06,
+      "loss": 0.3479,
+      "step": 704
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.2058337926864624,
+      "learning_rate": 3.3668801463860934e-06,
+      "loss": 0.352,
+      "step": 736
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.4847257137298584,
+      "learning_rate": 3.513266239707228e-06,
+      "loss": 0.3603,
+      "step": 768
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.2458118200302124,
+      "learning_rate": 3.659652333028363e-06,
+      "loss": 0.3451,
+      "step": 800
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.1888768672943115,
+      "learning_rate": 3.806038426349497e-06,
+      "loss": 0.3476,
+      "step": 832
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.2280688285827637,
+      "learning_rate": 3.952424519670632e-06,
+      "loss": 0.3439,
+      "step": 864
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.225164532661438,
+      "learning_rate": 4.098810612991766e-06,
+      "loss": 0.3382,
+      "step": 896
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.3854628801345825,
+      "learning_rate": 4.245196706312901e-06,
+      "loss": 0.334,
+      "step": 928
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.2386870384216309,
+      "learning_rate": 4.391582799634035e-06,
+      "loss": 0.3358,
+      "step": 960
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.3773902654647827,
+      "learning_rate": 4.537968892955169e-06,
+      "loss": 0.3397,
+      "step": 992
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.2690755128860474,
+      "learning_rate": 4.684354986276304e-06,
+      "loss": 0.3346,
+      "step": 1024
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.195071816444397,
+      "learning_rate": 4.830741079597438e-06,
+      "loss": 0.3362,
+      "step": 1056
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.5337246656417847,
+      "learning_rate": 4.977127172918573e-06,
+      "loss": 0.3385,
+      "step": 1088
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.2219808101654053,
+      "learning_rate": 4.999907039691762e-06,
+      "loss": 0.3363,
+      "step": 1120
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4543613195419312,
+      "learning_rate": 4.999556121725076e-06,
+      "loss": 0.3399,
+      "step": 1152
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.1301358938217163,
+      "learning_rate": 4.998944094799263e-06,
+      "loss": 0.336,
+      "step": 1184
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.1877110004425049,
+      "learning_rate": 4.998071022847959e-06,
+      "loss": 0.327,
+      "step": 1216
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.3346518278121948,
+      "learning_rate": 4.996936997074121e-06,
+      "loss": 0.3254,
+      "step": 1248
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.328561544418335,
+      "learning_rate": 4.995542135940498e-06,
+      "loss": 0.3267,
+      "step": 1280
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.1962031126022339,
+      "learning_rate": 4.9938865851572556e-06,
+      "loss": 0.3295,
+      "step": 1312
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.367148518562317,
+      "learning_rate": 4.9919705176667576e-06,
+      "loss": 0.3346,
+      "step": 1344
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.2407596111297607,
+      "learning_rate": 4.989794133625496e-06,
+      "loss": 0.3202,
+      "step": 1376
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.9892008304595947,
+      "learning_rate": 4.987357660383188e-06,
+      "loss": 0.3202,
+      "step": 1408
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1566520929336548,
+      "learning_rate": 4.98466135245902e-06,
+      "loss": 0.3278,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2611408233642578,
+      "learning_rate": 4.981705491515063e-06,
+      "loss": 0.3145,
+      "step": 1472
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.3457179069519043,
+      "learning_rate": 4.97849038632685e-06,
+      "loss": 0.329,
+      "step": 1504
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.1328198909759521,
+      "learning_rate": 4.97501637275112e-06,
+      "loss": 0.3254,
+      "step": 1536
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.3574585914611816,
+      "learning_rate": 4.971283813690736e-06,
+      "loss": 0.3233,
+      "step": 1568
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.1256043910980225,
+      "learning_rate": 4.967293099056771e-06,
+      "loss": 0.3208,
+      "step": 1600
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.249360203742981,
+      "learning_rate": 4.96304464572778e-06,
+      "loss": 0.3201,
+      "step": 1632
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.2611795663833618,
+      "learning_rate": 4.958538897506251e-06,
+      "loss": 0.3239,
+      "step": 1664
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.073809027671814,
+      "learning_rate": 4.953776325072246e-06,
+      "loss": 0.3162,
+      "step": 1696
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.1197922229766846,
+      "learning_rate": 4.94875742593423e-06,
+      "loss": 0.3205,
+      "step": 1728
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.158610463142395,
+      "learning_rate": 4.943482724377102e-06,
+      "loss": 0.3164,
+      "step": 1760
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.4227887392044067,
+      "learning_rate": 4.937952771407429e-06,
+      "loss": 0.3164,
+      "step": 1792
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.0640499591827393,
+      "learning_rate": 4.93216814469588e-06,
+      "loss": 0.3143,
+      "step": 1824
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.2627692222595215,
+      "learning_rate": 4.926129448516892e-06,
+      "loss": 0.3332,
+      "step": 1856
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.29629647731781,
+      "learning_rate": 4.9198373136855334e-06,
+      "loss": 0.3083,
+      "step": 1888
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.4851006269454956,
+      "learning_rate": 4.91329239749162e-06,
+      "loss": 0.3246,
+      "step": 1920
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.3672281503677368,
+      "learning_rate": 4.906495383631043e-06,
+      "loss": 0.3152,
+      "step": 1952
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.2322040796279907,
+      "learning_rate": 4.899446982134356e-06,
+      "loss": 0.3222,
+      "step": 1984
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.388634443283081,
+      "learning_rate": 4.892147929292599e-06,
+      "loss": 0.3237,
+      "step": 2016
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.1521799564361572,
+      "learning_rate": 4.884598987580387e-06,
+      "loss": 0.3215,
+      "step": 2048
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.4414801597595215,
+      "learning_rate": 4.8768009455762585e-06,
+      "loss": 0.3171,
+      "step": 2080
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.2265347242355347,
+      "learning_rate": 4.868754617880298e-06,
+      "loss": 0.3006,
+      "step": 2112
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.2373523712158203,
+      "learning_rate": 4.860460845029046e-06,
+      "loss": 0.2999,
+      "step": 2144
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2620317935943604,
+      "learning_rate": 4.851920493407686e-06,
+      "loss": 0.3088,
+      "step": 2176
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.456446886062622,
+      "learning_rate": 4.84313445515955e-06,
+      "loss": 0.3211,
+      "step": 2208
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.083969235420227,
+      "learning_rate": 4.8341036480929175e-06,
+      "loss": 0.3038,
+      "step": 2240
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.108154296875,
+      "learning_rate": 4.824829015585137e-06,
+      "loss": 0.3171,
+      "step": 2272
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.2438993453979492,
+      "learning_rate": 4.815311526484088e-06,
+      "loss": 0.3136,
+      "step": 2304
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.2784481048583984,
+      "learning_rate": 4.805552175006961e-06,
+      "loss": 0.3285,
+      "step": 2336
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.3175300359725952,
+      "learning_rate": 4.795551980636412e-06,
+      "loss": 0.3037,
+      "step": 2368
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.2200733423233032,
+      "learning_rate": 4.7853119880140536e-06,
+      "loss": 0.3077,
+      "step": 2400
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.4026285409927368,
+      "learning_rate": 4.774833266831338e-06,
+      "loss": 0.3057,
+      "step": 2432
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.2519586086273193,
+      "learning_rate": 4.7641169117178095e-06,
+      "loss": 0.3196,
+      "step": 2464
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.1315079927444458,
+      "learning_rate": 4.753164042126761e-06,
+      "loss": 0.3113,
+      "step": 2496
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.4601058959960938,
+      "learning_rate": 4.741975802218291e-06,
+      "loss": 0.3045,
+      "step": 2528
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.3377221822738647,
+      "learning_rate": 4.730553360739783e-06,
+      "loss": 0.317,
+      "step": 2560
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.2052831649780273,
+      "learning_rate": 4.718897910903815e-06,
+      "loss": 0.3074,
+      "step": 2592
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.297559380531311,
+      "learning_rate": 4.707010670263515e-06,
+      "loss": 0.3114,
+      "step": 2624
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.464591145515442,
+      "learning_rate": 4.694892880585374e-06,
+      "loss": 0.3093,
+      "step": 2656
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.3536854982376099,
+      "learning_rate": 4.682545807719522e-06,
+      "loss": 0.3142,
+      "step": 2688
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.4099351167678833,
+      "learning_rate": 4.669970741467506e-06,
+      "loss": 0.3156,
+      "step": 2720
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.6140319108963013,
+      "learning_rate": 4.657168995447543e-06,
+      "loss": 0.3139,
+      "step": 2752
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.1057366132736206,
+      "learning_rate": 4.644141906957304e-06,
+      "loss": 0.3055,
+      "step": 2784
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.3173573017120361,
+      "learning_rate": 4.630890836834214e-06,
+      "loss": 0.3066,
+      "step": 2816
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.25442636013031,
+      "learning_rate": 4.617417169313295e-06,
+      "loss": 0.2998,
+      "step": 2848
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.1627905368804932,
+      "learning_rate": 4.603722311882572e-06,
+      "loss": 0.3068,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.3471896648406982,
+      "learning_rate": 4.589807695136034e-06,
+      "loss": 0.2982,
+      "step": 2912
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.3181612491607666,
+      "learning_rate": 4.575674772624199e-06,
+      "loss": 0.3142,
+      "step": 2944
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.4064816236495972,
+      "learning_rate": 4.561325020702272e-06,
+      "loss": 0.3104,
+      "step": 2976
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.1795717477798462,
+      "learning_rate": 4.546759938375918e-06,
+      "loss": 0.3125,
+      "step": 3008
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.2061402797698975,
+      "learning_rate": 4.5319810471446744e-06,
+      "loss": 0.3001,
+      "step": 3040
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.42404043674469,
+      "learning_rate": 4.516989890843015e-06,
+      "loss": 0.3097,
+      "step": 3072
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.16380774974823,
+      "learning_rate": 4.501788035479075e-06,
+      "loss": 0.3047,
+      "step": 3104
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.2620742321014404,
+      "learning_rate": 4.486377069071057e-06,
+      "loss": 0.305,
+      "step": 3136
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.0642744302749634,
+      "learning_rate": 4.470758601481358e-06,
+      "loss": 0.2994,
+      "step": 3168
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.4131340980529785,
+      "learning_rate": 4.454934264248385e-06,
+      "loss": 0.3015,
+      "step": 3200
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.1669200658798218,
+      "learning_rate": 4.438905710416125e-06,
+      "loss": 0.2979,
+      "step": 3232
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.2006587982177734,
+      "learning_rate": 4.422674614361472e-06,
+      "loss": 0.3036,
+      "step": 3264
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.4893945455551147,
+      "learning_rate": 4.406242671619307e-06,
+      "loss": 0.2987,
+      "step": 3296
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.23745858669281,
+      "learning_rate": 4.389611598705387e-06,
+      "loss": 0.3043,
+      "step": 3328
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.135177731513977,
+      "learning_rate": 4.3727831329370294e-06,
+      "loss": 0.3008,
+      "step": 3360
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.4660807847976685,
+      "learning_rate": 4.355759032251631e-06,
+      "loss": 0.3163,
+      "step": 3392
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.2524827718734741,
+      "learning_rate": 4.338541075023028e-06,
+      "loss": 0.3063,
+      "step": 3424
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.432442545890808,
+      "learning_rate": 4.321131059875725e-06,
+      "loss": 0.297,
+      "step": 3456
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9542037844657898,
+      "learning_rate": 4.303530805497005e-06,
+      "loss": 0.2885,
+      "step": 3488
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.2449514865875244,
+      "learning_rate": 4.285742150446949e-06,
+      "loss": 0.3014,
+      "step": 3520
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.1579153537750244,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.2985,
+      "step": 3552
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.067274808883667,
+      "learning_rate": 4.2496070907827025e-06,
+      "loss": 0.2938,
+      "step": 3584
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.2658989429473877,
+      "learning_rate": 4.231264460913851e-06,
+      "loss": 0.2904,
+      "step": 3616
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.077365517616272,
+      "learning_rate": 4.2127409794700194e-06,
+      "loss": 0.2872,
+      "step": 3648
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 1.3447195291519165,
+      "learning_rate": 4.194038581453555e-06,
+      "loss": 0.2591,
+      "step": 3680
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 1.120044469833374,
+      "learning_rate": 4.175159220556808e-06,
+      "loss": 0.2661,
+      "step": 3712
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 1.1003544330596924,
+      "learning_rate": 4.156104868958052e-06,
+      "loss": 0.2571,
+      "step": 3744
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.2366827726364136,
+      "learning_rate": 4.1368775171154606e-06,
+      "loss": 0.2735,
+      "step": 3776
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 1.2097110748291016,
+      "learning_rate": 4.11747917355918e-06,
+      "loss": 0.266,
+      "step": 3808
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 1.1557356119155884,
+      "learning_rate": 4.0979118646815185e-06,
+      "loss": 0.2604,
+      "step": 3840
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 1.56402587890625,
+      "learning_rate": 4.07817763452526e-06,
+      "loss": 0.3354,
+      "step": 3872
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 1.1319921016693115,
+      "learning_rate": 4.0582785445701386e-06,
+      "loss": 0.2839,
+      "step": 3904
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.202816128730774,
+      "learning_rate": 4.0382166735175e-06,
+      "loss": 0.2712,
+      "step": 3936
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 1.2420419454574585,
+      "learning_rate": 4.017994117073145e-06,
+      "loss": 0.2654,
+      "step": 3968
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.0900554656982422,
+      "learning_rate": 3.9976129877284156e-06,
+      "loss": 0.2768,
+      "step": 4000
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 1.3165624141693115,
+      "learning_rate": 3.977075414539516e-06,
+      "loss": 0.2667,
+      "step": 4032
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.177911639213562,
+      "learning_rate": 3.956383542905108e-06,
+      "loss": 0.2637,
+      "step": 4064
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.0537302494049072,
+      "learning_rate": 3.935539534342197e-06,
+      "loss": 0.2677,
+      "step": 4096
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 1.1273211240768433,
+      "learning_rate": 3.914545566260338e-06,
+      "loss": 0.2513,
+      "step": 4128
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 1.256974697113037,
+      "learning_rate": 3.893403831734176e-06,
+      "loss": 0.2668,
+      "step": 4160
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 1.1725802421569824,
+      "learning_rate": 3.872116539274351e-06,
+      "loss": 0.2695,
+      "step": 4192
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.2964409589767456,
+      "learning_rate": 3.850685912596801e-06,
+      "loss": 0.268,
+      "step": 4224
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 1.1493666172027588,
+      "learning_rate": 3.8291141903904546e-06,
+      "loss": 0.2691,
+      "step": 4256
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.0970759391784668,
+      "learning_rate": 3.807403626083386e-06,
+      "loss": 0.2656,
+      "step": 4288
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.9655824303627014,
+      "learning_rate": 3.7855564876074086e-06,
+      "loss": 0.2565,
+      "step": 4320
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.2320510149002075,
+      "learning_rate": 3.763575057161164e-06,
+      "loss": 0.2498,
+      "step": 4352
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.2656631469726562,
+      "learning_rate": 3.7414616309717213e-06,
+      "loss": 0.2518,
+      "step": 4384
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 1.15951406955719,
+      "learning_rate": 3.7192185190547025e-06,
+      "loss": 0.2682,
+      "step": 4416
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 1.0986238718032837,
+      "learning_rate": 3.6968480449729805e-06,
+      "loss": 0.2682,
+      "step": 4448
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 1.2103216648101807,
+      "learning_rate": 3.6743525455939514e-06,
+      "loss": 0.26,
+      "step": 4480
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.031505823135376,
+      "learning_rate": 3.6517343708454173e-06,
+      "loss": 0.2588,
+      "step": 4512
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.0480434894561768,
+      "learning_rate": 3.6289958834701146e-06,
+      "loss": 0.2494,
+      "step": 4544
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.0918818712234497,
+      "learning_rate": 3.606139458778889e-06,
+      "loss": 0.2533,
+      "step": 4576
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.2527130842208862,
+      "learning_rate": 3.5831674844025732e-06,
+      "loss": 0.2559,
+      "step": 4608
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.9362933039665222,
+      "learning_rate": 3.560082360042564e-06,
+      "loss": 0.2573,
+      "step": 4640
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.1024744510650635,
+      "learning_rate": 3.5368864972201477e-06,
+      "loss": 0.2607,
+      "step": 4672
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 1.0679678916931152,
+      "learning_rate": 3.5135823190245856e-06,
+      "loss": 0.2473,
+      "step": 4704
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 1.228959321975708,
+      "learning_rate": 3.4901722598599946e-06,
+      "loss": 0.261,
+      "step": 4736
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 1.0304726362228394,
+      "learning_rate": 3.466658765191043e-06,
+      "loss": 0.2578,
+      "step": 4768
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.0423589944839478,
+      "learning_rate": 3.4430442912874916e-06,
+      "loss": 0.2485,
+      "step": 4800
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 1.0579800605773926,
+      "learning_rate": 3.4193313049676073e-06,
+      "loss": 0.2454,
+      "step": 4832
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 1.258385181427002,
+      "learning_rate": 3.3955222833404755e-06,
+      "loss": 0.2553,
+      "step": 4864
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 1.1673798561096191,
+      "learning_rate": 3.3716197135472323e-06,
+      "loss": 0.2597,
+      "step": 4896
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 1.2642861604690552,
+      "learning_rate": 3.3476260925012573e-06,
+      "loss": 0.2552,
+      "step": 4928
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.0974534749984741,
+      "learning_rate": 3.323543926627334e-06,
+      "loss": 0.2648,
+      "step": 4960
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 1.0666210651397705,
+      "learning_rate": 3.299375731599831e-06,
+      "loss": 0.259,
+      "step": 4992
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.1400901079177856,
+      "learning_rate": 3.2751240320799037e-06,
+      "loss": 0.2657,
+      "step": 5024
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 1.1349825859069824,
+      "learning_rate": 3.250791361451766e-06,
+      "loss": 0.26,
+      "step": 5056
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.0231640338897705,
+      "learning_rate": 3.2263802615580452e-06,
+      "loss": 0.2559,
+      "step": 5088
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 1.1220964193344116,
+      "learning_rate": 3.201893282434257e-06,
+      "loss": 0.2598,
+      "step": 5120
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 1.2639639377593994,
+      "learning_rate": 3.1773329820424233e-06,
+      "loss": 0.2565,
+      "step": 5152
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.2557729482650757,
+      "learning_rate": 3.152701926003863e-06,
+      "loss": 0.2611,
+      "step": 5184
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.3128156661987305,
+      "learning_rate": 3.1280026873311777e-06,
+      "loss": 0.2502,
+      "step": 5216
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.1379268169403076,
+      "learning_rate": 3.103237846159476e-06,
+      "loss": 0.2603,
+      "step": 5248
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 1.0746465921401978,
+      "learning_rate": 3.078409989476841e-06,
+      "loss": 0.2455,
+      "step": 5280
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 1.0750409364700317,
+      "learning_rate": 3.053521710854091e-06,
+      "loss": 0.2684,
+      "step": 5312
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.1325640678405762,
+      "learning_rate": 3.028575610173848e-06,
+      "loss": 0.26,
+      "step": 5344
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.2413684129714966,
+      "learning_rate": 3.003574293358951e-06,
+      "loss": 0.2687,
+      "step": 5376
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.36347234249115,
+      "learning_rate": 2.978520372100234e-06,
+      "loss": 0.2584,
+      "step": 5408
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.0437661409378052,
+      "learning_rate": 2.953416463583701e-06,
+      "loss": 0.2552,
+      "step": 5440
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.105076789855957,
+      "learning_rate": 2.9282651902171336e-06,
+      "loss": 0.2567,
+      "step": 5472
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 1.4056578874588013,
+      "learning_rate": 2.9030691793561468e-06,
+      "loss": 0.2502,
+      "step": 5504
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.169480323791504,
+      "learning_rate": 2.8778310630297274e-06,
+      "loss": 0.2553,
+      "step": 5536
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.0875940322875977,
+      "learning_rate": 2.852553477665292e-06,
+      "loss": 0.262,
+      "step": 5568
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 1.156416893005371,
+      "learning_rate": 2.827239063813273e-06,
+      "loss": 0.2523,
+      "step": 5600
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 1.2862755060195923,
+      "learning_rate": 2.8018904658712897e-06,
+      "loss": 0.2549,
+      "step": 5632
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 1.145634412765503,
+      "learning_rate": 2.776510331807901e-06,
+      "loss": 0.2567,
+      "step": 5664
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.0567256212234497,
+      "learning_rate": 2.7511013128859976e-06,
+      "loss": 0.2543,
+      "step": 5696
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.1589100360870361,
+      "learning_rate": 2.725666063385843e-06,
+      "loss": 0.255,
+      "step": 5728
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 1.040733814239502,
+      "learning_rate": 2.7002072403278034e-06,
+      "loss": 0.2528,
+      "step": 5760
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 1.023245096206665,
+      "learning_rate": 2.67472750319479e-06,
+      "loss": 0.2573,
+      "step": 5792
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.1324783563613892,
+      "learning_rate": 2.649229513654443e-06,
+      "loss": 0.2681,
+      "step": 5824
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 1.2279173135757446,
+      "learning_rate": 2.6237159352810844e-06,
+      "loss": 0.2528,
+      "step": 5856
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 1.1544438600540161,
+      "learning_rate": 2.5981894332774825e-06,
+      "loss": 0.2608,
+      "step": 5888
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 1.2529610395431519,
+      "learning_rate": 2.5726526741964354e-06,
+      "loss": 0.2607,
+      "step": 5920
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 1.1091320514678955,
+      "learning_rate": 2.547108325662215e-06,
+      "loss": 0.2509,
+      "step": 5952
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 1.1773228645324707,
+      "learning_rate": 2.521559056091908e-06,
+      "loss": 0.2622,
+      "step": 5984
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.1259273290634155,
+      "learning_rate": 2.4960075344166575e-06,
+      "loss": 0.2524,
+      "step": 6016
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 1.1716557741165161,
+      "learning_rate": 2.4704564298028705e-06,
+      "loss": 0.2727,
+      "step": 6048
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.0267339944839478,
+      "learning_rate": 2.4449084113733846e-06,
+      "loss": 0.2592,
+      "step": 6080
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.102716088294983,
+      "learning_rate": 2.4193661479286477e-06,
+      "loss": 0.2557,
+      "step": 6112
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 1.2147122621536255,
+      "learning_rate": 2.393832307667933e-06,
+      "loss": 0.2496,
+      "step": 6144
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.1931440830230713,
+      "learning_rate": 2.3683095579106075e-06,
+      "loss": 0.2508,
+      "step": 6176
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.2680373191833496,
+      "learning_rate": 2.3428005648174996e-06,
+      "loss": 0.2576,
+      "step": 6208
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 1.3690531253814697,
+      "learning_rate": 2.317307993112389e-06,
+      "loss": 0.2577,
+      "step": 6240
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 1.1122456789016724,
+      "learning_rate": 2.291834505803642e-06,
+      "loss": 0.2626,
+      "step": 6272
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.3283777236938477,
+      "learning_rate": 2.2663827639060274e-06,
+      "loss": 0.258,
+      "step": 6304
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 1.2135595083236694,
+      "learning_rate": 2.2409554261627427e-06,
+      "loss": 0.2646,
+      "step": 6336
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.3239319324493408,
+      "learning_rate": 2.215555148767675e-06,
+      "loss": 0.254,
+      "step": 6368
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.1491477489471436,
+      "learning_rate": 2.19018458508793e-06,
+      "loss": 0.2587,
+      "step": 6400
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.1253843307495117,
+      "learning_rate": 2.164846385386656e-06,
+      "loss": 0.2568,
+      "step": 6432
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.9814224243164062,
+      "learning_rate": 2.1395431965461906e-06,
+      "loss": 0.2477,
+      "step": 6464
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 1.1660529375076294,
+      "learning_rate": 2.11427766179156e-06,
+      "loss": 0.2612,
+      "step": 6496
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 1.1438708305358887,
+      "learning_rate": 2.089052420414369e-06,
+      "loss": 0.2477,
+      "step": 6528
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.0001698732376099,
+      "learning_rate": 2.063870107497088e-06,
+      "loss": 0.2505,
+      "step": 6560
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 1.1928672790527344,
+      "learning_rate": 2.038733353637787e-06,
+      "loss": 0.2583,
+      "step": 6592
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.0851984024047852,
+      "learning_rate": 2.013644784675341e-06,
+      "loss": 0.2645,
+      "step": 6624
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 1.1390419006347656,
+      "learning_rate": 1.988607021415131e-06,
+      "loss": 0.2586,
+      "step": 6656
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.1419297456741333,
+      "learning_rate": 1.963622679355263e-06,
+      "loss": 0.2575,
+      "step": 6688
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.034332275390625,
+      "learning_rate": 1.93869436841335e-06,
+      "loss": 0.2456,
+      "step": 6720
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 1.109264850616455,
+      "learning_rate": 1.913824692653877e-06,
+      "loss": 0.2507,
+      "step": 6752
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 1.027176022529602,
+      "learning_rate": 1.8890162500161723e-06,
+      "loss": 0.2513,
+      "step": 6784
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 1.256115436553955,
+      "learning_rate": 1.8642716320430215e-06,
+      "loss": 0.2421,
+      "step": 6816
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 1.0514394044876099,
+      "learning_rate": 1.8395934236099494e-06,
+      "loss": 0.2586,
+      "step": 6848
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 1.103553295135498,
+      "learning_rate": 1.8149842026551987e-06,
+      "loss": 0.2539,
+      "step": 6880
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 1.0124670267105103,
+      "learning_rate": 1.7904465399104348e-06,
+      "loss": 0.2524,
+      "step": 6912
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 1.1316817998886108,
+      "learning_rate": 1.7659829986321984e-06,
+      "loss": 0.256,
+      "step": 6944
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 1.1976351737976074,
+      "learning_rate": 1.7415961343341436e-06,
+      "loss": 0.2513,
+      "step": 6976
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.2452280521392822,
+      "learning_rate": 1.717288494520084e-06,
+      "loss": 0.2527,
+      "step": 7008
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.9649327397346497,
+      "learning_rate": 1.6930626184178766e-06,
+      "loss": 0.2504,
+      "step": 7040
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 1.1695955991744995,
+      "learning_rate": 1.6689210367141647e-06,
+      "loss": 0.2533,
+      "step": 7072
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 1.2222055196762085,
+      "learning_rate": 1.6448662712900195e-06,
+      "loss": 0.2536,
+      "step": 7104
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 1.1454925537109375,
+      "learning_rate": 1.6209008349574984e-06,
+      "loss": 0.2498,
+      "step": 7136
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.0606447458267212,
+      "learning_rate": 1.597027231197153e-06,
+      "loss": 0.2585,
+      "step": 7168
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 1.2395633459091187,
+      "learning_rate": 1.5732479538965073e-06,
+      "loss": 0.2483,
+      "step": 7200
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 1.150342583656311,
+      "learning_rate": 1.5495654870895426e-06,
+      "loss": 0.2532,
+      "step": 7232
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 1.090488314628601,
+      "learning_rate": 1.5259823046972092e-06,
+      "loss": 0.2599,
+      "step": 7264
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.114548683166504,
+      "learning_rate": 1.5025008702689975e-06,
+      "loss": 0.2407,
+      "step": 7296
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 1.0678861141204834,
+      "learning_rate": 1.4791236367255876e-06,
+      "loss": 0.221,
+      "step": 7328
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 1.1404924392700195,
+      "learning_rate": 1.455853046102613e-06,
+      "loss": 0.2207,
+      "step": 7360
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 1.0074459314346313,
+      "learning_rate": 1.43269152929556e-06,
+      "loss": 0.2256,
+      "step": 7392
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 1.1483248472213745,
+      "learning_rate": 1.4096415058058332e-06,
+      "loss": 0.2191,
+      "step": 7424
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 1.0560438632965088,
+      "learning_rate": 1.3867053834880078e-06,
+      "loss": 0.2157,
+      "step": 7456
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 1.1846274137496948,
+      "learning_rate": 1.3638855582982967e-06,
+      "loss": 0.2245,
+      "step": 7488
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 1.1909441947937012,
+      "learning_rate": 1.3411844140442704e-06,
+      "loss": 0.2207,
+      "step": 7520
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 1.1410772800445557,
+      "learning_rate": 1.3186043221358353e-06,
+      "loss": 0.228,
+      "step": 7552
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.187180995941162,
+      "learning_rate": 1.29614764133751e-06,
+      "loss": 0.2196,
+      "step": 7584
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 1.1110252141952515,
+      "learning_rate": 1.2738167175220278e-06,
+      "loss": 0.2192,
+      "step": 7616
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 1.005050539970398,
+      "learning_rate": 1.251613883425276e-06,
+      "loss": 0.22,
+      "step": 7648
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 1.0139673948287964,
+      "learning_rate": 1.2295414584026239e-06,
+      "loss": 0.2117,
+      "step": 7680
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.9602714776992798,
+      "learning_rate": 1.2076017481866228e-06,
+      "loss": 0.2198,
+      "step": 7712
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 1.0056389570236206,
+      "learning_rate": 1.1857970446461587e-06,
+      "loss": 0.2182,
+      "step": 7744
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 1.0241825580596924,
+      "learning_rate": 1.164129625547028e-06,
+      "loss": 0.2242,
+      "step": 7776
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 1.0806019306182861,
+      "learning_rate": 1.1426017543140047e-06,
+      "loss": 0.2163,
+      "step": 7808
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 1.0637164115905762,
+      "learning_rate": 1.121215679794396e-06,
+      "loss": 0.2213,
+      "step": 7840
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.0965406894683838,
+      "learning_rate": 1.0999736360231186e-06,
+      "loss": 0.213,
+      "step": 7872
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.9617595672607422,
+      "learning_rate": 1.0788778419893334e-06,
+      "loss": 0.2204,
+      "step": 7904
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.9679872393608093,
+      "learning_rate": 1.0579305014046417e-06,
+      "loss": 0.2201,
+      "step": 7936
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 1.441795825958252,
+      "learning_rate": 1.0371338024728796e-06,
+      "loss": 0.2234,
+      "step": 7968
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.0238152742385864,
+      "learning_rate": 1.0164899176615373e-06,
+      "loss": 0.2211,
+      "step": 8000
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.120363473892212,
+      "learning_rate": 9.960010034748124e-07,
+      "loss": 0.2198,
+      "step": 8032
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 1.2121866941452026,
+      "learning_rate": 9.756692002283475e-07,
+      "loss": 0.2224,
+      "step": 8064
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.9803070425987244,
+      "learning_rate": 9.554966318256356e-07,
+      "loss": 0.2164,
+      "step": 8096
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 1.0884270668029785,
+      "learning_rate": 9.354854055361595e-07,
+      "loss": 0.2167,
+      "step": 8128
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.996280312538147,
+      "learning_rate": 9.156376117752641e-07,
+      "loss": 0.2143,
+      "step": 8160
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 1.113319754600525,
+      "learning_rate": 8.959553238857796e-07,
+      "loss": 0.2131,
+      "step": 8192
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 1.1390118598937988,
+      "learning_rate": 8.764405979214457e-07,
+      "loss": 0.2272,
+      "step": 8224
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 1.2022590637207031,
+      "learning_rate": 8.57095472432121e-07,
+      "loss": 0.2253,
+      "step": 8256
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 1.1126353740692139,
+      "learning_rate": 8.37921968250841e-07,
+      "loss": 0.2254,
+      "step": 8288
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 1.1019079685211182,
+      "learning_rate": 8.189220882827104e-07,
+      "loss": 0.2213,
+      "step": 8320
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 1.200058102607727,
+      "learning_rate": 8.000978172956808e-07,
+      "loss": 0.2227,
+      "step": 8352
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 1.122356653213501,
+      "learning_rate": 7.814511217132156e-07,
+      "loss": 0.2291,
+      "step": 8384
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 1.2049360275268555,
+      "learning_rate": 7.629839494088709e-07,
+      "loss": 0.2193,
+      "step": 8416
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.0520132780075073,
+      "learning_rate": 7.446982295028201e-07,
+      "loss": 0.2312,
+      "step": 8448
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 1.0635144710540771,
+      "learning_rate": 7.265958721603333e-07,
+      "loss": 0.2253,
+      "step": 8480
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 1.0917962789535522,
+      "learning_rate": 7.086787683922339e-07,
+      "loss": 0.22,
+      "step": 8512
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.9784510731697083,
+      "learning_rate": 6.909487898573649e-07,
+      "loss": 0.2186,
+      "step": 8544
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 1.056834101676941,
+      "learning_rate": 6.734077886670651e-07,
+      "loss": 0.2199,
+      "step": 8576
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.0819662809371948,
+      "learning_rate": 6.560575971917024e-07,
+      "loss": 0.2203,
+      "step": 8608
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 1.1823601722717285,
+      "learning_rate": 6.389000278692505e-07,
+      "loss": 0.2192,
+      "step": 8640
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 1.2468321323394775,
+      "learning_rate": 6.219368730159642e-07,
+      "loss": 0.2085,
+      "step": 8672
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 1.227073311805725,
+      "learning_rate": 6.051699046391488e-07,
+      "loss": 0.2315,
+      "step": 8704
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.0343830585479736,
+      "learning_rate": 5.886008742520524e-07,
+      "loss": 0.2255,
+      "step": 8736
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 1.0291675329208374,
+      "learning_rate": 5.722315126908987e-07,
+      "loss": 0.2204,
+      "step": 8768
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 1.0927751064300537,
+      "learning_rate": 5.560635299340791e-07,
+      "loss": 0.2232,
+      "step": 8800
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 1.0045360326766968,
+      "learning_rate": 5.400986149235276e-07,
+      "loss": 0.2287,
+      "step": 8832
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 1.0229657888412476,
+      "learning_rate": 5.243384353882888e-07,
+      "loss": 0.221,
+      "step": 8864
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 1.0993235111236572,
+      "learning_rate": 5.087846376703012e-07,
+      "loss": 0.235,
+      "step": 8896
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 1.0891718864440918,
+      "learning_rate": 4.934388465524212e-07,
+      "loss": 0.2147,
+      "step": 8928
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 1.0884323120117188,
+      "learning_rate": 4.783026650886905e-07,
+      "loss": 0.2187,
+      "step": 8960
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 1.069006323814392,
+      "learning_rate": 4.633776744368809e-07,
+      "loss": 0.2194,
+      "step": 8992
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 1.042988896369934,
+      "learning_rate": 4.4866543369332274e-07,
+      "loss": 0.2243,
+      "step": 9024
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 1.0417791604995728,
+      "learning_rate": 4.3416747973003466e-07,
+      "loss": 0.228,
+      "step": 9056
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 1.0614454746246338,
+      "learning_rate": 4.198853270341843e-07,
+      "loss": 0.2193,
+      "step": 9088
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.0270013809204102,
+      "learning_rate": 4.058204675498781e-07,
+      "loss": 0.2109,
+      "step": 9120
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 1.3116717338562012,
+      "learning_rate": 3.919743705223111e-07,
+      "loss": 0.2237,
+      "step": 9152
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 1.129503607749939,
+      "learning_rate": 3.7834848234428427e-07,
+      "loss": 0.2201,
+      "step": 9184
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 1.0962566137313843,
+      "learning_rate": 3.649442264051145e-07,
+      "loss": 0.2164,
+      "step": 9216
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.9729294180870056,
+      "learning_rate": 3.517630029419428e-07,
+      "loss": 0.2162,
+      "step": 9248
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 1.1391122341156006,
+      "learning_rate": 3.388061888934607e-07,
+      "loss": 0.2162,
+      "step": 9280
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.061091661453247,
+      "learning_rate": 3.260751377560761e-07,
+      "loss": 0.2271,
+      "step": 9312
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.2862564325332642,
+      "learning_rate": 3.135711794425203e-07,
+      "loss": 0.2221,
+      "step": 9344
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 1.1859101057052612,
+      "learning_rate": 3.01295620142926e-07,
+      "loss": 0.2122,
+      "step": 9376
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 1.04880690574646,
+      "learning_rate": 2.892497421883772e-07,
+      "loss": 0.2207,
+      "step": 9408
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 1.0756020545959473,
+      "learning_rate": 2.774348039169547e-07,
+      "loss": 0.2159,
+      "step": 9440
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.0920884609222412,
+      "learning_rate": 2.6585203954228865e-07,
+      "loss": 0.2092,
+      "step": 9472
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.9831371903419495,
+      "learning_rate": 2.5450265902462914e-07,
+      "loss": 0.2127,
+      "step": 9504
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 1.0958073139190674,
+      "learning_rate": 2.433878479444515e-07,
+      "loss": 0.2205,
+      "step": 9536
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 1.150566577911377,
+      "learning_rate": 2.3250876737860696e-07,
+      "loss": 0.219,
+      "step": 9568
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.067936658859253,
+      "learning_rate": 2.2186655377903375e-07,
+      "loss": 0.2225,
+      "step": 9600
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.1066455841064453,
+      "learning_rate": 2.1146231885404572e-07,
+      "loss": 0.2211,
+      "step": 9632
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 1.1435866355895996,
+      "learning_rate": 2.0129714945219343e-07,
+      "loss": 0.2242,
+      "step": 9664
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 1.1800599098205566,
+      "learning_rate": 1.9137210744873597e-07,
+      "loss": 0.2075,
+      "step": 9696
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 1.170454978942871,
+      "learning_rate": 1.8168822963471084e-07,
+      "loss": 0.2267,
+      "step": 9728
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 1.055645227432251,
+      "learning_rate": 1.7224652760863131e-07,
+      "loss": 0.2135,
+      "step": 9760
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 1.0400182008743286,
+      "learning_rate": 1.6304798767081243e-07,
+      "loss": 0.2268,
+      "step": 9792
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 1.0586903095245361,
+      "learning_rate": 1.5409357072033781e-07,
+      "loss": 0.2185,
+      "step": 9824
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 1.2480932474136353,
+      "learning_rate": 1.4538421215468418e-07,
+      "loss": 0.2221,
+      "step": 9856
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 1.0862683057785034,
+      "learning_rate": 1.3692082177200833e-07,
+      "loss": 0.2304,
+      "step": 9888
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 1.1616886854171753,
+      "learning_rate": 1.2870428367610433e-07,
+      "loss": 0.2156,
+      "step": 9920
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 1.0725858211517334,
+      "learning_rate": 1.2073545618405207e-07,
+      "loss": 0.2073,
+      "step": 9952
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 1.110379695892334,
+      "learning_rate": 1.1301517173655241e-07,
+      "loss": 0.2162,
+      "step": 9984
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 1.016119122505188,
+      "learning_rate": 1.0554423681097242e-07,
+      "loss": 0.2195,
+      "step": 10016
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.0370144844055176,
+      "learning_rate": 9.832343183709404e-08,
+      "loss": 0.2099,
+      "step": 10048
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 1.0954487323760986,
+      "learning_rate": 9.135351111559331e-08,
+      "loss": 0.2186,
+      "step": 10080
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.137527346611023,
+      "learning_rate": 8.463520273924163e-08,
+      "loss": 0.2057,
+      "step": 10112
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.2059780359268188,
+      "learning_rate": 7.816920851684922e-08,
+      "loss": 0.2198,
+      "step": 10144
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 1.1751294136047363,
+      "learning_rate": 7.19562038999519e-08,
+      "loss": 0.2165,
+      "step": 10176
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.138420581817627,
+      "learning_rate": 6.599683791225165e-08,
+      "loss": 0.2131,
+      "step": 10208
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 1.0257811546325684,
+      "learning_rate": 6.029173308181923e-08,
+      "loss": 0.2197,
+      "step": 10240
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.9232725501060486,
+      "learning_rate": 5.484148537606399e-08,
+      "loss": 0.2213,
+      "step": 10272
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 1.1405422687530518,
+      "learning_rate": 4.964666413947466e-08,
+      "loss": 0.2166,
+      "step": 10304
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 1.0040420293807983,
+      "learning_rate": 4.4707812034148754e-08,
+      "loss": 0.2269,
+      "step": 10336
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 1.119696021080017,
+      "learning_rate": 4.002544498310196e-08,
+      "loss": 0.224,
+      "step": 10368
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 1.0494204759597778,
+      "learning_rate": 3.560005211637435e-08,
+      "loss": 0.2211,
+      "step": 10400
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 1.036290168762207,
+      "learning_rate": 3.1432095719936276e-08,
+      "loss": 0.2223,
+      "step": 10432
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 1.1206755638122559,
+      "learning_rate": 2.752201118739417e-08,
+      "loss": 0.2133,
+      "step": 10464
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.1237061023712158,
+      "learning_rate": 2.3870206974511423e-08,
+      "loss": 0.2175,
+      "step": 10496
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 1.0311527252197266,
+      "learning_rate": 2.0477064556537753e-08,
+      "loss": 0.2234,
+      "step": 10528
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 1.3335694074630737,
+      "learning_rate": 1.7342938388361376e-08,
+      "loss": 0.2187,
+      "step": 10560
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 1.1897953748703003,
+      "learning_rate": 1.446815586748085e-08,
+      "loss": 0.2258,
+      "step": 10592
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 1.1656417846679688,
+      "learning_rate": 1.1853017299804371e-08,
+      "loss": 0.2205,
+      "step": 10624
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 1.2942816019058228,
+      "learning_rate": 9.497795868279592e-09,
+      "loss": 0.2193,
+      "step": 10656
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 1.1674617528915405,
+      "learning_rate": 7.402737604356725e-09,
+      "loss": 0.2263,
+      "step": 10688
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 1.091424822807312,
+      "learning_rate": 5.568061362286326e-09,
+      "loss": 0.2198,
+      "step": 10720
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 1.0884166955947876,
+      "learning_rate": 3.9939587962584124e-09,
+      "loss": 0.2114,
+      "step": 10752
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.0358613729476929,
+      "learning_rate": 2.6805943403818146e-09,
+      "loss": 0.2237,
+      "step": 10784
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 1.0734291076660156,
+      "learning_rate": 1.6281051915059687e-09,
+      "loss": 0.215,
+      "step": 10816
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 1.3051434755325317,
+      "learning_rate": 8.366012948907154e-10,
+      "loss": 0.2201,
+      "step": 10848
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 1.0843610763549805,
+      "learning_rate": 3.0616533271937696e-10,
+      "loss": 0.2249,
+      "step": 10880
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.1933664083480835,
+      "learning_rate": 3.685271546344238e-11,
+      "loss": 0.211,
+      "step": 10912
+    }
+  ],
+  "logging_steps": 32,
+  "max_steps": 10929,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 3643,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1453591c2c4cf5405f2595557cdb2bd5f8cfa7fa4efe83689115e16bbfa734cf
+size 7032