Upload folder using huggingface_hub

added_tokens.json

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

checkpoint-12208/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": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-12208/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": "4.44.0.dev0"
+}

checkpoint-12208/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5ee70b809f3a8229c90f6bedf8ad0dfed28fbd791aadf028ac7225834504a1
+size 4976687216

checkpoint-12208/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb205482e80b5d03e63693e387d459b0cb9c97948cde971ff025ba98f1396d
+size 4778622352

checkpoint-12208/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222b40c6fea7def1d5911b059ab36bf97b9328e0251689f78a0a9ebd98cd18d
+size 4932743960

checkpoint-12208/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-12208/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-12208/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1528399458e8b61ba5714afbe0724d3b4dd92cbd9f8373cf906db0281325349
+size 3662865184

checkpoint-12208/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e539a6327f6418c6eff11bf80402ac8baf275bdc0c6c6e0aa9fb724277f13e7
+size 2179989632

checkpoint-12208/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-12208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37cd26dbe1d2b0debe46c45a0f26501ffa7643dabfb39cedf3804dc392cddbf
+size 16177880918

checkpoint-12208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-12208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe644ed33a3c4139223f0857a985127f3e6fbaa8c89fa14b57671b49ca52c21
+size 1064

checkpoint-12208/trainer_state.json

@@ -0,0 +1,2784 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3205461467769463,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008139687541026651,
+      "grad_norm": 4.344635963439941,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 2.2692,
+      "step": 31
+    },
+    {
+      "epoch": 0.0016279375082053301,
+      "grad_norm": 3.368666648864746,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 2.1052,
+      "step": 62
+    },
+    {
+      "epoch": 0.0024419062623079954,
+      "grad_norm": 2.7267792224884033,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.9706,
+      "step": 93
+    },
+    {
+      "epoch": 0.0032558750164106602,
+      "grad_norm": 2.7047057151794434,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.8885,
+      "step": 124
+    },
+    {
+      "epoch": 0.004069843770513325,
+      "grad_norm": 3.3375585079193115,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.8478,
+      "step": 155
+    },
+    {
+      "epoch": 0.004883812524615991,
+      "grad_norm": 3.4933056831359863,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.7963,
+      "step": 186
+    },
+    {
+      "epoch": 0.005697781278718656,
+      "grad_norm": 3.0248019695281982,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.7574,
+      "step": 217
+    },
+    {
+      "epoch": 0.0065117500328213205,
+      "grad_norm": 4.682138442993164,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.7395,
+      "step": 248
+    },
+    {
+      "epoch": 0.007325718786923986,
+      "grad_norm": 3.119105815887451,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.6976,
+      "step": 279
+    },
+    {
+      "epoch": 0.00813968754102665,
+      "grad_norm": 3.5156071186065674,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.674,
+      "step": 310
+    },
+    {
+      "epoch": 0.008953656295129316,
+      "grad_norm": 4.706497669219971,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.6624,
+      "step": 341
+    },
+    {
+      "epoch": 0.009767625049231982,
+      "grad_norm": 3.1241273880004883,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.6397,
+      "step": 372
+    },
+    {
+      "epoch": 0.010581593803334646,
+      "grad_norm": 3.151201009750366,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.6188,
+      "step": 403
+    },
+    {
+      "epoch": 0.011395562557437311,
+      "grad_norm": 3.722181797027588,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 1.611,
+      "step": 434
+    },
+    {
+      "epoch": 0.012209531311539977,
+      "grad_norm": 3.824608087539673,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 1.586,
+      "step": 465
+    },
+    {
+      "epoch": 0.013023500065642641,
+      "grad_norm": 3.6900010108947754,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 1.587,
+      "step": 496
+    },
+    {
+      "epoch": 0.013837468819745307,
+      "grad_norm": 2.8361997604370117,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 1.5588,
+      "step": 527
+    },
+    {
+      "epoch": 0.014651437573847972,
+      "grad_norm": 3.0725274085998535,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 1.5444,
+      "step": 558
+    },
+    {
+      "epoch": 0.015465406327950636,
+      "grad_norm": 3.16789174079895,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 1.5263,
+      "step": 589
+    },
+    {
+      "epoch": 0.0162793750820533,
+      "grad_norm": 3.24831485748291,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 1.5183,
+      "step": 620
+    },
+    {
+      "epoch": 0.017093343836155968,
+      "grad_norm": 2.6746206283569336,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 1.507,
+      "step": 651
+    },
+    {
+      "epoch": 0.017907312590258632,
+      "grad_norm": 3.2530715465545654,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 1.4959,
+      "step": 682
+    },
+    {
+      "epoch": 0.018721281344361296,
+      "grad_norm": 2.9383180141448975,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 1.4917,
+      "step": 713
+    },
+    {
+      "epoch": 0.019535250098463963,
+      "grad_norm": 3.0983939170837402,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 1.4733,
+      "step": 744
+    },
+    {
+      "epoch": 0.020349218852566627,
+      "grad_norm": 2.7612287998199463,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 1.466,
+      "step": 775
+    },
+    {
+      "epoch": 0.02116318760666929,
+      "grad_norm": 3.277587890625,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 1.4632,
+      "step": 806
+    },
+    {
+      "epoch": 0.02197715636077196,
+      "grad_norm": 3.678492546081543,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 1.4451,
+      "step": 837
+    },
+    {
+      "epoch": 0.022791125114874623,
+      "grad_norm": 3.4245243072509766,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 1.4531,
+      "step": 868
+    },
+    {
+      "epoch": 0.023605093868977287,
+      "grad_norm": 2.77119517326355,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 1.4336,
+      "step": 899
+    },
+    {
+      "epoch": 0.024419062623079954,
+      "grad_norm": 4.630955696105957,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 1.428,
+      "step": 930
+    },
+    {
+      "epoch": 0.025233031377182618,
+      "grad_norm": 2.700655937194824,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 1.4258,
+      "step": 961
+    },
+    {
+      "epoch": 0.026047000131285282,
+      "grad_norm": 3.1581950187683105,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 1.416,
+      "step": 992
+    },
+    {
+      "epoch": 0.02686096888538795,
+      "grad_norm": 2.463796377182007,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 1.4104,
+      "step": 1023
+    },
+    {
+      "epoch": 0.027674937639490613,
+      "grad_norm": 3.4881789684295654,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 1.4173,
+      "step": 1054
+    },
+    {
+      "epoch": 0.028488906393593277,
+      "grad_norm": 2.7470004558563232,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 1.398,
+      "step": 1085
+    },
+    {
+      "epoch": 0.029302875147695945,
+      "grad_norm": 2.9164175987243652,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 1.3864,
+      "step": 1116
+    },
+    {
+      "epoch": 0.03011684390179861,
+      "grad_norm": 3.191851854324341,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 1.3691,
+      "step": 1147
+    },
+    {
+      "epoch": 0.030930812655901273,
+      "grad_norm": 2.9015703201293945,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 1.3716,
+      "step": 1178
+    },
+    {
+      "epoch": 0.03174478141000394,
+      "grad_norm": 2.196329116821289,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 1.3784,
+      "step": 1209
+    },
+    {
+      "epoch": 0.0325587501641066,
+      "grad_norm": 3.0216293334960938,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 1.3729,
+      "step": 1240
+    },
+    {
+      "epoch": 0.03337271891820927,
+      "grad_norm": 2.435076951980591,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 1.3602,
+      "step": 1271
+    },
+    {
+      "epoch": 0.034186687672311936,
+      "grad_norm": 2.6987342834472656,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 1.3543,
+      "step": 1302
+    },
+    {
+      "epoch": 0.035000656426414596,
+      "grad_norm": 2.6493725776672363,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 1.35,
+      "step": 1333
+    },
+    {
+      "epoch": 0.035814625180517264,
+      "grad_norm": 2.2131760120391846,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 1.3459,
+      "step": 1364
+    },
+    {
+      "epoch": 0.03662859393461993,
+      "grad_norm": 2.9322702884674072,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 1.3553,
+      "step": 1395
+    },
+    {
+      "epoch": 0.03744256268872259,
+      "grad_norm": 2.8188889026641846,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 1.3445,
+      "step": 1426
+    },
+    {
+      "epoch": 0.03825653144282526,
+      "grad_norm": 3.5980286598205566,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 1.3412,
+      "step": 1457
+    },
+    {
+      "epoch": 0.039070500196927926,
+      "grad_norm": 2.4997692108154297,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 1.3291,
+      "step": 1488
+    },
+    {
+      "epoch": 0.03988446895103059,
+      "grad_norm": 3.452521562576294,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 1.3322,
+      "step": 1519
+    },
+    {
+      "epoch": 0.040698437705133254,
+      "grad_norm": 6.19186544418335,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 1.4477,
+      "step": 1550
+    },
+    {
+      "epoch": 0.04151240645923592,
+      "grad_norm": 2.761378526687622,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 1.464,
+      "step": 1581
+    },
+    {
+      "epoch": 0.04232637521333858,
+      "grad_norm": 2.5867984294891357,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 1.3881,
+      "step": 1612
+    },
+    {
+      "epoch": 0.04314034396744125,
+      "grad_norm": 3.0545732975006104,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 1.3787,
+      "step": 1643
+    },
+    {
+      "epoch": 0.04395431272154392,
+      "grad_norm": 2.5986175537109375,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 1.348,
+      "step": 1674
+    },
+    {
+      "epoch": 0.04476828147564658,
+      "grad_norm": 4.640907287597656,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 1.339,
+      "step": 1705
+    },
+    {
+      "epoch": 0.045582250229749245,
+      "grad_norm": 2.5423412322998047,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 1.3411,
+      "step": 1736
+    },
+    {
+      "epoch": 0.04639621898385191,
+      "grad_norm": 2.46950364112854,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 1.3278,
+      "step": 1767
+    },
+    {
+      "epoch": 0.04721018773795457,
+      "grad_norm": 3.782280445098877,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 1.303,
+      "step": 1798
+    },
+    {
+      "epoch": 0.04802415649205724,
+      "grad_norm": 2.7267119884490967,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 1.3125,
+      "step": 1829
+    },
+    {
+      "epoch": 0.04883812524615991,
+      "grad_norm": 2.2012853622436523,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 1.3121,
+      "step": 1860
+    },
+    {
+      "epoch": 0.04965209400026257,
+      "grad_norm": 2.5827276706695557,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 1.285,
+      "step": 1891
+    },
+    {
+      "epoch": 0.050466062754365236,
+      "grad_norm": 2.8490679264068604,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 1.2817,
+      "step": 1922
+    },
+    {
+      "epoch": 0.0512800315084679,
+      "grad_norm": 3.1449127197265625,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 1.2844,
+      "step": 1953
+    },
+    {
+      "epoch": 0.052094000262570564,
+      "grad_norm": 2.512974739074707,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 1.2949,
+      "step": 1984
+    },
+    {
+      "epoch": 0.05290796901667323,
+      "grad_norm": 2.118725299835205,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 1.2804,
+      "step": 2015
+    },
+    {
+      "epoch": 0.0537219377707759,
+      "grad_norm": 2.0815465450286865,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 1.2694,
+      "step": 2046
+    },
+    {
+      "epoch": 0.05453590652487856,
+      "grad_norm": 1.9531530141830444,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 1.2705,
+      "step": 2077
+    },
+    {
+      "epoch": 0.05534987527898123,
+      "grad_norm": 2.194906711578369,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 1.274,
+      "step": 2108
+    },
+    {
+      "epoch": 0.056163844033083894,
+      "grad_norm": 2.4935038089752197,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 1.2668,
+      "step": 2139
+    },
+    {
+      "epoch": 0.056977812787186555,
+      "grad_norm": 2.5282671451568604,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 1.2641,
+      "step": 2170
+    },
+    {
+      "epoch": 0.05779178154128922,
+      "grad_norm": 2.0164363384246826,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.2618,
+      "step": 2201
+    },
+    {
+      "epoch": 0.05860575029539189,
+      "grad_norm": 1.9289182424545288,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.2407,
+      "step": 2232
+    },
+    {
+      "epoch": 0.05941971904949455,
+      "grad_norm": 2.9115793704986572,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 1.2555,
+      "step": 2263
+    },
+    {
+      "epoch": 0.06023368780359722,
+      "grad_norm": 1.9424489736557007,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 1.2522,
+      "step": 2294
+    },
+    {
+      "epoch": 0.061047656557699885,
+      "grad_norm": 2.2720956802368164,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 1.245,
+      "step": 2325
+    },
+    {
+      "epoch": 0.061861625311802546,
+      "grad_norm": 2.204970121383667,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 1.2554,
+      "step": 2356
+    },
+    {
+      "epoch": 0.06267559406590521,
+      "grad_norm": 1.7172690629959106,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 1.2443,
+      "step": 2387
+    },
+    {
+      "epoch": 0.06348956282000788,
+      "grad_norm": 2.3312878608703613,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 1.2506,
+      "step": 2418
+    },
+    {
+      "epoch": 0.06430353157411055,
+      "grad_norm": 1.9023312330245972,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 1.239,
+      "step": 2449
+    },
+    {
+      "epoch": 0.0651175003282132,
+      "grad_norm": 2.0047945976257324,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.236,
+      "step": 2480
+    },
+    {
+      "epoch": 0.06593146908231587,
+      "grad_norm": 2.2633707523345947,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 1.2375,
+      "step": 2511
+    },
+    {
+      "epoch": 0.06674543783641854,
+      "grad_norm": 2.812201499938965,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 1.2412,
+      "step": 2542
+    },
+    {
+      "epoch": 0.0675594065905212,
+      "grad_norm": 2.291375160217285,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.2391,
+      "step": 2573
+    },
+    {
+      "epoch": 0.06837337534462387,
+      "grad_norm": 12.856545448303223,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.2201,
+      "step": 2604
+    },
+    {
+      "epoch": 0.06918734409872654,
+      "grad_norm": 2.3172965049743652,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.2333,
+      "step": 2635
+    },
+    {
+      "epoch": 0.07000131285282919,
+      "grad_norm": 2.4617788791656494,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.2152,
+      "step": 2666
+    },
+    {
+      "epoch": 0.07081528160693186,
+      "grad_norm": 3.4079201221466064,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.2315,
+      "step": 2697
+    },
+    {
+      "epoch": 0.07162925036103453,
+      "grad_norm": 2.0874247550964355,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.2457,
+      "step": 2728
+    },
+    {
+      "epoch": 0.0724432191151372,
+      "grad_norm": 1.8917243480682373,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.2345,
+      "step": 2759
+    },
+    {
+      "epoch": 0.07325718786923986,
+      "grad_norm": 2.0507922172546387,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.2088,
+      "step": 2790
+    },
+    {
+      "epoch": 0.07407115662334253,
+      "grad_norm": 2.2421083450317383,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.2168,
+      "step": 2821
+    },
+    {
+      "epoch": 0.07488512537744518,
+      "grad_norm": 2.0551934242248535,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.2161,
+      "step": 2852
+    },
+    {
+      "epoch": 0.07569909413154785,
+      "grad_norm": 2.987886667251587,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.2026,
+      "step": 2883
+    },
+    {
+      "epoch": 0.07651306288565052,
+      "grad_norm": 1.7029023170471191,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.2241,
+      "step": 2914
+    },
+    {
+      "epoch": 0.07732703163975319,
+      "grad_norm": 2.826143503189087,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.2116,
+      "step": 2945
+    },
+    {
+      "epoch": 0.07814100039385585,
+      "grad_norm": 2.029524564743042,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.207,
+      "step": 2976
+    },
+    {
+      "epoch": 0.07895496914795852,
+      "grad_norm": 2.3787524700164795,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.2097,
+      "step": 3007
+    },
+    {
+      "epoch": 0.07976893790206117,
+      "grad_norm": 1.4938246011734009,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.2025,
+      "step": 3038
+    },
+    {
+      "epoch": 0.08058290665616384,
+      "grad_norm": 2.125171184539795,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.2106,
+      "step": 3069
+    },
+    {
+      "epoch": 0.08139687541026651,
+      "grad_norm": 2.165095329284668,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.2075,
+      "step": 3100
+    },
+    {
+      "epoch": 0.08221084416436918,
+      "grad_norm": 1.8615927696228027,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.1982,
+      "step": 3131
+    },
+    {
+      "epoch": 0.08302481291847184,
+      "grad_norm": 1.6977221965789795,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.2039,
+      "step": 3162
+    },
+    {
+      "epoch": 0.08383878167257451,
+      "grad_norm": 1.5559513568878174,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.2024,
+      "step": 3193
+    },
+    {
+      "epoch": 0.08465275042667716,
+      "grad_norm": 2.228041172027588,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.1928,
+      "step": 3224
+    },
+    {
+      "epoch": 0.08546671918077983,
+      "grad_norm": 1.6358845233917236,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.1965,
+      "step": 3255
+    },
+    {
+      "epoch": 0.0862806879348825,
+      "grad_norm": 1.8761228322982788,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.1864,
+      "step": 3286
+    },
+    {
+      "epoch": 0.08709465668898517,
+      "grad_norm": 2.3128018379211426,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.1958,
+      "step": 3317
+    },
+    {
+      "epoch": 0.08790862544308783,
+      "grad_norm": 1.9828768968582153,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.1885,
+      "step": 3348
+    },
+    {
+      "epoch": 0.08872259419719049,
+      "grad_norm": 1.9600850343704224,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.19,
+      "step": 3379
+    },
+    {
+      "epoch": 0.08953656295129316,
+      "grad_norm": 1.755077600479126,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.1939,
+      "step": 3410
+    },
+    {
+      "epoch": 0.09035053170539582,
+      "grad_norm": 2.477156400680542,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.1895,
+      "step": 3441
+    },
+    {
+      "epoch": 0.09116450045949849,
+      "grad_norm": 2.5017731189727783,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.1957,
+      "step": 3472
+    },
+    {
+      "epoch": 0.09197846921360116,
+      "grad_norm": 1.8620328903198242,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.1898,
+      "step": 3503
+    },
+    {
+      "epoch": 0.09279243796770383,
+      "grad_norm": 1.9636398553848267,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.1934,
+      "step": 3534
+    },
+    {
+      "epoch": 0.09360640672180648,
+      "grad_norm": 1.7159295082092285,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.1909,
+      "step": 3565
+    },
+    {
+      "epoch": 0.09442037547590915,
+      "grad_norm": 2.02683424949646,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.1785,
+      "step": 3596
+    },
+    {
+      "epoch": 0.09523434423001181,
+      "grad_norm": 2.09055757522583,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.1713,
+      "step": 3627
+    },
+    {
+      "epoch": 0.09604831298411448,
+      "grad_norm": 1.5010393857955933,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.1754,
+      "step": 3658
+    },
+    {
+      "epoch": 0.09686228173821715,
+      "grad_norm": 1.864301085472107,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.1808,
+      "step": 3689
+    },
+    {
+      "epoch": 0.09767625049231982,
+      "grad_norm": 1.7567156553268433,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.1648,
+      "step": 3720
+    },
+    {
+      "epoch": 0.09849021924642247,
+      "grad_norm": 1.424232006072998,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.1708,
+      "step": 3751
+    },
+    {
+      "epoch": 0.09930418800052514,
+      "grad_norm": 1.8835548162460327,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.1669,
+      "step": 3782
+    },
+    {
+      "epoch": 0.1001181567546278,
+      "grad_norm": 1.3818198442459106,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.1727,
+      "step": 3813
+    },
+    {
+      "epoch": 0.10093212550873047,
+      "grad_norm": 1.6063064336776733,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.1499,
+      "step": 3844
+    },
+    {
+      "epoch": 0.10174609426283314,
+      "grad_norm": 1.8761767148971558,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.1707,
+      "step": 3875
+    },
+    {
+      "epoch": 0.1025600630169358,
+      "grad_norm": 2.069032669067383,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.1577,
+      "step": 3906
+    },
+    {
+      "epoch": 0.10337403177103846,
+      "grad_norm": 1.6974114179611206,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.1704,
+      "step": 3937
+    },
+    {
+      "epoch": 0.10418800052514113,
+      "grad_norm": 1.4797635078430176,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.1648,
+      "step": 3968
+    },
+    {
+      "epoch": 0.1050019692792438,
+      "grad_norm": 2.3781850337982178,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.1647,
+      "step": 3999
+    },
+    {
+      "epoch": 0.10581593803334646,
+      "grad_norm": 1.6512064933776855,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.1654,
+      "step": 4030
+    },
+    {
+      "epoch": 0.10662990678744913,
+      "grad_norm": 1.760602355003357,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.1596,
+      "step": 4061
+    },
+    {
+      "epoch": 0.1074438755415518,
+      "grad_norm": 1.785792350769043,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.1493,
+      "step": 4092
+    },
+    {
+      "epoch": 0.10825784429565445,
+      "grad_norm": 2.3284568786621094,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.1732,
+      "step": 4123
+    },
+    {
+      "epoch": 0.10907181304975712,
+      "grad_norm": 1.4291197061538696,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.1605,
+      "step": 4154
+    },
+    {
+      "epoch": 0.10988578180385979,
+      "grad_norm": 2.1645402908325195,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.1576,
+      "step": 4185
+    },
+    {
+      "epoch": 0.11069975055796245,
+      "grad_norm": 2.064669609069824,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.1485,
+      "step": 4216
+    },
+    {
+      "epoch": 0.11151371931206512,
+      "grad_norm": 1.6745102405548096,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.1738,
+      "step": 4247
+    },
+    {
+      "epoch": 0.11232768806616779,
+      "grad_norm": 2.76240611076355,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.1482,
+      "step": 4278
+    },
+    {
+      "epoch": 0.11314165682027044,
+      "grad_norm": 1.3859837055206299,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.157,
+      "step": 4309
+    },
+    {
+      "epoch": 0.11395562557437311,
+      "grad_norm": 1.7919600009918213,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.1459,
+      "step": 4340
+    },
+    {
+      "epoch": 0.11476959432847578,
+      "grad_norm": 1.7550104856491089,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.1512,
+      "step": 4371
+    },
+    {
+      "epoch": 0.11558356308257844,
+      "grad_norm": 1.2225311994552612,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.1555,
+      "step": 4402
+    },
+    {
+      "epoch": 0.11639753183668111,
+      "grad_norm": 1.7609676122665405,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.1503,
+      "step": 4433
+    },
+    {
+      "epoch": 0.11721150059078378,
+      "grad_norm": 1.539068341255188,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.1517,
+      "step": 4464
+    },
+    {
+      "epoch": 0.11802546934488643,
+      "grad_norm": 1.4526177644729614,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.1533,
+      "step": 4495
+    },
+    {
+      "epoch": 0.1188394380989891,
+      "grad_norm": 1.9552894830703735,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.1647,
+      "step": 4526
+    },
+    {
+      "epoch": 0.11965340685309177,
+      "grad_norm": 1.3867082595825195,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.1412,
+      "step": 4557
+    },
+    {
+      "epoch": 0.12046737560719444,
+      "grad_norm": 1.7866445779800415,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.15,
+      "step": 4588
+    },
+    {
+      "epoch": 0.1212813443612971,
+      "grad_norm": 1.757614016532898,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.1462,
+      "step": 4619
+    },
+    {
+      "epoch": 0.12209531311539977,
+      "grad_norm": 1.644196629524231,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.1411,
+      "step": 4650
+    },
+    {
+      "epoch": 0.12290928186950242,
+      "grad_norm": 1.5721986293792725,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.153,
+      "step": 4681
+    },
+    {
+      "epoch": 0.12372325062360509,
+      "grad_norm": 1.493248462677002,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.1373,
+      "step": 4712
+    },
+    {
+      "epoch": 0.12453721937770776,
+      "grad_norm": 1.7797431945800781,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.1475,
+      "step": 4743
+    },
+    {
+      "epoch": 0.12535118813181043,
+      "grad_norm": 1.5288772583007812,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.139,
+      "step": 4774
+    },
+    {
+      "epoch": 0.1261651568859131,
+      "grad_norm": 2.1584365367889404,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.14,
+      "step": 4805
+    },
+    {
+      "epoch": 0.12697912564001576,
+      "grad_norm": 1.7980725765228271,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.1441,
+      "step": 4836
+    },
+    {
+      "epoch": 0.12779309439411843,
+      "grad_norm": 1.739778995513916,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.1402,
+      "step": 4867
+    },
+    {
+      "epoch": 0.1286070631482211,
+      "grad_norm": 1.7673060894012451,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.1313,
+      "step": 4898
+    },
+    {
+      "epoch": 0.12942103190232376,
+      "grad_norm": 1.660517930984497,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.1474,
+      "step": 4929
+    },
+    {
+      "epoch": 0.1302350006564264,
+      "grad_norm": 1.7969893217086792,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.144,
+      "step": 4960
+    },
+    {
+      "epoch": 0.13104896941052907,
+      "grad_norm": 1.5473248958587646,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.146,
+      "step": 4991
+    },
+    {
+      "epoch": 0.13186293816463174,
+      "grad_norm": 1.723632574081421,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.1527,
+      "step": 5022
+    },
+    {
+      "epoch": 0.1326769069187344,
+      "grad_norm": 1.4418350458145142,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.1308,
+      "step": 5053
+    },
+    {
+      "epoch": 0.13349087567283707,
+      "grad_norm": 1.9781032800674438,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.1358,
+      "step": 5084
+    },
+    {
+      "epoch": 0.13430484442693974,
+      "grad_norm": 1.8926130533218384,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.141,
+      "step": 5115
+    },
+    {
+      "epoch": 0.1351188131810424,
+      "grad_norm": 1.5577887296676636,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.132,
+      "step": 5146
+    },
+    {
+      "epoch": 0.13593278193514508,
+      "grad_norm": 2.112377166748047,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.1499,
+      "step": 5177
+    },
+    {
+      "epoch": 0.13674675068924774,
+      "grad_norm": 2.142568826675415,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.1488,
+      "step": 5208
+    },
+    {
+      "epoch": 0.1375607194433504,
+      "grad_norm": 1.713492751121521,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.1312,
+      "step": 5239
+    },
+    {
+      "epoch": 0.13837468819745308,
+      "grad_norm": 1.8712431192398071,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.1344,
+      "step": 5270
+    },
+    {
+      "epoch": 0.13918865695155572,
+      "grad_norm": 1.609357237815857,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.1209,
+      "step": 5301
+    },
+    {
+      "epoch": 0.14000262570565838,
+      "grad_norm": 2.1064646244049072,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.1416,
+      "step": 5332
+    },
+    {
+      "epoch": 0.14081659445976105,
+      "grad_norm": 1.4620094299316406,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.1275,
+      "step": 5363
+    },
+    {
+      "epoch": 0.14163056321386372,
+      "grad_norm": 1.32656729221344,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.1329,
+      "step": 5394
+    },
+    {
+      "epoch": 0.1424445319679664,
+      "grad_norm": 1.4479507207870483,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.1354,
+      "step": 5425
+    },
+    {
+      "epoch": 0.14325850072206905,
+      "grad_norm": 1.6729614734649658,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.1364,
+      "step": 5456
+    },
+    {
+      "epoch": 0.14407246947617172,
+      "grad_norm": 1.4260097742080688,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.1319,
+      "step": 5487
+    },
+    {
+      "epoch": 0.1448864382302744,
+      "grad_norm": 1.5216090679168701,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.1392,
+      "step": 5518
+    },
+    {
+      "epoch": 0.14570040698437706,
+      "grad_norm": 1.3038978576660156,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.1262,
+      "step": 5549
+    },
+    {
+      "epoch": 0.14651437573847972,
+      "grad_norm": 1.3285478353500366,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.1154,
+      "step": 5580
+    },
+    {
+      "epoch": 0.1473283444925824,
+      "grad_norm": 1.4460917711257935,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.1226,
+      "step": 5611
+    },
+    {
+      "epoch": 0.14814231324668506,
+      "grad_norm": 1.3280593156814575,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.1154,
+      "step": 5642
+    },
+    {
+      "epoch": 0.1489562820007877,
+      "grad_norm": 1.8312699794769287,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.126,
+      "step": 5673
+    },
+    {
+      "epoch": 0.14977025075489037,
+      "grad_norm": 2.0447463989257812,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.1274,
+      "step": 5704
+    },
+    {
+      "epoch": 0.15058421950899303,
+      "grad_norm": 1.5046786069869995,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.1097,
+      "step": 5735
+    },
+    {
+      "epoch": 0.1513981882630957,
+      "grad_norm": 1.5917468070983887,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.1219,
+      "step": 5766
+    },
+    {
+      "epoch": 0.15221215701719837,
+      "grad_norm": 1.4890860319137573,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.1307,
+      "step": 5797
+    },
+    {
+      "epoch": 0.15302612577130104,
+      "grad_norm": 1.557468056678772,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.1173,
+      "step": 5828
+    },
+    {
+      "epoch": 0.1538400945254037,
+      "grad_norm": 1.7449064254760742,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.1216,
+      "step": 5859
+    },
+    {
+      "epoch": 0.15465406327950637,
+      "grad_norm": 1.6439781188964844,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.1228,
+      "step": 5890
+    },
+    {
+      "epoch": 0.15546803203360904,
+      "grad_norm": 2.3047573566436768,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.126,
+      "step": 5921
+    },
+    {
+      "epoch": 0.1562820007877117,
+      "grad_norm": 2.0222270488739014,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.1245,
+      "step": 5952
+    },
+    {
+      "epoch": 0.15709596954181437,
+      "grad_norm": 1.5156447887420654,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.128,
+      "step": 5983
+    },
+    {
+      "epoch": 0.15790993829591704,
+      "grad_norm": 1.8281335830688477,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.12,
+      "step": 6014
+    },
+    {
+      "epoch": 0.15872390705001968,
+      "grad_norm": 1.669470191001892,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.1065,
+      "step": 6045
+    },
+    {
+      "epoch": 0.15953787580412235,
+      "grad_norm": 1.4428647756576538,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.1218,
+      "step": 6076
+    },
+    {
+      "epoch": 0.16035184455822502,
+      "grad_norm": 1.5096391439437866,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.1125,
+      "step": 6107
+    },
+    {
+      "epoch": 0.16116581331232768,
+      "grad_norm": 1.6360524892807007,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.0959,
+      "step": 6138
+    },
+    {
+      "epoch": 0.16197978206643035,
+      "grad_norm": 1.6503233909606934,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.1046,
+      "step": 6169
+    },
+    {
+      "epoch": 0.16279375082053302,
+      "grad_norm": 1.6234620809555054,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.1101,
+      "step": 6200
+    },
+    {
+      "epoch": 0.16360771957463568,
+      "grad_norm": 1.1652549505233765,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.0979,
+      "step": 6231
+    },
+    {
+      "epoch": 0.16442168832873835,
+      "grad_norm": 1.8738065958023071,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.1158,
+      "step": 6262
+    },
+    {
+      "epoch": 0.16523565708284102,
+      "grad_norm": 1.678968071937561,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.1185,
+      "step": 6293
+    },
+    {
+      "epoch": 0.1660496258369437,
+      "grad_norm": 1.4664219617843628,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.1127,
+      "step": 6324
+    },
+    {
+      "epoch": 0.16686359459104635,
+      "grad_norm": 1.463440179824829,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.1039,
+      "step": 6355
+    },
+    {
+      "epoch": 0.16767756334514902,
+      "grad_norm": 1.4472638368606567,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.1158,
+      "step": 6386
+    },
+    {
+      "epoch": 0.16849153209925166,
+      "grad_norm": 1.5634558200836182,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.1074,
+      "step": 6417
+    },
+    {
+      "epoch": 0.16930550085335433,
+      "grad_norm": 1.4016892910003662,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.0988,
+      "step": 6448
+    },
+    {
+      "epoch": 0.170119469607457,
+      "grad_norm": 1.4526346921920776,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.1032,
+      "step": 6479
+    },
+    {
+      "epoch": 0.17093343836155966,
+      "grad_norm": 1.8762003183364868,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.0924,
+      "step": 6510
+    },
+    {
+      "epoch": 0.17174740711566233,
+      "grad_norm": 1.4504212141036987,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.1182,
+      "step": 6541
+    },
+    {
+      "epoch": 0.172561375869765,
+      "grad_norm": 1.4169540405273438,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.119,
+      "step": 6572
+    },
+    {
+      "epoch": 0.17337534462386767,
+      "grad_norm": 1.9999427795410156,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.1039,
+      "step": 6603
+    },
+    {
+      "epoch": 0.17418931337797033,
+      "grad_norm": 1.826111078262329,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.1056,
+      "step": 6634
+    },
+    {
+      "epoch": 0.175003282132073,
+      "grad_norm": 1.5917997360229492,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.1131,
+      "step": 6665
+    },
+    {
+      "epoch": 0.17581725088617567,
+      "grad_norm": 1.679688811302185,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.0905,
+      "step": 6696
+    },
+    {
+      "epoch": 0.17663121964027834,
+      "grad_norm": 1.0461444854736328,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.1079,
+      "step": 6727
+    },
+    {
+      "epoch": 0.17744518839438098,
+      "grad_norm": 1.2755801677703857,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.1098,
+      "step": 6758
+    },
+    {
+      "epoch": 0.17825915714848364,
+      "grad_norm": 1.9257614612579346,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.1138,
+      "step": 6789
+    },
+    {
+      "epoch": 0.1790731259025863,
+      "grad_norm": 1.3688116073608398,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.0994,
+      "step": 6820
+    },
+    {
+      "epoch": 0.17988709465668898,
+      "grad_norm": 1.9413882493972778,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.1033,
+      "step": 6851
+    },
+    {
+      "epoch": 0.18070106341079165,
+      "grad_norm": 1.2649338245391846,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.1045,
+      "step": 6882
+    },
+    {
+      "epoch": 0.1815150321648943,
+      "grad_norm": 1.4563463926315308,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.1078,
+      "step": 6913
+    },
+    {
+      "epoch": 0.18232900091899698,
+      "grad_norm": 1.2975566387176514,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.0961,
+      "step": 6944
+    },
+    {
+      "epoch": 0.18314296967309965,
+      "grad_norm": 1.3268362283706665,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.0907,
+      "step": 6975
+    },
+    {
+      "epoch": 0.18395693842720232,
+      "grad_norm": 1.811310052871704,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.0973,
+      "step": 7006
+    },
+    {
+      "epoch": 0.18477090718130498,
+      "grad_norm": 1.5738041400909424,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.0992,
+      "step": 7037
+    },
+    {
+      "epoch": 0.18558487593540765,
+      "grad_norm": 2.2612175941467285,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.1024,
+      "step": 7068
+    },
+    {
+      "epoch": 0.18639884468951032,
+      "grad_norm": 1.7416468858718872,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.0993,
+      "step": 7099
+    },
+    {
+      "epoch": 0.18721281344361296,
+      "grad_norm": 1.358522653579712,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.1034,
+      "step": 7130
+    },
+    {
+      "epoch": 0.18802678219771563,
+      "grad_norm": 1.3705374002456665,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.093,
+      "step": 7161
+    },
+    {
+      "epoch": 0.1888407509518183,
+      "grad_norm": 1.7620149850845337,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.0948,
+      "step": 7192
+    },
+    {
+      "epoch": 0.18965471970592096,
+      "grad_norm": 1.8306667804718018,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.1016,
+      "step": 7223
+    },
+    {
+      "epoch": 0.19046868846002363,
+      "grad_norm": 1.3714003562927246,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.1016,
+      "step": 7254
+    },
+    {
+      "epoch": 0.1912826572141263,
+      "grad_norm": 1.2869197130203247,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.0924,
+      "step": 7285
+    },
+    {
+      "epoch": 0.19209662596822896,
+      "grad_norm": 1.3529052734375,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.0972,
+      "step": 7316
+    },
+    {
+      "epoch": 0.19291059472233163,
+      "grad_norm": 1.3062899112701416,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.0963,
+      "step": 7347
+    },
+    {
+      "epoch": 0.1937245634764343,
+      "grad_norm": 1.7407621145248413,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.0992,
+      "step": 7378
+    },
+    {
+      "epoch": 0.19453853223053696,
+      "grad_norm": 1.2803786993026733,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.1025,
+      "step": 7409
+    },
+    {
+      "epoch": 0.19535250098463963,
+      "grad_norm": 1.5632768869400024,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.1008,
+      "step": 7440
+    },
+    {
+      "epoch": 0.1961664697387423,
+      "grad_norm": 1.6344542503356934,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.0975,
+      "step": 7471
+    },
+    {
+      "epoch": 0.19698043849284494,
+      "grad_norm": 1.531846523284912,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.099,
+      "step": 7502
+    },
+    {
+      "epoch": 0.1977944072469476,
+      "grad_norm": 1.588841199874878,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.0874,
+      "step": 7533
+    },
+    {
+      "epoch": 0.19860837600105027,
+      "grad_norm": 1.8889760971069336,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.0909,
+      "step": 7564
+    },
+    {
+      "epoch": 0.19942234475515294,
+      "grad_norm": 1.1373437643051147,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.1004,
+      "step": 7595
+    },
+    {
+      "epoch": 0.2002363135092556,
+      "grad_norm": 1.4850921630859375,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.1033,
+      "step": 7626
+    },
+    {
+      "epoch": 0.20105028226335828,
+      "grad_norm": 2.14884090423584,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.0981,
+      "step": 7657
+    },
+    {
+      "epoch": 0.20186425101746094,
+      "grad_norm": 1.7331793308258057,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.0981,
+      "step": 7688
+    },
+    {
+      "epoch": 0.2026782197715636,
+      "grad_norm": 1.8480019569396973,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.0849,
+      "step": 7719
+    },
+    {
+      "epoch": 0.20349218852566628,
+      "grad_norm": 1.6195038557052612,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.0978,
+      "step": 7750
+    },
+    {
+      "epoch": 0.20430615727976895,
+      "grad_norm": 1.5065410137176514,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.0888,
+      "step": 7781
+    },
+    {
+      "epoch": 0.2051201260338716,
+      "grad_norm": 1.6099448204040527,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.081,
+      "step": 7812
+    },
+    {
+      "epoch": 0.20593409478797428,
+      "grad_norm": 1.7982425689697266,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.0876,
+      "step": 7843
+    },
+    {
+      "epoch": 0.20674806354207692,
+      "grad_norm": 1.864194393157959,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.093,
+      "step": 7874
+    },
+    {
+      "epoch": 0.2075620322961796,
+      "grad_norm": 1.3261879682540894,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.0927,
+      "step": 7905
+    },
+    {
+      "epoch": 0.20837600105028226,
+      "grad_norm": 1.3466005325317383,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.1003,
+      "step": 7936
+    },
+    {
+      "epoch": 0.20918996980438492,
+      "grad_norm": 1.545696496963501,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.0809,
+      "step": 7967
+    },
+    {
+      "epoch": 0.2100039385584876,
+      "grad_norm": 1.5338133573532104,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.0752,
+      "step": 7998
+    },
+    {
+      "epoch": 0.21081790731259026,
+      "grad_norm": 2.43064022064209,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.0845,
+      "step": 8029
+    },
+    {
+      "epoch": 0.21163187606669293,
+      "grad_norm": 1.5302485227584839,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.0826,
+      "step": 8060
+    },
+    {
+      "epoch": 0.2124458448207956,
+      "grad_norm": 1.8339937925338745,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.0948,
+      "step": 8091
+    },
+    {
+      "epoch": 0.21325981357489826,
+      "grad_norm": 1.9686979055404663,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.0754,
+      "step": 8122
+    },
+    {
+      "epoch": 0.21407378232900093,
+      "grad_norm": 1.540440559387207,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.0884,
+      "step": 8153
+    },
+    {
+      "epoch": 0.2148877510831036,
+      "grad_norm": 1.741109013557434,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.074,
+      "step": 8184
+    },
+    {
+      "epoch": 0.21570171983720626,
+      "grad_norm": 1.1937834024429321,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.098,
+      "step": 8215
+    },
+    {
+      "epoch": 0.2165156885913089,
+      "grad_norm": 1.762987732887268,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.0894,
+      "step": 8246
+    },
+    {
+      "epoch": 0.21732965734541157,
+      "grad_norm": 1.6183695793151855,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.0944,
+      "step": 8277
+    },
+    {
+      "epoch": 0.21814362609951424,
+      "grad_norm": 2.039792776107788,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.0832,
+      "step": 8308
+    },
+    {
+      "epoch": 0.2189575948536169,
+      "grad_norm": 1.7424120903015137,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.0765,
+      "step": 8339
+    },
+    {
+      "epoch": 0.21977156360771957,
+      "grad_norm": 1.4619733095169067,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.084,
+      "step": 8370
+    },
+    {
+      "epoch": 0.22058553236182224,
+      "grad_norm": 1.578750729560852,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.0803,
+      "step": 8401
+    },
+    {
+      "epoch": 0.2213995011159249,
+      "grad_norm": 1.5708528757095337,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.0633,
+      "step": 8432
+    },
+    {
+      "epoch": 0.22221346987002757,
+      "grad_norm": 1.1335474252700806,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.0853,
+      "step": 8463
+    },
+    {
+      "epoch": 0.22302743862413024,
+      "grad_norm": 1.2993063926696777,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.0899,
+      "step": 8494
+    },
+    {
+      "epoch": 0.2238414073782329,
+      "grad_norm": 1.2681806087493896,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.0927,
+      "step": 8525
+    },
+    {
+      "epoch": 0.22465537613233558,
+      "grad_norm": 1.8203648328781128,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.0866,
+      "step": 8556
+    },
+    {
+      "epoch": 0.22546934488643822,
+      "grad_norm": 1.5113874673843384,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.0876,
+      "step": 8587
+    },
+    {
+      "epoch": 0.22628331364054088,
+      "grad_norm": 1.6668130159378052,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.0773,
+      "step": 8618
+    },
+    {
+      "epoch": 0.22709728239464355,
+      "grad_norm": 1.9352772235870361,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.0721,
+      "step": 8649
+    },
+    {
+      "epoch": 0.22791125114874622,
+      "grad_norm": 1.4542369842529297,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.0799,
+      "step": 8680
+    },
+    {
+      "epoch": 0.2287252199028489,
+      "grad_norm": 1.529205083847046,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.082,
+      "step": 8711
+    },
+    {
+      "epoch": 0.22953918865695155,
+      "grad_norm": 1.1309294700622559,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.0755,
+      "step": 8742
+    },
+    {
+      "epoch": 0.23035315741105422,
+      "grad_norm": 1.5995324850082397,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.0926,
+      "step": 8773
+    },
+    {
+      "epoch": 0.2311671261651569,
+      "grad_norm": 1.6205707788467407,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.0739,
+      "step": 8804
+    },
+    {
+      "epoch": 0.23198109491925956,
+      "grad_norm": 1.2695502042770386,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.0732,
+      "step": 8835
+    },
+    {
+      "epoch": 0.23279506367336222,
+      "grad_norm": 1.1835676431655884,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.0784,
+      "step": 8866
+    },
+    {
+      "epoch": 0.2336090324274649,
+      "grad_norm": 1.8403820991516113,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.0697,
+      "step": 8897
+    },
+    {
+      "epoch": 0.23442300118156756,
+      "grad_norm": 1.5087056159973145,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.0807,
+      "step": 8928
+    },
+    {
+      "epoch": 0.2352369699356702,
+      "grad_norm": 2.1309752464294434,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.0693,
+      "step": 8959
+    },
+    {
+      "epoch": 0.23605093868977287,
+      "grad_norm": 1.253975749015808,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.0602,
+      "step": 8990
+    },
+    {
+      "epoch": 0.23686490744387553,
+      "grad_norm": 1.1763646602630615,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.0879,
+      "step": 9021
+    },
+    {
+      "epoch": 0.2376788761979782,
+      "grad_norm": 1.3210095167160034,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.0731,
+      "step": 9052
+    },
+    {
+      "epoch": 0.23849284495208087,
+      "grad_norm": 1.157331109046936,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.0687,
+      "step": 9083
+    },
+    {
+      "epoch": 0.23930681370618354,
+      "grad_norm": 1.0788758993148804,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.0831,
+      "step": 9114
+    },
+    {
+      "epoch": 0.2401207824602862,
+      "grad_norm": 1.5682411193847656,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.066,
+      "step": 9145
+    },
+    {
+      "epoch": 0.24093475121438887,
+      "grad_norm": 1.419979453086853,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.0763,
+      "step": 9176
+    },
+    {
+      "epoch": 0.24174871996849154,
+      "grad_norm": 1.5313338041305542,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.0613,
+      "step": 9207
+    },
+    {
+      "epoch": 0.2425626887225942,
+      "grad_norm": 1.2968827486038208,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.0754,
+      "step": 9238
+    },
+    {
+      "epoch": 0.24337665747669687,
+      "grad_norm": 1.365473985671997,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.0791,
+      "step": 9269
+    },
+    {
+      "epoch": 0.24419062623079954,
+      "grad_norm": 1.4556167125701904,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.07,
+      "step": 9300
+    },
+    {
+      "epoch": 0.24500459498490218,
+      "grad_norm": 1.1634196043014526,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.0677,
+      "step": 9331
+    },
+    {
+      "epoch": 0.24581856373900485,
+      "grad_norm": 1.330187439918518,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.0704,
+      "step": 9362
+    },
+    {
+      "epoch": 0.24663253249310751,
+      "grad_norm": 1.2695295810699463,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.078,
+      "step": 9393
+    },
+    {
+      "epoch": 0.24744650124721018,
+      "grad_norm": 1.2025364637374878,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.0651,
+      "step": 9424
+    },
+    {
+      "epoch": 0.24826047000131285,
+      "grad_norm": 1.2230535745620728,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.0808,
+      "step": 9455
+    },
+    {
+      "epoch": 0.24907443875541552,
+      "grad_norm": 1.506484866142273,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.0683,
+      "step": 9486
+    },
+    {
+      "epoch": 0.24988840750951818,
+      "grad_norm": 1.1423263549804688,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.071,
+      "step": 9517
+    },
+    {
+      "epoch": 0.25070237626362085,
+      "grad_norm": 1.5298495292663574,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.0708,
+      "step": 9548
+    },
+    {
+      "epoch": 0.2515163450177235,
+      "grad_norm": 1.2905675172805786,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.0716,
+      "step": 9579
+    },
+    {
+      "epoch": 0.2523303137718262,
+      "grad_norm": 1.434274673461914,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.0741,
+      "step": 9610
+    },
+    {
+      "epoch": 0.25314428252592885,
+      "grad_norm": 1.038212776184082,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.0614,
+      "step": 9641
+    },
+    {
+      "epoch": 0.2539582512800315,
+      "grad_norm": 1.6105865240097046,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.0591,
+      "step": 9672
+    },
+    {
+      "epoch": 0.2547722200341342,
+      "grad_norm": 1.4211845397949219,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.0698,
+      "step": 9703
+    },
+    {
+      "epoch": 0.25558618878823686,
+      "grad_norm": 1.242308497428894,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.0616,
+      "step": 9734
+    },
+    {
+      "epoch": 0.2564001575423395,
+      "grad_norm": 1.3395428657531738,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.0808,
+      "step": 9765
+    },
+    {
+      "epoch": 0.2572141262964422,
+      "grad_norm": 1.1953140497207642,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.0774,
+      "step": 9796
+    },
+    {
+      "epoch": 0.25802809505054486,
+      "grad_norm": 1.149362325668335,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.0643,
+      "step": 9827
+    },
+    {
+      "epoch": 0.2588420638046475,
+      "grad_norm": 1.892229676246643,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.0743,
+      "step": 9858
+    },
+    {
+      "epoch": 0.25965603255875014,
+      "grad_norm": 1.41962468624115,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.0769,
+      "step": 9889
+    },
+    {
+      "epoch": 0.2604700013128528,
+      "grad_norm": 1.3629595041275024,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.0765,
+      "step": 9920
+    },
+    {
+      "epoch": 0.2612839700669555,
+      "grad_norm": 1.670115351676941,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.0691,
+      "step": 9951
+    },
+    {
+      "epoch": 0.26209793882105814,
+      "grad_norm": 2.000357151031494,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.054,
+      "step": 9982
+    },
+    {
+      "epoch": 0.2629119075751608,
+      "grad_norm": 2.0412051677703857,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.0601,
+      "step": 10013
+    },
+    {
+      "epoch": 0.2637258763292635,
+      "grad_norm": 1.3711960315704346,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.06,
+      "step": 10044
+    },
+    {
+      "epoch": 0.26453984508336614,
+      "grad_norm": 1.7754977941513062,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.0619,
+      "step": 10075
+    },
+    {
+      "epoch": 0.2653538138374688,
+      "grad_norm": 1.3407222032546997,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.0609,
+      "step": 10106
+    },
+    {
+      "epoch": 0.2661677825915715,
+      "grad_norm": 1.2290297746658325,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.0563,
+      "step": 10137
+    },
+    {
+      "epoch": 0.26698175134567415,
+      "grad_norm": 3.2722887992858887,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.052,
+      "step": 10168
+    },
+    {
+      "epoch": 0.2677957200997768,
+      "grad_norm": 1.2119083404541016,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.0614,
+      "step": 10199
+    },
+    {
+      "epoch": 0.2686096888538795,
+      "grad_norm": 1.3571163415908813,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.0622,
+      "step": 10230
+    },
+    {
+      "epoch": 0.26942365760798215,
+      "grad_norm": 1.3679335117340088,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.0582,
+      "step": 10261
+    },
+    {
+      "epoch": 0.2702376263620848,
+      "grad_norm": 1.6836955547332764,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.0594,
+      "step": 10292
+    },
+    {
+      "epoch": 0.2710515951161875,
+      "grad_norm": 1.04588782787323,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.0605,
+      "step": 10323
+    },
+    {
+      "epoch": 0.27186556387029015,
+      "grad_norm": 1.5175026655197144,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.0544,
+      "step": 10354
+    },
+    {
+      "epoch": 0.2726795326243928,
+      "grad_norm": 1.294839859008789,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.0568,
+      "step": 10385
+    },
+    {
+      "epoch": 0.2734935013784955,
+      "grad_norm": 1.378948450088501,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.0664,
+      "step": 10416
+    },
+    {
+      "epoch": 0.27430747013259815,
+      "grad_norm": 1.264730453491211,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.0487,
+      "step": 10447
+    },
+    {
+      "epoch": 0.2751214388867008,
+      "grad_norm": 1.3794598579406738,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.0728,
+      "step": 10478
+    },
+    {
+      "epoch": 0.2759354076408035,
+      "grad_norm": 1.2001047134399414,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.0555,
+      "step": 10509
+    },
+    {
+      "epoch": 0.27674937639490615,
+      "grad_norm": 1.4941588640213013,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.0639,
+      "step": 10540
+    },
+    {
+      "epoch": 0.2775633451490088,
+      "grad_norm": 1.7082380056381226,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.0552,
+      "step": 10571
+    },
+    {
+      "epoch": 0.27837731390311143,
+      "grad_norm": 1.3252317905426025,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.0664,
+      "step": 10602
+    },
+    {
+      "epoch": 0.2791912826572141,
+      "grad_norm": 1.2412651777267456,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.0703,
+      "step": 10633
+    },
+    {
+      "epoch": 0.28000525141131677,
+      "grad_norm": 1.388967752456665,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.0678,
+      "step": 10664
+    },
+    {
+      "epoch": 0.28081922016541944,
+      "grad_norm": 1.393232822418213,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.0698,
+      "step": 10695
+    },
+    {
+      "epoch": 0.2816331889195221,
+      "grad_norm": 1.1924173831939697,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.0545,
+      "step": 10726
+    },
+    {
+      "epoch": 0.28244715767362477,
+      "grad_norm": 1.5071165561676025,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.0557,
+      "step": 10757
+    },
+    {
+      "epoch": 0.28326112642772744,
+      "grad_norm": 1.4572780132293701,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.0552,
+      "step": 10788
+    },
+    {
+      "epoch": 0.2840750951818301,
+      "grad_norm": 1.1776372194290161,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.0503,
+      "step": 10819
+    },
+    {
+      "epoch": 0.2848890639359328,
+      "grad_norm": 1.3957065343856812,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.0515,
+      "step": 10850
+    },
+    {
+      "epoch": 0.28570303269003544,
+      "grad_norm": 1.3888555765151978,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.0555,
+      "step": 10881
+    },
+    {
+      "epoch": 0.2865170014441381,
+      "grad_norm": 1.5020958185195923,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.0615,
+      "step": 10912
+    },
+    {
+      "epoch": 0.2873309701982408,
+      "grad_norm": 1.4686287641525269,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.0651,
+      "step": 10943
+    },
+    {
+      "epoch": 0.28814493895234344,
+      "grad_norm": 2.4933149814605713,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.0537,
+      "step": 10974
+    },
+    {
+      "epoch": 0.2889589077064461,
+      "grad_norm": 1.4286261796951294,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.0581,
+      "step": 11005
+    },
+    {
+      "epoch": 0.2897728764605488,
+      "grad_norm": 1.467076301574707,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.05,
+      "step": 11036
+    },
+    {
+      "epoch": 0.29058684521465145,
+      "grad_norm": 1.2770767211914062,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.07,
+      "step": 11067
+    },
+    {
+      "epoch": 0.2914008139687541,
+      "grad_norm": 1.5246391296386719,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.0519,
+      "step": 11098
+    },
+    {
+      "epoch": 0.2922147827228568,
+      "grad_norm": 1.4184919595718384,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.0574,
+      "step": 11129
+    },
+    {
+      "epoch": 0.29302875147695945,
+      "grad_norm": 1.3131129741668701,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.0528,
+      "step": 11160
+    },
+    {
+      "epoch": 0.2938427202310621,
+      "grad_norm": 1.3122843503952026,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.0437,
+      "step": 11191
+    },
+    {
+      "epoch": 0.2946566889851648,
+      "grad_norm": 1.2273770570755005,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.057,
+      "step": 11222
+    },
+    {
+      "epoch": 0.29547065773926745,
+      "grad_norm": 1.33588445186615,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.0626,
+      "step": 11253
+    },
+    {
+      "epoch": 0.2962846264933701,
+      "grad_norm": 1.402394413948059,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.0592,
+      "step": 11284
+    },
+    {
+      "epoch": 0.2970985952474728,
+      "grad_norm": 1.3858364820480347,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.0511,
+      "step": 11315
+    },
+    {
+      "epoch": 0.2979125640015754,
+      "grad_norm": 1.2623993158340454,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.0579,
+      "step": 11346
+    },
+    {
+      "epoch": 0.29872653275567806,
+      "grad_norm": 1.7344574928283691,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.0525,
+      "step": 11377
+    },
+    {
+      "epoch": 0.29954050150978073,
+      "grad_norm": 1.317647933959961,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.0418,
+      "step": 11408
+    },
+    {
+      "epoch": 0.3003544702638834,
+      "grad_norm": 1.2395405769348145,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.0562,
+      "step": 11439
+    },
+    {
+      "epoch": 0.30116843901798607,
+      "grad_norm": 1.3758254051208496,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.0437,
+      "step": 11470
+    },
+    {
+      "epoch": 0.30198240777208873,
+      "grad_norm": 1.1999878883361816,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.0624,
+      "step": 11501
+    },
+    {
+      "epoch": 0.3027963765261914,
+      "grad_norm": 1.1281747817993164,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.05,
+      "step": 11532
+    },
+    {
+      "epoch": 0.30361034528029407,
+      "grad_norm": 1.3711642026901245,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.0417,
+      "step": 11563
+    },
+    {
+      "epoch": 0.30442431403439674,
+      "grad_norm": 1.4176310300827026,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.06,
+      "step": 11594
+    },
+    {
+      "epoch": 0.3052382827884994,
+      "grad_norm": 1.2043743133544922,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.0422,
+      "step": 11625
+    },
+    {
+      "epoch": 0.30605225154260207,
+      "grad_norm": 1.1716021299362183,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.0501,
+      "step": 11656
+    },
+    {
+      "epoch": 0.30686622029670474,
+      "grad_norm": 1.0683443546295166,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.0534,
+      "step": 11687
+    },
+    {
+      "epoch": 0.3076801890508074,
+      "grad_norm": 1.3755611181259155,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.0557,
+      "step": 11718
+    },
+    {
+      "epoch": 0.3084941578049101,
+      "grad_norm": 1.4390757083892822,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.0442,
+      "step": 11749
+    },
+    {
+      "epoch": 0.30930812655901274,
+      "grad_norm": 1.8701292276382446,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.0518,
+      "step": 11780
+    },
+    {
+      "epoch": 0.3101220953131154,
+      "grad_norm": 1.2634522914886475,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.0467,
+      "step": 11811
+    },
+    {
+      "epoch": 0.3109360640672181,
+      "grad_norm": 1.398391604423523,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.0525,
+      "step": 11842
+    },
+    {
+      "epoch": 0.31175003282132074,
+      "grad_norm": 1.226790428161621,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.0598,
+      "step": 11873
+    },
+    {
+      "epoch": 0.3125640015754234,
+      "grad_norm": 1.2871681451797485,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.0533,
+      "step": 11904
+    },
+    {
+      "epoch": 0.3133779703295261,
+      "grad_norm": 1.2870562076568604,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.0386,
+      "step": 11935
+    },
+    {
+      "epoch": 0.31419193908362875,
+      "grad_norm": 1.6357537508010864,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.0433,
+      "step": 11966
+    },
+    {
+      "epoch": 0.3150059078377314,
+      "grad_norm": 1.455797791481018,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.0486,
+      "step": 11997
+    },
+    {
+      "epoch": 0.3158198765918341,
+      "grad_norm": 1.4254469871520996,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.0397,
+      "step": 12028
+    },
+    {
+      "epoch": 0.3166338453459367,
+      "grad_norm": 1.1427268981933594,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.0471,
+      "step": 12059
+    },
+    {
+      "epoch": 0.31744781410003936,
+      "grad_norm": 1.4286659955978394,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.0422,
+      "step": 12090
+    },
+    {
+      "epoch": 0.31826178285414203,
+      "grad_norm": 1.167340636253357,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.0453,
+      "step": 12121
+    },
+    {
+      "epoch": 0.3190757516082447,
+      "grad_norm": 1.3806867599487305,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.0388,
+      "step": 12152
+    },
+    {
+      "epoch": 0.31988972036234736,
+      "grad_norm": 1.1291500329971313,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.0367,
+      "step": 12183
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.48541631240156e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4603817deb4fe9dbf9231c537a49054e10822b91664f8a6b53bf4ff6aba3ab1b
+size 5304

checkpoint-15260/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": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-15260/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": "4.44.0.dev0"
+}

checkpoint-15260/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb330efdb910771786336aea038035accaf5519fe8ee58e2d60dfe39a16ffe1
+size 4976687216

checkpoint-15260/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb205482e80b5d03e63693e387d459b0cb9c97948cde971ff025ba98f1396d
+size 4778622352

checkpoint-15260/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222b40c6fea7def1d5911b059ab36bf97b9328e0251689f78a0a9ebd98cd18d
+size 4932743960

checkpoint-15260/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-15260/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-15260/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32acc49fa5945a9af53c40918b23740a99279ef058426558ad7b65ded61fde33
+size 3662865184

checkpoint-15260/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfb073d41c3e4360af93c5be49c9ae39037264c7eebbea1ff648bd8214e3441
+size 2179989632

checkpoint-15260/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-15260/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c62cb9a830ce6c1ecc71b742d6d5eceba1bd5f3d685279a9c64adbde76a52d
+size 16177880918

checkpoint-15260/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-15260/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce335347efaebf038b8915bc0a8d2d587a4a1aa08ad0e015b4bc7cc4fba634e
+size 1064

checkpoint-15260/trainer_state.json

@@ -0,0 +1,3477 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.40068268347118285,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008139687541026651,
+      "grad_norm": 4.344635963439941,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 2.2692,
+      "step": 31
+    },
+    {
+      "epoch": 0.0016279375082053301,
+      "grad_norm": 3.368666648864746,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 2.1052,
+      "step": 62
+    },
+    {
+      "epoch": 0.0024419062623079954,
+      "grad_norm": 2.7267792224884033,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.9706,
+      "step": 93
+    },
+    {
+      "epoch": 0.0032558750164106602,
+      "grad_norm": 2.7047057151794434,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.8885,
+      "step": 124
+    },
+    {
+      "epoch": 0.004069843770513325,
+      "grad_norm": 3.3375585079193115,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.8478,
+      "step": 155
+    },
+    {
+      "epoch": 0.004883812524615991,
+      "grad_norm": 3.4933056831359863,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.7963,
+      "step": 186
+    },
+    {
+      "epoch": 0.005697781278718656,
+      "grad_norm": 3.0248019695281982,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.7574,
+      "step": 217
+    },
+    {
+      "epoch": 0.0065117500328213205,
+      "grad_norm": 4.682138442993164,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.7395,
+      "step": 248
+    },
+    {
+      "epoch": 0.007325718786923986,
+      "grad_norm": 3.119105815887451,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.6976,
+      "step": 279
+    },
+    {
+      "epoch": 0.00813968754102665,
+      "grad_norm": 3.5156071186065674,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.674,
+      "step": 310
+    },
+    {
+      "epoch": 0.008953656295129316,
+      "grad_norm": 4.706497669219971,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.6624,
+      "step": 341
+    },
+    {
+      "epoch": 0.009767625049231982,
+      "grad_norm": 3.1241273880004883,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.6397,
+      "step": 372
+    },
+    {
+      "epoch": 0.010581593803334646,
+      "grad_norm": 3.151201009750366,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.6188,
+      "step": 403
+    },
+    {
+      "epoch": 0.011395562557437311,
+      "grad_norm": 3.722181797027588,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 1.611,
+      "step": 434
+    },
+    {
+      "epoch": 0.012209531311539977,
+      "grad_norm": 3.824608087539673,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 1.586,
+      "step": 465
+    },
+    {
+      "epoch": 0.013023500065642641,
+      "grad_norm": 3.6900010108947754,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 1.587,
+      "step": 496
+    },
+    {
+      "epoch": 0.013837468819745307,
+      "grad_norm": 2.8361997604370117,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 1.5588,
+      "step": 527
+    },
+    {
+      "epoch": 0.014651437573847972,
+      "grad_norm": 3.0725274085998535,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 1.5444,
+      "step": 558
+    },
+    {
+      "epoch": 0.015465406327950636,
+      "grad_norm": 3.16789174079895,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 1.5263,
+      "step": 589
+    },
+    {
+      "epoch": 0.0162793750820533,
+      "grad_norm": 3.24831485748291,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 1.5183,
+      "step": 620
+    },
+    {
+      "epoch": 0.017093343836155968,
+      "grad_norm": 2.6746206283569336,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 1.507,
+      "step": 651
+    },
+    {
+      "epoch": 0.017907312590258632,
+      "grad_norm": 3.2530715465545654,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 1.4959,
+      "step": 682
+    },
+    {
+      "epoch": 0.018721281344361296,
+      "grad_norm": 2.9383180141448975,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 1.4917,
+      "step": 713
+    },
+    {
+      "epoch": 0.019535250098463963,
+      "grad_norm": 3.0983939170837402,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 1.4733,
+      "step": 744
+    },
+    {
+      "epoch": 0.020349218852566627,
+      "grad_norm": 2.7612287998199463,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 1.466,
+      "step": 775
+    },
+    {
+      "epoch": 0.02116318760666929,
+      "grad_norm": 3.277587890625,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 1.4632,
+      "step": 806
+    },
+    {
+      "epoch": 0.02197715636077196,
+      "grad_norm": 3.678492546081543,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 1.4451,
+      "step": 837
+    },
+    {
+      "epoch": 0.022791125114874623,
+      "grad_norm": 3.4245243072509766,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 1.4531,
+      "step": 868
+    },
+    {
+      "epoch": 0.023605093868977287,
+      "grad_norm": 2.77119517326355,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 1.4336,
+      "step": 899
+    },
+    {
+      "epoch": 0.024419062623079954,
+      "grad_norm": 4.630955696105957,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 1.428,
+      "step": 930
+    },
+    {
+      "epoch": 0.025233031377182618,
+      "grad_norm": 2.700655937194824,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 1.4258,
+      "step": 961
+    },
+    {
+      "epoch": 0.026047000131285282,
+      "grad_norm": 3.1581950187683105,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 1.416,
+      "step": 992
+    },
+    {
+      "epoch": 0.02686096888538795,
+      "grad_norm": 2.463796377182007,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 1.4104,
+      "step": 1023
+    },
+    {
+      "epoch": 0.027674937639490613,
+      "grad_norm": 3.4881789684295654,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 1.4173,
+      "step": 1054
+    },
+    {
+      "epoch": 0.028488906393593277,
+      "grad_norm": 2.7470004558563232,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 1.398,
+      "step": 1085
+    },
+    {
+      "epoch": 0.029302875147695945,
+      "grad_norm": 2.9164175987243652,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 1.3864,
+      "step": 1116
+    },
+    {
+      "epoch": 0.03011684390179861,
+      "grad_norm": 3.191851854324341,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 1.3691,
+      "step": 1147
+    },
+    {
+      "epoch": 0.030930812655901273,
+      "grad_norm": 2.9015703201293945,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 1.3716,
+      "step": 1178
+    },
+    {
+      "epoch": 0.03174478141000394,
+      "grad_norm": 2.196329116821289,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 1.3784,
+      "step": 1209
+    },
+    {
+      "epoch": 0.0325587501641066,
+      "grad_norm": 3.0216293334960938,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 1.3729,
+      "step": 1240
+    },
+    {
+      "epoch": 0.03337271891820927,
+      "grad_norm": 2.435076951980591,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 1.3602,
+      "step": 1271
+    },
+    {
+      "epoch": 0.034186687672311936,
+      "grad_norm": 2.6987342834472656,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 1.3543,
+      "step": 1302
+    },
+    {
+      "epoch": 0.035000656426414596,
+      "grad_norm": 2.6493725776672363,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 1.35,
+      "step": 1333
+    },
+    {
+      "epoch": 0.035814625180517264,
+      "grad_norm": 2.2131760120391846,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 1.3459,
+      "step": 1364
+    },
+    {
+      "epoch": 0.03662859393461993,
+      "grad_norm": 2.9322702884674072,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 1.3553,
+      "step": 1395
+    },
+    {
+      "epoch": 0.03744256268872259,
+      "grad_norm": 2.8188889026641846,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 1.3445,
+      "step": 1426
+    },
+    {
+      "epoch": 0.03825653144282526,
+      "grad_norm": 3.5980286598205566,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 1.3412,
+      "step": 1457
+    },
+    {
+      "epoch": 0.039070500196927926,
+      "grad_norm": 2.4997692108154297,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 1.3291,
+      "step": 1488
+    },
+    {
+      "epoch": 0.03988446895103059,
+      "grad_norm": 3.452521562576294,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 1.3322,
+      "step": 1519
+    },
+    {
+      "epoch": 0.040698437705133254,
+      "grad_norm": 6.19186544418335,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 1.4477,
+      "step": 1550
+    },
+    {
+      "epoch": 0.04151240645923592,
+      "grad_norm": 2.761378526687622,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 1.464,
+      "step": 1581
+    },
+    {
+      "epoch": 0.04232637521333858,
+      "grad_norm": 2.5867984294891357,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 1.3881,
+      "step": 1612
+    },
+    {
+      "epoch": 0.04314034396744125,
+      "grad_norm": 3.0545732975006104,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 1.3787,
+      "step": 1643
+    },
+    {
+      "epoch": 0.04395431272154392,
+      "grad_norm": 2.5986175537109375,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 1.348,
+      "step": 1674
+    },
+    {
+      "epoch": 0.04476828147564658,
+      "grad_norm": 4.640907287597656,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 1.339,
+      "step": 1705
+    },
+    {
+      "epoch": 0.045582250229749245,
+      "grad_norm": 2.5423412322998047,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 1.3411,
+      "step": 1736
+    },
+    {
+      "epoch": 0.04639621898385191,
+      "grad_norm": 2.46950364112854,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 1.3278,
+      "step": 1767
+    },
+    {
+      "epoch": 0.04721018773795457,
+      "grad_norm": 3.782280445098877,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 1.303,
+      "step": 1798
+    },
+    {
+      "epoch": 0.04802415649205724,
+      "grad_norm": 2.7267119884490967,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 1.3125,
+      "step": 1829
+    },
+    {
+      "epoch": 0.04883812524615991,
+      "grad_norm": 2.2012853622436523,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 1.3121,
+      "step": 1860
+    },
+    {
+      "epoch": 0.04965209400026257,
+      "grad_norm": 2.5827276706695557,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 1.285,
+      "step": 1891
+    },
+    {
+      "epoch": 0.050466062754365236,
+      "grad_norm": 2.8490679264068604,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 1.2817,
+      "step": 1922
+    },
+    {
+      "epoch": 0.0512800315084679,
+      "grad_norm": 3.1449127197265625,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 1.2844,
+      "step": 1953
+    },
+    {
+      "epoch": 0.052094000262570564,
+      "grad_norm": 2.512974739074707,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 1.2949,
+      "step": 1984
+    },
+    {
+      "epoch": 0.05290796901667323,
+      "grad_norm": 2.118725299835205,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 1.2804,
+      "step": 2015
+    },
+    {
+      "epoch": 0.0537219377707759,
+      "grad_norm": 2.0815465450286865,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 1.2694,
+      "step": 2046
+    },
+    {
+      "epoch": 0.05453590652487856,
+      "grad_norm": 1.9531530141830444,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 1.2705,
+      "step": 2077
+    },
+    {
+      "epoch": 0.05534987527898123,
+      "grad_norm": 2.194906711578369,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 1.274,
+      "step": 2108
+    },
+    {
+      "epoch": 0.056163844033083894,
+      "grad_norm": 2.4935038089752197,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 1.2668,
+      "step": 2139
+    },
+    {
+      "epoch": 0.056977812787186555,
+      "grad_norm": 2.5282671451568604,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 1.2641,
+      "step": 2170
+    },
+    {
+      "epoch": 0.05779178154128922,
+      "grad_norm": 2.0164363384246826,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.2618,
+      "step": 2201
+    },
+    {
+      "epoch": 0.05860575029539189,
+      "grad_norm": 1.9289182424545288,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.2407,
+      "step": 2232
+    },
+    {
+      "epoch": 0.05941971904949455,
+      "grad_norm": 2.9115793704986572,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 1.2555,
+      "step": 2263
+    },
+    {
+      "epoch": 0.06023368780359722,
+      "grad_norm": 1.9424489736557007,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 1.2522,
+      "step": 2294
+    },
+    {
+      "epoch": 0.061047656557699885,
+      "grad_norm": 2.2720956802368164,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 1.245,
+      "step": 2325
+    },
+    {
+      "epoch": 0.061861625311802546,
+      "grad_norm": 2.204970121383667,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 1.2554,
+      "step": 2356
+    },
+    {
+      "epoch": 0.06267559406590521,
+      "grad_norm": 1.7172690629959106,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 1.2443,
+      "step": 2387
+    },
+    {
+      "epoch": 0.06348956282000788,
+      "grad_norm": 2.3312878608703613,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 1.2506,
+      "step": 2418
+    },
+    {
+      "epoch": 0.06430353157411055,
+      "grad_norm": 1.9023312330245972,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 1.239,
+      "step": 2449
+    },
+    {
+      "epoch": 0.0651175003282132,
+      "grad_norm": 2.0047945976257324,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.236,
+      "step": 2480
+    },
+    {
+      "epoch": 0.06593146908231587,
+      "grad_norm": 2.2633707523345947,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 1.2375,
+      "step": 2511
+    },
+    {
+      "epoch": 0.06674543783641854,
+      "grad_norm": 2.812201499938965,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 1.2412,
+      "step": 2542
+    },
+    {
+      "epoch": 0.0675594065905212,
+      "grad_norm": 2.291375160217285,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.2391,
+      "step": 2573
+    },
+    {
+      "epoch": 0.06837337534462387,
+      "grad_norm": 12.856545448303223,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.2201,
+      "step": 2604
+    },
+    {
+      "epoch": 0.06918734409872654,
+      "grad_norm": 2.3172965049743652,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.2333,
+      "step": 2635
+    },
+    {
+      "epoch": 0.07000131285282919,
+      "grad_norm": 2.4617788791656494,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.2152,
+      "step": 2666
+    },
+    {
+      "epoch": 0.07081528160693186,
+      "grad_norm": 3.4079201221466064,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.2315,
+      "step": 2697
+    },
+    {
+      "epoch": 0.07162925036103453,
+      "grad_norm": 2.0874247550964355,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.2457,
+      "step": 2728
+    },
+    {
+      "epoch": 0.0724432191151372,
+      "grad_norm": 1.8917243480682373,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.2345,
+      "step": 2759
+    },
+    {
+      "epoch": 0.07325718786923986,
+      "grad_norm": 2.0507922172546387,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.2088,
+      "step": 2790
+    },
+    {
+      "epoch": 0.07407115662334253,
+      "grad_norm": 2.2421083450317383,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.2168,
+      "step": 2821
+    },
+    {
+      "epoch": 0.07488512537744518,
+      "grad_norm": 2.0551934242248535,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.2161,
+      "step": 2852
+    },
+    {
+      "epoch": 0.07569909413154785,
+      "grad_norm": 2.987886667251587,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.2026,
+      "step": 2883
+    },
+    {
+      "epoch": 0.07651306288565052,
+      "grad_norm": 1.7029023170471191,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.2241,
+      "step": 2914
+    },
+    {
+      "epoch": 0.07732703163975319,
+      "grad_norm": 2.826143503189087,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.2116,
+      "step": 2945
+    },
+    {
+      "epoch": 0.07814100039385585,
+      "grad_norm": 2.029524564743042,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.207,
+      "step": 2976
+    },
+    {
+      "epoch": 0.07895496914795852,
+      "grad_norm": 2.3787524700164795,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.2097,
+      "step": 3007
+    },
+    {
+      "epoch": 0.07976893790206117,
+      "grad_norm": 1.4938246011734009,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.2025,
+      "step": 3038
+    },
+    {
+      "epoch": 0.08058290665616384,
+      "grad_norm": 2.125171184539795,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.2106,
+      "step": 3069
+    },
+    {
+      "epoch": 0.08139687541026651,
+      "grad_norm": 2.165095329284668,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.2075,
+      "step": 3100
+    },
+    {
+      "epoch": 0.08221084416436918,
+      "grad_norm": 1.8615927696228027,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.1982,
+      "step": 3131
+    },
+    {
+      "epoch": 0.08302481291847184,
+      "grad_norm": 1.6977221965789795,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.2039,
+      "step": 3162
+    },
+    {
+      "epoch": 0.08383878167257451,
+      "grad_norm": 1.5559513568878174,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.2024,
+      "step": 3193
+    },
+    {
+      "epoch": 0.08465275042667716,
+      "grad_norm": 2.228041172027588,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.1928,
+      "step": 3224
+    },
+    {
+      "epoch": 0.08546671918077983,
+      "grad_norm": 1.6358845233917236,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.1965,
+      "step": 3255
+    },
+    {
+      "epoch": 0.0862806879348825,
+      "grad_norm": 1.8761228322982788,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.1864,
+      "step": 3286
+    },
+    {
+      "epoch": 0.08709465668898517,
+      "grad_norm": 2.3128018379211426,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.1958,
+      "step": 3317
+    },
+    {
+      "epoch": 0.08790862544308783,
+      "grad_norm": 1.9828768968582153,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.1885,
+      "step": 3348
+    },
+    {
+      "epoch": 0.08872259419719049,
+      "grad_norm": 1.9600850343704224,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.19,
+      "step": 3379
+    },
+    {
+      "epoch": 0.08953656295129316,
+      "grad_norm": 1.755077600479126,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.1939,
+      "step": 3410
+    },
+    {
+      "epoch": 0.09035053170539582,
+      "grad_norm": 2.477156400680542,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.1895,
+      "step": 3441
+    },
+    {
+      "epoch": 0.09116450045949849,
+      "grad_norm": 2.5017731189727783,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.1957,
+      "step": 3472
+    },
+    {
+      "epoch": 0.09197846921360116,
+      "grad_norm": 1.8620328903198242,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.1898,
+      "step": 3503
+    },
+    {
+      "epoch": 0.09279243796770383,
+      "grad_norm": 1.9636398553848267,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.1934,
+      "step": 3534
+    },
+    {
+      "epoch": 0.09360640672180648,
+      "grad_norm": 1.7159295082092285,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.1909,
+      "step": 3565
+    },
+    {
+      "epoch": 0.09442037547590915,
+      "grad_norm": 2.02683424949646,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.1785,
+      "step": 3596
+    },
+    {
+      "epoch": 0.09523434423001181,
+      "grad_norm": 2.09055757522583,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.1713,
+      "step": 3627
+    },
+    {
+      "epoch": 0.09604831298411448,
+      "grad_norm": 1.5010393857955933,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.1754,
+      "step": 3658
+    },
+    {
+      "epoch": 0.09686228173821715,
+      "grad_norm": 1.864301085472107,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.1808,
+      "step": 3689
+    },
+    {
+      "epoch": 0.09767625049231982,
+      "grad_norm": 1.7567156553268433,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.1648,
+      "step": 3720
+    },
+    {
+      "epoch": 0.09849021924642247,
+      "grad_norm": 1.424232006072998,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.1708,
+      "step": 3751
+    },
+    {
+      "epoch": 0.09930418800052514,
+      "grad_norm": 1.8835548162460327,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.1669,
+      "step": 3782
+    },
+    {
+      "epoch": 0.1001181567546278,
+      "grad_norm": 1.3818198442459106,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.1727,
+      "step": 3813
+    },
+    {
+      "epoch": 0.10093212550873047,
+      "grad_norm": 1.6063064336776733,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.1499,
+      "step": 3844
+    },
+    {
+      "epoch": 0.10174609426283314,
+      "grad_norm": 1.8761767148971558,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.1707,
+      "step": 3875
+    },
+    {
+      "epoch": 0.1025600630169358,
+      "grad_norm": 2.069032669067383,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.1577,
+      "step": 3906
+    },
+    {
+      "epoch": 0.10337403177103846,
+      "grad_norm": 1.6974114179611206,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.1704,
+      "step": 3937
+    },
+    {
+      "epoch": 0.10418800052514113,
+      "grad_norm": 1.4797635078430176,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.1648,
+      "step": 3968
+    },
+    {
+      "epoch": 0.1050019692792438,
+      "grad_norm": 2.3781850337982178,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.1647,
+      "step": 3999
+    },
+    {
+      "epoch": 0.10581593803334646,
+      "grad_norm": 1.6512064933776855,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.1654,
+      "step": 4030
+    },
+    {
+      "epoch": 0.10662990678744913,
+      "grad_norm": 1.760602355003357,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.1596,
+      "step": 4061
+    },
+    {
+      "epoch": 0.1074438755415518,
+      "grad_norm": 1.785792350769043,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.1493,
+      "step": 4092
+    },
+    {
+      "epoch": 0.10825784429565445,
+      "grad_norm": 2.3284568786621094,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.1732,
+      "step": 4123
+    },
+    {
+      "epoch": 0.10907181304975712,
+      "grad_norm": 1.4291197061538696,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.1605,
+      "step": 4154
+    },
+    {
+      "epoch": 0.10988578180385979,
+      "grad_norm": 2.1645402908325195,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.1576,
+      "step": 4185
+    },
+    {
+      "epoch": 0.11069975055796245,
+      "grad_norm": 2.064669609069824,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.1485,
+      "step": 4216
+    },
+    {
+      "epoch": 0.11151371931206512,
+      "grad_norm": 1.6745102405548096,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.1738,
+      "step": 4247
+    },
+    {
+      "epoch": 0.11232768806616779,
+      "grad_norm": 2.76240611076355,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.1482,
+      "step": 4278
+    },
+    {
+      "epoch": 0.11314165682027044,
+      "grad_norm": 1.3859837055206299,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.157,
+      "step": 4309
+    },
+    {
+      "epoch": 0.11395562557437311,
+      "grad_norm": 1.7919600009918213,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.1459,
+      "step": 4340
+    },
+    {
+      "epoch": 0.11476959432847578,
+      "grad_norm": 1.7550104856491089,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.1512,
+      "step": 4371
+    },
+    {
+      "epoch": 0.11558356308257844,
+      "grad_norm": 1.2225311994552612,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.1555,
+      "step": 4402
+    },
+    {
+      "epoch": 0.11639753183668111,
+      "grad_norm": 1.7609676122665405,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.1503,
+      "step": 4433
+    },
+    {
+      "epoch": 0.11721150059078378,
+      "grad_norm": 1.539068341255188,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.1517,
+      "step": 4464
+    },
+    {
+      "epoch": 0.11802546934488643,
+      "grad_norm": 1.4526177644729614,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.1533,
+      "step": 4495
+    },
+    {
+      "epoch": 0.1188394380989891,
+      "grad_norm": 1.9552894830703735,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.1647,
+      "step": 4526
+    },
+    {
+      "epoch": 0.11965340685309177,
+      "grad_norm": 1.3867082595825195,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.1412,
+      "step": 4557
+    },
+    {
+      "epoch": 0.12046737560719444,
+      "grad_norm": 1.7866445779800415,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.15,
+      "step": 4588
+    },
+    {
+      "epoch": 0.1212813443612971,
+      "grad_norm": 1.757614016532898,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.1462,
+      "step": 4619
+    },
+    {
+      "epoch": 0.12209531311539977,
+      "grad_norm": 1.644196629524231,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.1411,
+      "step": 4650
+    },
+    {
+      "epoch": 0.12290928186950242,
+      "grad_norm": 1.5721986293792725,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.153,
+      "step": 4681
+    },
+    {
+      "epoch": 0.12372325062360509,
+      "grad_norm": 1.493248462677002,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.1373,
+      "step": 4712
+    },
+    {
+      "epoch": 0.12453721937770776,
+      "grad_norm": 1.7797431945800781,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.1475,
+      "step": 4743
+    },
+    {
+      "epoch": 0.12535118813181043,
+      "grad_norm": 1.5288772583007812,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.139,
+      "step": 4774
+    },
+    {
+      "epoch": 0.1261651568859131,
+      "grad_norm": 2.1584365367889404,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.14,
+      "step": 4805
+    },
+    {
+      "epoch": 0.12697912564001576,
+      "grad_norm": 1.7980725765228271,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.1441,
+      "step": 4836
+    },
+    {
+      "epoch": 0.12779309439411843,
+      "grad_norm": 1.739778995513916,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.1402,
+      "step": 4867
+    },
+    {
+      "epoch": 0.1286070631482211,
+      "grad_norm": 1.7673060894012451,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.1313,
+      "step": 4898
+    },
+    {
+      "epoch": 0.12942103190232376,
+      "grad_norm": 1.660517930984497,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.1474,
+      "step": 4929
+    },
+    {
+      "epoch": 0.1302350006564264,
+      "grad_norm": 1.7969893217086792,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.144,
+      "step": 4960
+    },
+    {
+      "epoch": 0.13104896941052907,
+      "grad_norm": 1.5473248958587646,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.146,
+      "step": 4991
+    },
+    {
+      "epoch": 0.13186293816463174,
+      "grad_norm": 1.723632574081421,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.1527,
+      "step": 5022
+    },
+    {
+      "epoch": 0.1326769069187344,
+      "grad_norm": 1.4418350458145142,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.1308,
+      "step": 5053
+    },
+    {
+      "epoch": 0.13349087567283707,
+      "grad_norm": 1.9781032800674438,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.1358,
+      "step": 5084
+    },
+    {
+      "epoch": 0.13430484442693974,
+      "grad_norm": 1.8926130533218384,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.141,
+      "step": 5115
+    },
+    {
+      "epoch": 0.1351188131810424,
+      "grad_norm": 1.5577887296676636,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.132,
+      "step": 5146
+    },
+    {
+      "epoch": 0.13593278193514508,
+      "grad_norm": 2.112377166748047,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.1499,
+      "step": 5177
+    },
+    {
+      "epoch": 0.13674675068924774,
+      "grad_norm": 2.142568826675415,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.1488,
+      "step": 5208
+    },
+    {
+      "epoch": 0.1375607194433504,
+      "grad_norm": 1.713492751121521,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.1312,
+      "step": 5239
+    },
+    {
+      "epoch": 0.13837468819745308,
+      "grad_norm": 1.8712431192398071,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.1344,
+      "step": 5270
+    },
+    {
+      "epoch": 0.13918865695155572,
+      "grad_norm": 1.609357237815857,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.1209,
+      "step": 5301
+    },
+    {
+      "epoch": 0.14000262570565838,
+      "grad_norm": 2.1064646244049072,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.1416,
+      "step": 5332
+    },
+    {
+      "epoch": 0.14081659445976105,
+      "grad_norm": 1.4620094299316406,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.1275,
+      "step": 5363
+    },
+    {
+      "epoch": 0.14163056321386372,
+      "grad_norm": 1.32656729221344,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.1329,
+      "step": 5394
+    },
+    {
+      "epoch": 0.1424445319679664,
+      "grad_norm": 1.4479507207870483,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.1354,
+      "step": 5425
+    },
+    {
+      "epoch": 0.14325850072206905,
+      "grad_norm": 1.6729614734649658,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.1364,
+      "step": 5456
+    },
+    {
+      "epoch": 0.14407246947617172,
+      "grad_norm": 1.4260097742080688,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.1319,
+      "step": 5487
+    },
+    {
+      "epoch": 0.1448864382302744,
+      "grad_norm": 1.5216090679168701,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.1392,
+      "step": 5518
+    },
+    {
+      "epoch": 0.14570040698437706,
+      "grad_norm": 1.3038978576660156,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.1262,
+      "step": 5549
+    },
+    {
+      "epoch": 0.14651437573847972,
+      "grad_norm": 1.3285478353500366,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.1154,
+      "step": 5580
+    },
+    {
+      "epoch": 0.1473283444925824,
+      "grad_norm": 1.4460917711257935,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.1226,
+      "step": 5611
+    },
+    {
+      "epoch": 0.14814231324668506,
+      "grad_norm": 1.3280593156814575,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.1154,
+      "step": 5642
+    },
+    {
+      "epoch": 0.1489562820007877,
+      "grad_norm": 1.8312699794769287,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.126,
+      "step": 5673
+    },
+    {
+      "epoch": 0.14977025075489037,
+      "grad_norm": 2.0447463989257812,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.1274,
+      "step": 5704
+    },
+    {
+      "epoch": 0.15058421950899303,
+      "grad_norm": 1.5046786069869995,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.1097,
+      "step": 5735
+    },
+    {
+      "epoch": 0.1513981882630957,
+      "grad_norm": 1.5917468070983887,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.1219,
+      "step": 5766
+    },
+    {
+      "epoch": 0.15221215701719837,
+      "grad_norm": 1.4890860319137573,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.1307,
+      "step": 5797
+    },
+    {
+      "epoch": 0.15302612577130104,
+      "grad_norm": 1.557468056678772,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.1173,
+      "step": 5828
+    },
+    {
+      "epoch": 0.1538400945254037,
+      "grad_norm": 1.7449064254760742,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.1216,
+      "step": 5859
+    },
+    {
+      "epoch": 0.15465406327950637,
+      "grad_norm": 1.6439781188964844,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.1228,
+      "step": 5890
+    },
+    {
+      "epoch": 0.15546803203360904,
+      "grad_norm": 2.3047573566436768,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.126,
+      "step": 5921
+    },
+    {
+      "epoch": 0.1562820007877117,
+      "grad_norm": 2.0222270488739014,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.1245,
+      "step": 5952
+    },
+    {
+      "epoch": 0.15709596954181437,
+      "grad_norm": 1.5156447887420654,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.128,
+      "step": 5983
+    },
+    {
+      "epoch": 0.15790993829591704,
+      "grad_norm": 1.8281335830688477,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.12,
+      "step": 6014
+    },
+    {
+      "epoch": 0.15872390705001968,
+      "grad_norm": 1.669470191001892,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.1065,
+      "step": 6045
+    },
+    {
+      "epoch": 0.15953787580412235,
+      "grad_norm": 1.4428647756576538,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.1218,
+      "step": 6076
+    },
+    {
+      "epoch": 0.16035184455822502,
+      "grad_norm": 1.5096391439437866,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.1125,
+      "step": 6107
+    },
+    {
+      "epoch": 0.16116581331232768,
+      "grad_norm": 1.6360524892807007,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.0959,
+      "step": 6138
+    },
+    {
+      "epoch": 0.16197978206643035,
+      "grad_norm": 1.6503233909606934,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.1046,
+      "step": 6169
+    },
+    {
+      "epoch": 0.16279375082053302,
+      "grad_norm": 1.6234620809555054,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.1101,
+      "step": 6200
+    },
+    {
+      "epoch": 0.16360771957463568,
+      "grad_norm": 1.1652549505233765,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.0979,
+      "step": 6231
+    },
+    {
+      "epoch": 0.16442168832873835,
+      "grad_norm": 1.8738065958023071,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.1158,
+      "step": 6262
+    },
+    {
+      "epoch": 0.16523565708284102,
+      "grad_norm": 1.678968071937561,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.1185,
+      "step": 6293
+    },
+    {
+      "epoch": 0.1660496258369437,
+      "grad_norm": 1.4664219617843628,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.1127,
+      "step": 6324
+    },
+    {
+      "epoch": 0.16686359459104635,
+      "grad_norm": 1.463440179824829,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.1039,
+      "step": 6355
+    },
+    {
+      "epoch": 0.16767756334514902,
+      "grad_norm": 1.4472638368606567,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.1158,
+      "step": 6386
+    },
+    {
+      "epoch": 0.16849153209925166,
+      "grad_norm": 1.5634558200836182,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.1074,
+      "step": 6417
+    },
+    {
+      "epoch": 0.16930550085335433,
+      "grad_norm": 1.4016892910003662,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.0988,
+      "step": 6448
+    },
+    {
+      "epoch": 0.170119469607457,
+      "grad_norm": 1.4526346921920776,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.1032,
+      "step": 6479
+    },
+    {
+      "epoch": 0.17093343836155966,
+      "grad_norm": 1.8762003183364868,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.0924,
+      "step": 6510
+    },
+    {
+      "epoch": 0.17174740711566233,
+      "grad_norm": 1.4504212141036987,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.1182,
+      "step": 6541
+    },
+    {
+      "epoch": 0.172561375869765,
+      "grad_norm": 1.4169540405273438,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.119,
+      "step": 6572
+    },
+    {
+      "epoch": 0.17337534462386767,
+      "grad_norm": 1.9999427795410156,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.1039,
+      "step": 6603
+    },
+    {
+      "epoch": 0.17418931337797033,
+      "grad_norm": 1.826111078262329,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.1056,
+      "step": 6634
+    },
+    {
+      "epoch": 0.175003282132073,
+      "grad_norm": 1.5917997360229492,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.1131,
+      "step": 6665
+    },
+    {
+      "epoch": 0.17581725088617567,
+      "grad_norm": 1.679688811302185,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.0905,
+      "step": 6696
+    },
+    {
+      "epoch": 0.17663121964027834,
+      "grad_norm": 1.0461444854736328,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.1079,
+      "step": 6727
+    },
+    {
+      "epoch": 0.17744518839438098,
+      "grad_norm": 1.2755801677703857,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.1098,
+      "step": 6758
+    },
+    {
+      "epoch": 0.17825915714848364,
+      "grad_norm": 1.9257614612579346,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.1138,
+      "step": 6789
+    },
+    {
+      "epoch": 0.1790731259025863,
+      "grad_norm": 1.3688116073608398,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.0994,
+      "step": 6820
+    },
+    {
+      "epoch": 0.17988709465668898,
+      "grad_norm": 1.9413882493972778,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.1033,
+      "step": 6851
+    },
+    {
+      "epoch": 0.18070106341079165,
+      "grad_norm": 1.2649338245391846,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.1045,
+      "step": 6882
+    },
+    {
+      "epoch": 0.1815150321648943,
+      "grad_norm": 1.4563463926315308,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.1078,
+      "step": 6913
+    },
+    {
+      "epoch": 0.18232900091899698,
+      "grad_norm": 1.2975566387176514,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.0961,
+      "step": 6944
+    },
+    {
+      "epoch": 0.18314296967309965,
+      "grad_norm": 1.3268362283706665,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.0907,
+      "step": 6975
+    },
+    {
+      "epoch": 0.18395693842720232,
+      "grad_norm": 1.811310052871704,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.0973,
+      "step": 7006
+    },
+    {
+      "epoch": 0.18477090718130498,
+      "grad_norm": 1.5738041400909424,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.0992,
+      "step": 7037
+    },
+    {
+      "epoch": 0.18558487593540765,
+      "grad_norm": 2.2612175941467285,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.1024,
+      "step": 7068
+    },
+    {
+      "epoch": 0.18639884468951032,
+      "grad_norm": 1.7416468858718872,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.0993,
+      "step": 7099
+    },
+    {
+      "epoch": 0.18721281344361296,
+      "grad_norm": 1.358522653579712,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.1034,
+      "step": 7130
+    },
+    {
+      "epoch": 0.18802678219771563,
+      "grad_norm": 1.3705374002456665,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.093,
+      "step": 7161
+    },
+    {
+      "epoch": 0.1888407509518183,
+      "grad_norm": 1.7620149850845337,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.0948,
+      "step": 7192
+    },
+    {
+      "epoch": 0.18965471970592096,
+      "grad_norm": 1.8306667804718018,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.1016,
+      "step": 7223
+    },
+    {
+      "epoch": 0.19046868846002363,
+      "grad_norm": 1.3714003562927246,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.1016,
+      "step": 7254
+    },
+    {
+      "epoch": 0.1912826572141263,
+      "grad_norm": 1.2869197130203247,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.0924,
+      "step": 7285
+    },
+    {
+      "epoch": 0.19209662596822896,
+      "grad_norm": 1.3529052734375,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.0972,
+      "step": 7316
+    },
+    {
+      "epoch": 0.19291059472233163,
+      "grad_norm": 1.3062899112701416,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.0963,
+      "step": 7347
+    },
+    {
+      "epoch": 0.1937245634764343,
+      "grad_norm": 1.7407621145248413,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.0992,
+      "step": 7378
+    },
+    {
+      "epoch": 0.19453853223053696,
+      "grad_norm": 1.2803786993026733,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.1025,
+      "step": 7409
+    },
+    {
+      "epoch": 0.19535250098463963,
+      "grad_norm": 1.5632768869400024,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.1008,
+      "step": 7440
+    },
+    {
+      "epoch": 0.1961664697387423,
+      "grad_norm": 1.6344542503356934,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.0975,
+      "step": 7471
+    },
+    {
+      "epoch": 0.19698043849284494,
+      "grad_norm": 1.531846523284912,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.099,
+      "step": 7502
+    },
+    {
+      "epoch": 0.1977944072469476,
+      "grad_norm": 1.588841199874878,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.0874,
+      "step": 7533
+    },
+    {
+      "epoch": 0.19860837600105027,
+      "grad_norm": 1.8889760971069336,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.0909,
+      "step": 7564
+    },
+    {
+      "epoch": 0.19942234475515294,
+      "grad_norm": 1.1373437643051147,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.1004,
+      "step": 7595
+    },
+    {
+      "epoch": 0.2002363135092556,
+      "grad_norm": 1.4850921630859375,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.1033,
+      "step": 7626
+    },
+    {
+      "epoch": 0.20105028226335828,
+      "grad_norm": 2.14884090423584,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.0981,
+      "step": 7657
+    },
+    {
+      "epoch": 0.20186425101746094,
+      "grad_norm": 1.7331793308258057,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.0981,
+      "step": 7688
+    },
+    {
+      "epoch": 0.2026782197715636,
+      "grad_norm": 1.8480019569396973,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.0849,
+      "step": 7719
+    },
+    {
+      "epoch": 0.20349218852566628,
+      "grad_norm": 1.6195038557052612,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.0978,
+      "step": 7750
+    },
+    {
+      "epoch": 0.20430615727976895,
+      "grad_norm": 1.5065410137176514,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.0888,
+      "step": 7781
+    },
+    {
+      "epoch": 0.2051201260338716,
+      "grad_norm": 1.6099448204040527,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.081,
+      "step": 7812
+    },
+    {
+      "epoch": 0.20593409478797428,
+      "grad_norm": 1.7982425689697266,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.0876,
+      "step": 7843
+    },
+    {
+      "epoch": 0.20674806354207692,
+      "grad_norm": 1.864194393157959,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.093,
+      "step": 7874
+    },
+    {
+      "epoch": 0.2075620322961796,
+      "grad_norm": 1.3261879682540894,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.0927,
+      "step": 7905
+    },
+    {
+      "epoch": 0.20837600105028226,
+      "grad_norm": 1.3466005325317383,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.1003,
+      "step": 7936
+    },
+    {
+      "epoch": 0.20918996980438492,
+      "grad_norm": 1.545696496963501,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.0809,
+      "step": 7967
+    },
+    {
+      "epoch": 0.2100039385584876,
+      "grad_norm": 1.5338133573532104,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.0752,
+      "step": 7998
+    },
+    {
+      "epoch": 0.21081790731259026,
+      "grad_norm": 2.43064022064209,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.0845,
+      "step": 8029
+    },
+    {
+      "epoch": 0.21163187606669293,
+      "grad_norm": 1.5302485227584839,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.0826,
+      "step": 8060
+    },
+    {
+      "epoch": 0.2124458448207956,
+      "grad_norm": 1.8339937925338745,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.0948,
+      "step": 8091
+    },
+    {
+      "epoch": 0.21325981357489826,
+      "grad_norm": 1.9686979055404663,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.0754,
+      "step": 8122
+    },
+    {
+      "epoch": 0.21407378232900093,
+      "grad_norm": 1.540440559387207,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.0884,
+      "step": 8153
+    },
+    {
+      "epoch": 0.2148877510831036,
+      "grad_norm": 1.741109013557434,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.074,
+      "step": 8184
+    },
+    {
+      "epoch": 0.21570171983720626,
+      "grad_norm": 1.1937834024429321,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.098,
+      "step": 8215
+    },
+    {
+      "epoch": 0.2165156885913089,
+      "grad_norm": 1.762987732887268,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.0894,
+      "step": 8246
+    },
+    {
+      "epoch": 0.21732965734541157,
+      "grad_norm": 1.6183695793151855,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.0944,
+      "step": 8277
+    },
+    {
+      "epoch": 0.21814362609951424,
+      "grad_norm": 2.039792776107788,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.0832,
+      "step": 8308
+    },
+    {
+      "epoch": 0.2189575948536169,
+      "grad_norm": 1.7424120903015137,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.0765,
+      "step": 8339
+    },
+    {
+      "epoch": 0.21977156360771957,
+      "grad_norm": 1.4619733095169067,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.084,
+      "step": 8370
+    },
+    {
+      "epoch": 0.22058553236182224,
+      "grad_norm": 1.578750729560852,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.0803,
+      "step": 8401
+    },
+    {
+      "epoch": 0.2213995011159249,
+      "grad_norm": 1.5708528757095337,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.0633,
+      "step": 8432
+    },
+    {
+      "epoch": 0.22221346987002757,
+      "grad_norm": 1.1335474252700806,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.0853,
+      "step": 8463
+    },
+    {
+      "epoch": 0.22302743862413024,
+      "grad_norm": 1.2993063926696777,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.0899,
+      "step": 8494
+    },
+    {
+      "epoch": 0.2238414073782329,
+      "grad_norm": 1.2681806087493896,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.0927,
+      "step": 8525
+    },
+    {
+      "epoch": 0.22465537613233558,
+      "grad_norm": 1.8203648328781128,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.0866,
+      "step": 8556
+    },
+    {
+      "epoch": 0.22546934488643822,
+      "grad_norm": 1.5113874673843384,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.0876,
+      "step": 8587
+    },
+    {
+      "epoch": 0.22628331364054088,
+      "grad_norm": 1.6668130159378052,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.0773,
+      "step": 8618
+    },
+    {
+      "epoch": 0.22709728239464355,
+      "grad_norm": 1.9352772235870361,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.0721,
+      "step": 8649
+    },
+    {
+      "epoch": 0.22791125114874622,
+      "grad_norm": 1.4542369842529297,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.0799,
+      "step": 8680
+    },
+    {
+      "epoch": 0.2287252199028489,
+      "grad_norm": 1.529205083847046,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.082,
+      "step": 8711
+    },
+    {
+      "epoch": 0.22953918865695155,
+      "grad_norm": 1.1309294700622559,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.0755,
+      "step": 8742
+    },
+    {
+      "epoch": 0.23035315741105422,
+      "grad_norm": 1.5995324850082397,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.0926,
+      "step": 8773
+    },
+    {
+      "epoch": 0.2311671261651569,
+      "grad_norm": 1.6205707788467407,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.0739,
+      "step": 8804
+    },
+    {
+      "epoch": 0.23198109491925956,
+      "grad_norm": 1.2695502042770386,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.0732,
+      "step": 8835
+    },
+    {
+      "epoch": 0.23279506367336222,
+      "grad_norm": 1.1835676431655884,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.0784,
+      "step": 8866
+    },
+    {
+      "epoch": 0.2336090324274649,
+      "grad_norm": 1.8403820991516113,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.0697,
+      "step": 8897
+    },
+    {
+      "epoch": 0.23442300118156756,
+      "grad_norm": 1.5087056159973145,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.0807,
+      "step": 8928
+    },
+    {
+      "epoch": 0.2352369699356702,
+      "grad_norm": 2.1309752464294434,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.0693,
+      "step": 8959
+    },
+    {
+      "epoch": 0.23605093868977287,
+      "grad_norm": 1.253975749015808,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.0602,
+      "step": 8990
+    },
+    {
+      "epoch": 0.23686490744387553,
+      "grad_norm": 1.1763646602630615,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.0879,
+      "step": 9021
+    },
+    {
+      "epoch": 0.2376788761979782,
+      "grad_norm": 1.3210095167160034,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.0731,
+      "step": 9052
+    },
+    {
+      "epoch": 0.23849284495208087,
+      "grad_norm": 1.157331109046936,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.0687,
+      "step": 9083
+    },
+    {
+      "epoch": 0.23930681370618354,
+      "grad_norm": 1.0788758993148804,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.0831,
+      "step": 9114
+    },
+    {
+      "epoch": 0.2401207824602862,
+      "grad_norm": 1.5682411193847656,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.066,
+      "step": 9145
+    },
+    {
+      "epoch": 0.24093475121438887,
+      "grad_norm": 1.419979453086853,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.0763,
+      "step": 9176
+    },
+    {
+      "epoch": 0.24174871996849154,
+      "grad_norm": 1.5313338041305542,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.0613,
+      "step": 9207
+    },
+    {
+      "epoch": 0.2425626887225942,
+      "grad_norm": 1.2968827486038208,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.0754,
+      "step": 9238
+    },
+    {
+      "epoch": 0.24337665747669687,
+      "grad_norm": 1.365473985671997,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.0791,
+      "step": 9269
+    },
+    {
+      "epoch": 0.24419062623079954,
+      "grad_norm": 1.4556167125701904,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.07,
+      "step": 9300
+    },
+    {
+      "epoch": 0.24500459498490218,
+      "grad_norm": 1.1634196043014526,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.0677,
+      "step": 9331
+    },
+    {
+      "epoch": 0.24581856373900485,
+      "grad_norm": 1.330187439918518,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.0704,
+      "step": 9362
+    },
+    {
+      "epoch": 0.24663253249310751,
+      "grad_norm": 1.2695295810699463,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.078,
+      "step": 9393
+    },
+    {
+      "epoch": 0.24744650124721018,
+      "grad_norm": 1.2025364637374878,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.0651,
+      "step": 9424
+    },
+    {
+      "epoch": 0.24826047000131285,
+      "grad_norm": 1.2230535745620728,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.0808,
+      "step": 9455
+    },
+    {
+      "epoch": 0.24907443875541552,
+      "grad_norm": 1.506484866142273,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.0683,
+      "step": 9486
+    },
+    {
+      "epoch": 0.24988840750951818,
+      "grad_norm": 1.1423263549804688,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.071,
+      "step": 9517
+    },
+    {
+      "epoch": 0.25070237626362085,
+      "grad_norm": 1.5298495292663574,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.0708,
+      "step": 9548
+    },
+    {
+      "epoch": 0.2515163450177235,
+      "grad_norm": 1.2905675172805786,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.0716,
+      "step": 9579
+    },
+    {
+      "epoch": 0.2523303137718262,
+      "grad_norm": 1.434274673461914,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.0741,
+      "step": 9610
+    },
+    {
+      "epoch": 0.25314428252592885,
+      "grad_norm": 1.038212776184082,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.0614,
+      "step": 9641
+    },
+    {
+      "epoch": 0.2539582512800315,
+      "grad_norm": 1.6105865240097046,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.0591,
+      "step": 9672
+    },
+    {
+      "epoch": 0.2547722200341342,
+      "grad_norm": 1.4211845397949219,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.0698,
+      "step": 9703
+    },
+    {
+      "epoch": 0.25558618878823686,
+      "grad_norm": 1.242308497428894,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.0616,
+      "step": 9734
+    },
+    {
+      "epoch": 0.2564001575423395,
+      "grad_norm": 1.3395428657531738,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.0808,
+      "step": 9765
+    },
+    {
+      "epoch": 0.2572141262964422,
+      "grad_norm": 1.1953140497207642,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.0774,
+      "step": 9796
+    },
+    {
+      "epoch": 0.25802809505054486,
+      "grad_norm": 1.149362325668335,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.0643,
+      "step": 9827
+    },
+    {
+      "epoch": 0.2588420638046475,
+      "grad_norm": 1.892229676246643,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.0743,
+      "step": 9858
+    },
+    {
+      "epoch": 0.25965603255875014,
+      "grad_norm": 1.41962468624115,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.0769,
+      "step": 9889
+    },
+    {
+      "epoch": 0.2604700013128528,
+      "grad_norm": 1.3629595041275024,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.0765,
+      "step": 9920
+    },
+    {
+      "epoch": 0.2612839700669555,
+      "grad_norm": 1.670115351676941,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.0691,
+      "step": 9951
+    },
+    {
+      "epoch": 0.26209793882105814,
+      "grad_norm": 2.000357151031494,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.054,
+      "step": 9982
+    },
+    {
+      "epoch": 0.2629119075751608,
+      "grad_norm": 2.0412051677703857,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.0601,
+      "step": 10013
+    },
+    {
+      "epoch": 0.2637258763292635,
+      "grad_norm": 1.3711960315704346,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.06,
+      "step": 10044
+    },
+    {
+      "epoch": 0.26453984508336614,
+      "grad_norm": 1.7754977941513062,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.0619,
+      "step": 10075
+    },
+    {
+      "epoch": 0.2653538138374688,
+      "grad_norm": 1.3407222032546997,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.0609,
+      "step": 10106
+    },
+    {
+      "epoch": 0.2661677825915715,
+      "grad_norm": 1.2290297746658325,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.0563,
+      "step": 10137
+    },
+    {
+      "epoch": 0.26698175134567415,
+      "grad_norm": 3.2722887992858887,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.052,
+      "step": 10168
+    },
+    {
+      "epoch": 0.2677957200997768,
+      "grad_norm": 1.2119083404541016,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.0614,
+      "step": 10199
+    },
+    {
+      "epoch": 0.2686096888538795,
+      "grad_norm": 1.3571163415908813,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.0622,
+      "step": 10230
+    },
+    {
+      "epoch": 0.26942365760798215,
+      "grad_norm": 1.3679335117340088,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.0582,
+      "step": 10261
+    },
+    {
+      "epoch": 0.2702376263620848,
+      "grad_norm": 1.6836955547332764,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.0594,
+      "step": 10292
+    },
+    {
+      "epoch": 0.2710515951161875,
+      "grad_norm": 1.04588782787323,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.0605,
+      "step": 10323
+    },
+    {
+      "epoch": 0.27186556387029015,
+      "grad_norm": 1.5175026655197144,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.0544,
+      "step": 10354
+    },
+    {
+      "epoch": 0.2726795326243928,
+      "grad_norm": 1.294839859008789,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.0568,
+      "step": 10385
+    },
+    {
+      "epoch": 0.2734935013784955,
+      "grad_norm": 1.378948450088501,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.0664,
+      "step": 10416
+    },
+    {
+      "epoch": 0.27430747013259815,
+      "grad_norm": 1.264730453491211,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.0487,
+      "step": 10447
+    },
+    {
+      "epoch": 0.2751214388867008,
+      "grad_norm": 1.3794598579406738,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.0728,
+      "step": 10478
+    },
+    {
+      "epoch": 0.2759354076408035,
+      "grad_norm": 1.2001047134399414,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.0555,
+      "step": 10509
+    },
+    {
+      "epoch": 0.27674937639490615,
+      "grad_norm": 1.4941588640213013,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.0639,
+      "step": 10540
+    },
+    {
+      "epoch": 0.2775633451490088,
+      "grad_norm": 1.7082380056381226,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.0552,
+      "step": 10571
+    },
+    {
+      "epoch": 0.27837731390311143,
+      "grad_norm": 1.3252317905426025,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.0664,
+      "step": 10602
+    },
+    {
+      "epoch": 0.2791912826572141,
+      "grad_norm": 1.2412651777267456,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.0703,
+      "step": 10633
+    },
+    {
+      "epoch": 0.28000525141131677,
+      "grad_norm": 1.388967752456665,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.0678,
+      "step": 10664
+    },
+    {
+      "epoch": 0.28081922016541944,
+      "grad_norm": 1.393232822418213,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.0698,
+      "step": 10695
+    },
+    {
+      "epoch": 0.2816331889195221,
+      "grad_norm": 1.1924173831939697,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.0545,
+      "step": 10726
+    },
+    {
+      "epoch": 0.28244715767362477,
+      "grad_norm": 1.5071165561676025,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.0557,
+      "step": 10757
+    },
+    {
+      "epoch": 0.28326112642772744,
+      "grad_norm": 1.4572780132293701,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.0552,
+      "step": 10788
+    },
+    {
+      "epoch": 0.2840750951818301,
+      "grad_norm": 1.1776372194290161,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.0503,
+      "step": 10819
+    },
+    {
+      "epoch": 0.2848890639359328,
+      "grad_norm": 1.3957065343856812,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.0515,
+      "step": 10850
+    },
+    {
+      "epoch": 0.28570303269003544,
+      "grad_norm": 1.3888555765151978,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.0555,
+      "step": 10881
+    },
+    {
+      "epoch": 0.2865170014441381,
+      "grad_norm": 1.5020958185195923,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.0615,
+      "step": 10912
+    },
+    {
+      "epoch": 0.2873309701982408,
+      "grad_norm": 1.4686287641525269,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.0651,
+      "step": 10943
+    },
+    {
+      "epoch": 0.28814493895234344,
+      "grad_norm": 2.4933149814605713,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.0537,
+      "step": 10974
+    },
+    {
+      "epoch": 0.2889589077064461,
+      "grad_norm": 1.4286261796951294,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.0581,
+      "step": 11005
+    },
+    {
+      "epoch": 0.2897728764605488,
+      "grad_norm": 1.467076301574707,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.05,
+      "step": 11036
+    },
+    {
+      "epoch": 0.29058684521465145,
+      "grad_norm": 1.2770767211914062,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.07,
+      "step": 11067
+    },
+    {
+      "epoch": 0.2914008139687541,
+      "grad_norm": 1.5246391296386719,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.0519,
+      "step": 11098
+    },
+    {
+      "epoch": 0.2922147827228568,
+      "grad_norm": 1.4184919595718384,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.0574,
+      "step": 11129
+    },
+    {
+      "epoch": 0.29302875147695945,
+      "grad_norm": 1.3131129741668701,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.0528,
+      "step": 11160
+    },
+    {
+      "epoch": 0.2938427202310621,
+      "grad_norm": 1.3122843503952026,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.0437,
+      "step": 11191
+    },
+    {
+      "epoch": 0.2946566889851648,
+      "grad_norm": 1.2273770570755005,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.057,
+      "step": 11222
+    },
+    {
+      "epoch": 0.29547065773926745,
+      "grad_norm": 1.33588445186615,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.0626,
+      "step": 11253
+    },
+    {
+      "epoch": 0.2962846264933701,
+      "grad_norm": 1.402394413948059,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.0592,
+      "step": 11284
+    },
+    {
+      "epoch": 0.2970985952474728,
+      "grad_norm": 1.3858364820480347,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.0511,
+      "step": 11315
+    },
+    {
+      "epoch": 0.2979125640015754,
+      "grad_norm": 1.2623993158340454,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.0579,
+      "step": 11346
+    },
+    {
+      "epoch": 0.29872653275567806,
+      "grad_norm": 1.7344574928283691,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.0525,
+      "step": 11377
+    },
+    {
+      "epoch": 0.29954050150978073,
+      "grad_norm": 1.317647933959961,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.0418,
+      "step": 11408
+    },
+    {
+      "epoch": 0.3003544702638834,
+      "grad_norm": 1.2395405769348145,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.0562,
+      "step": 11439
+    },
+    {
+      "epoch": 0.30116843901798607,
+      "grad_norm": 1.3758254051208496,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.0437,
+      "step": 11470
+    },
+    {
+      "epoch": 0.30198240777208873,
+      "grad_norm": 1.1999878883361816,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.0624,
+      "step": 11501
+    },
+    {
+      "epoch": 0.3027963765261914,
+      "grad_norm": 1.1281747817993164,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.05,
+      "step": 11532
+    },
+    {
+      "epoch": 0.30361034528029407,
+      "grad_norm": 1.3711642026901245,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.0417,
+      "step": 11563
+    },
+    {
+      "epoch": 0.30442431403439674,
+      "grad_norm": 1.4176310300827026,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.06,
+      "step": 11594
+    },
+    {
+      "epoch": 0.3052382827884994,
+      "grad_norm": 1.2043743133544922,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.0422,
+      "step": 11625
+    },
+    {
+      "epoch": 0.30605225154260207,
+      "grad_norm": 1.1716021299362183,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.0501,
+      "step": 11656
+    },
+    {
+      "epoch": 0.30686622029670474,
+      "grad_norm": 1.0683443546295166,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.0534,
+      "step": 11687
+    },
+    {
+      "epoch": 0.3076801890508074,
+      "grad_norm": 1.3755611181259155,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.0557,
+      "step": 11718
+    },
+    {
+      "epoch": 0.3084941578049101,
+      "grad_norm": 1.4390757083892822,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.0442,
+      "step": 11749
+    },
+    {
+      "epoch": 0.30930812655901274,
+      "grad_norm": 1.8701292276382446,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.0518,
+      "step": 11780
+    },
+    {
+      "epoch": 0.3101220953131154,
+      "grad_norm": 1.2634522914886475,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.0467,
+      "step": 11811
+    },
+    {
+      "epoch": 0.3109360640672181,
+      "grad_norm": 1.398391604423523,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.0525,
+      "step": 11842
+    },
+    {
+      "epoch": 0.31175003282132074,
+      "grad_norm": 1.226790428161621,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.0598,
+      "step": 11873
+    },
+    {
+      "epoch": 0.3125640015754234,
+      "grad_norm": 1.2871681451797485,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.0533,
+      "step": 11904
+    },
+    {
+      "epoch": 0.3133779703295261,
+      "grad_norm": 1.2870562076568604,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.0386,
+      "step": 11935
+    },
+    {
+      "epoch": 0.31419193908362875,
+      "grad_norm": 1.6357537508010864,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.0433,
+      "step": 11966
+    },
+    {
+      "epoch": 0.3150059078377314,
+      "grad_norm": 1.455797791481018,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.0486,
+      "step": 11997
+    },
+    {
+      "epoch": 0.3158198765918341,
+      "grad_norm": 1.4254469871520996,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.0397,
+      "step": 12028
+    },
+    {
+      "epoch": 0.3166338453459367,
+      "grad_norm": 1.1427268981933594,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.0471,
+      "step": 12059
+    },
+    {
+      "epoch": 0.31744781410003936,
+      "grad_norm": 1.4286659955978394,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.0422,
+      "step": 12090
+    },
+    {
+      "epoch": 0.31826178285414203,
+      "grad_norm": 1.167340636253357,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.0453,
+      "step": 12121
+    },
+    {
+      "epoch": 0.3190757516082447,
+      "grad_norm": 1.3806867599487305,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.0388,
+      "step": 12152
+    },
+    {
+      "epoch": 0.31988972036234736,
+      "grad_norm": 1.1291500329971313,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.0367,
+      "step": 12183
+    },
+    {
+      "epoch": 0.32070368911645003,
+      "grad_norm": 1.122763752937317,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 1.0338,
+      "step": 12214
+    },
+    {
+      "epoch": 0.3215176578705527,
+      "grad_norm": 1.316038966178894,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 1.0554,
+      "step": 12245
+    },
+    {
+      "epoch": 0.32233162662465537,
+      "grad_norm": 1.1073695421218872,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 1.0521,
+      "step": 12276
+    },
+    {
+      "epoch": 0.32314559537875803,
+      "grad_norm": 1.3001607656478882,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 1.0454,
+      "step": 12307
+    },
+    {
+      "epoch": 0.3239595641328607,
+      "grad_norm": 1.4280298948287964,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 1.0408,
+      "step": 12338
+    },
+    {
+      "epoch": 0.32477353288696337,
+      "grad_norm": 1.4252976179122925,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 1.0414,
+      "step": 12369
+    },
+    {
+      "epoch": 0.32558750164106603,
+      "grad_norm": 1.586527943611145,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 1.0449,
+      "step": 12400
+    },
+    {
+      "epoch": 0.3264014703951687,
+      "grad_norm": 1.345456838607788,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 1.0448,
+      "step": 12431
+    },
+    {
+      "epoch": 0.32721543914927137,
+      "grad_norm": 1.1366424560546875,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 1.0422,
+      "step": 12462
+    },
+    {
+      "epoch": 0.32802940790337404,
+      "grad_norm": 1.2205365896224976,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 1.0367,
+      "step": 12493
+    },
+    {
+      "epoch": 0.3288433766574767,
+      "grad_norm": 1.0971546173095703,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 1.0379,
+      "step": 12524
+    },
+    {
+      "epoch": 0.32965734541157937,
+      "grad_norm": 1.3336870670318604,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 1.0475,
+      "step": 12555
+    },
+    {
+      "epoch": 0.33047131416568204,
+      "grad_norm": 1.090570330619812,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 1.0473,
+      "step": 12586
+    },
+    {
+      "epoch": 0.3312852829197847,
+      "grad_norm": 1.344089150428772,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 1.0487,
+      "step": 12617
+    },
+    {
+      "epoch": 0.3320992516738874,
+      "grad_norm": 1.3599270582199097,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 1.047,
+      "step": 12648
+    },
+    {
+      "epoch": 0.33291322042799004,
+      "grad_norm": 1.106147050857544,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 1.0431,
+      "step": 12679
+    },
+    {
+      "epoch": 0.3337271891820927,
+      "grad_norm": 1.111688494682312,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 1.0298,
+      "step": 12710
+    },
+    {
+      "epoch": 0.3345411579361954,
+      "grad_norm": 1.1327451467514038,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 1.0492,
+      "step": 12741
+    },
+    {
+      "epoch": 0.33535512669029804,
+      "grad_norm": 1.3703464269638062,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 1.0409,
+      "step": 12772
+    },
+    {
+      "epoch": 0.33616909544440066,
+      "grad_norm": 1.2657904624938965,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 1.0291,
+      "step": 12803
+    },
+    {
+      "epoch": 0.3369830641985033,
+      "grad_norm": 1.8904515504837036,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 1.0562,
+      "step": 12834
+    },
+    {
+      "epoch": 0.337797032952606,
+      "grad_norm": 1.1837934255599976,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 1.037,
+      "step": 12865
+    },
+    {
+      "epoch": 0.33861100170670866,
+      "grad_norm": 1.291637659072876,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 1.0418,
+      "step": 12896
+    },
+    {
+      "epoch": 0.3394249704608113,
+      "grad_norm": 1.1425219774246216,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 1.0428,
+      "step": 12927
+    },
+    {
+      "epoch": 0.340238939214914,
+      "grad_norm": 1.3942662477493286,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 1.0341,
+      "step": 12958
+    },
+    {
+      "epoch": 0.34105290796901666,
+      "grad_norm": 1.873417854309082,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 1.0512,
+      "step": 12989
+    },
+    {
+      "epoch": 0.34186687672311933,
+      "grad_norm": 1.1052135229110718,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 1.0419,
+      "step": 13020
+    },
+    {
+      "epoch": 0.342680845477222,
+      "grad_norm": 1.7213804721832275,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 1.0504,
+      "step": 13051
+    },
+    {
+      "epoch": 0.34349481423132466,
+      "grad_norm": 1.288442611694336,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 1.048,
+      "step": 13082
+    },
+    {
+      "epoch": 0.34430878298542733,
+      "grad_norm": 0.9848569631576538,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 1.0457,
+      "step": 13113
+    },
+    {
+      "epoch": 0.34512275173953,
+      "grad_norm": 1.2687885761260986,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 1.0239,
+      "step": 13144
+    },
+    {
+      "epoch": 0.34593672049363267,
+      "grad_norm": 1.4076862335205078,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 1.0362,
+      "step": 13175
+    },
+    {
+      "epoch": 0.34675068924773533,
+      "grad_norm": 1.2733044624328613,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 1.044,
+      "step": 13206
+    },
+    {
+      "epoch": 0.347564658001838,
+      "grad_norm": 1.2099367380142212,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 1.0387,
+      "step": 13237
+    },
+    {
+      "epoch": 0.34837862675594067,
+      "grad_norm": 1.3610024452209473,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 1.0428,
+      "step": 13268
+    },
+    {
+      "epoch": 0.34919259551004334,
+      "grad_norm": 1.7405134439468384,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 1.0435,
+      "step": 13299
+    },
+    {
+      "epoch": 0.350006564264146,
+      "grad_norm": 1.0439188480377197,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 1.0354,
+      "step": 13330
+    },
+    {
+      "epoch": 0.35082053301824867,
+      "grad_norm": 1.2063871622085571,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 1.0426,
+      "step": 13361
+    },
+    {
+      "epoch": 0.35163450177235134,
+      "grad_norm": 1.0741288661956787,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 1.0388,
+      "step": 13392
+    },
+    {
+      "epoch": 0.352448470526454,
+      "grad_norm": 1.519148349761963,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 1.0403,
+      "step": 13423
+    },
+    {
+      "epoch": 0.3532624392805567,
+      "grad_norm": 1.5526783466339111,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 1.02,
+      "step": 13454
+    },
+    {
+      "epoch": 0.35407640803465934,
+      "grad_norm": 1.408262848854065,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 1.0316,
+      "step": 13485
+    },
+    {
+      "epoch": 0.35489037678876195,
+      "grad_norm": 1.4089866876602173,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 1.0377,
+      "step": 13516
+    },
+    {
+      "epoch": 0.3557043455428646,
+      "grad_norm": 1.0842416286468506,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 1.0228,
+      "step": 13547
+    },
+    {
+      "epoch": 0.3565183142969673,
+      "grad_norm": 1.0705150365829468,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 1.0311,
+      "step": 13578
+    },
+    {
+      "epoch": 0.35733228305106995,
+      "grad_norm": 1.5801275968551636,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 1.0232,
+      "step": 13609
+    },
+    {
+      "epoch": 0.3581462518051726,
+      "grad_norm": 1.3737410306930542,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 1.0452,
+      "step": 13640
+    },
+    {
+      "epoch": 0.3589602205592753,
+      "grad_norm": 1.0981717109680176,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 1.0252,
+      "step": 13671
+    },
+    {
+      "epoch": 0.35977418931337796,
+      "grad_norm": 1.3020241260528564,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 1.0343,
+      "step": 13702
+    },
+    {
+      "epoch": 0.3605881580674806,
+      "grad_norm": 1.3917444944381714,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 1.0436,
+      "step": 13733
+    },
+    {
+      "epoch": 0.3614021268215833,
+      "grad_norm": 1.366969108581543,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 1.0305,
+      "step": 13764
+    },
+    {
+      "epoch": 0.36221609557568596,
+      "grad_norm": 1.2640056610107422,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 1.0302,
+      "step": 13795
+    },
+    {
+      "epoch": 0.3630300643297886,
+      "grad_norm": 1.52952241897583,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 1.0264,
+      "step": 13826
+    },
+    {
+      "epoch": 0.3638440330838913,
+      "grad_norm": 1.1217405796051025,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 1.0307,
+      "step": 13857
+    },
+    {
+      "epoch": 0.36465800183799396,
+      "grad_norm": 1.2057907581329346,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 1.0394,
+      "step": 13888
+    },
+    {
+      "epoch": 0.36547197059209663,
+      "grad_norm": 1.2924937009811401,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 1.0361,
+      "step": 13919
+    },
+    {
+      "epoch": 0.3662859393461993,
+      "grad_norm": 1.1641929149627686,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 1.0413,
+      "step": 13950
+    },
+    {
+      "epoch": 0.36709990810030196,
+      "grad_norm": 1.0687799453735352,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 1.0276,
+      "step": 13981
+    },
+    {
+      "epoch": 0.36791387685440463,
+      "grad_norm": 1.429776668548584,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 1.0211,
+      "step": 14012
+    },
+    {
+      "epoch": 0.3687278456085073,
+      "grad_norm": 1.618382453918457,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 1.0401,
+      "step": 14043
+    },
+    {
+      "epoch": 0.36954181436260997,
+      "grad_norm": 1.3987113237380981,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 1.0465,
+      "step": 14074
+    },
+    {
+      "epoch": 0.37035578311671263,
+      "grad_norm": 1.6193658113479614,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 1.0238,
+      "step": 14105
+    },
+    {
+      "epoch": 0.3711697518708153,
+      "grad_norm": 1.0907481908798218,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 1.0222,
+      "step": 14136
+    },
+    {
+      "epoch": 0.37198372062491797,
+      "grad_norm": 1.5249978303909302,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 1.0344,
+      "step": 14167
+    },
+    {
+      "epoch": 0.37279768937902064,
+      "grad_norm": 1.5456349849700928,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 1.0259,
+      "step": 14198
+    },
+    {
+      "epoch": 0.3736116581331233,
+      "grad_norm": 1.1890850067138672,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 1.027,
+      "step": 14229
+    },
+    {
+      "epoch": 0.3744256268872259,
+      "grad_norm": 1.2732579708099365,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 1.0147,
+      "step": 14260
+    },
+    {
+      "epoch": 0.3752395956413286,
+      "grad_norm": 1.1628611087799072,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 1.0298,
+      "step": 14291
+    },
+    {
+      "epoch": 0.37605356439543125,
+      "grad_norm": 1.7209378480911255,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 1.0338,
+      "step": 14322
+    },
+    {
+      "epoch": 0.3768675331495339,
+      "grad_norm": 1.251638650894165,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 1.0297,
+      "step": 14353
+    },
+    {
+      "epoch": 0.3776815019036366,
+      "grad_norm": 1.2227071523666382,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 1.0148,
+      "step": 14384
+    },
+    {
+      "epoch": 0.37849547065773925,
+      "grad_norm": 1.5267024040222168,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 1.0345,
+      "step": 14415
+    },
+    {
+      "epoch": 0.3793094394118419,
+      "grad_norm": 1.1948013305664062,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 1.0226,
+      "step": 14446
+    },
+    {
+      "epoch": 0.3801234081659446,
+      "grad_norm": 1.4295780658721924,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 1.0247,
+      "step": 14477
+    },
+    {
+      "epoch": 0.38093737692004725,
+      "grad_norm": 1.2600759267807007,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 1.0244,
+      "step": 14508
+    },
+    {
+      "epoch": 0.3817513456741499,
+      "grad_norm": 1.1114932298660278,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 1.0341,
+      "step": 14539
+    },
+    {
+      "epoch": 0.3825653144282526,
+      "grad_norm": 0.9899073243141174,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 1.0269,
+      "step": 14570
+    },
+    {
+      "epoch": 0.38337928318235526,
+      "grad_norm": 1.2238157987594604,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 1.0282,
+      "step": 14601
+    },
+    {
+      "epoch": 0.3841932519364579,
+      "grad_norm": 1.2272999286651611,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 1.0216,
+      "step": 14632
+    },
+    {
+      "epoch": 0.3850072206905606,
+      "grad_norm": 1.3068078756332397,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 1.0306,
+      "step": 14663
+    },
+    {
+      "epoch": 0.38582118944466326,
+      "grad_norm": 1.5419495105743408,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 1.0231,
+      "step": 14694
+    },
+    {
+      "epoch": 0.3866351581987659,
+      "grad_norm": 1.2356003522872925,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 1.0183,
+      "step": 14725
+    },
+    {
+      "epoch": 0.3874491269528686,
+      "grad_norm": 1.1553258895874023,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 1.0191,
+      "step": 14756
+    },
+    {
+      "epoch": 0.38826309570697126,
+      "grad_norm": 1.4058918952941895,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 1.0346,
+      "step": 14787
+    },
+    {
+      "epoch": 0.38907706446107393,
+      "grad_norm": 1.091408371925354,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 1.0193,
+      "step": 14818
+    },
+    {
+      "epoch": 0.3898910332151766,
+      "grad_norm": 0.9390985369682312,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 1.0178,
+      "step": 14849
+    },
+    {
+      "epoch": 0.39070500196927926,
+      "grad_norm": 1.4442778825759888,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 1.0237,
+      "step": 14880
+    },
+    {
+      "epoch": 0.39151897072338193,
+      "grad_norm": 1.3647695779800415,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 1.019,
+      "step": 14911
+    },
+    {
+      "epoch": 0.3923329394774846,
+      "grad_norm": 1.3495923280715942,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 1.0282,
+      "step": 14942
+    },
+    {
+      "epoch": 0.39314690823158727,
+      "grad_norm": 1.2871686220169067,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 1.0081,
+      "step": 14973
+    },
+    {
+      "epoch": 0.3939608769856899,
+      "grad_norm": 1.3448808193206787,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 1.0248,
+      "step": 15004
+    },
+    {
+      "epoch": 0.39477484573979255,
+      "grad_norm": 1.0908681154251099,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 1.0237,
+      "step": 15035
+    },
+    {
+      "epoch": 0.3955888144938952,
+      "grad_norm": 1.5554354190826416,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 1.0215,
+      "step": 15066
+    },
+    {
+      "epoch": 0.3964027832479979,
+      "grad_norm": 1.3245160579681396,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 1.0078,
+      "step": 15097
+    },
+    {
+      "epoch": 0.39721675200210055,
+      "grad_norm": 1.4786434173583984,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 1.0222,
+      "step": 15128
+    },
+    {
+      "epoch": 0.3980307207562032,
+      "grad_norm": 1.5292481184005737,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 1.0291,
+      "step": 15159
+    },
+    {
+      "epoch": 0.3988446895103059,
+      "grad_norm": 1.2219812870025635,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 1.0331,
+      "step": 15190
+    },
+    {
+      "epoch": 0.39965865826440855,
+      "grad_norm": 1.1807560920715332,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 1.0185,
+      "step": 15221
+    },
+    {
+      "epoch": 0.4004726270185112,
+      "grad_norm": 1.095656394958496,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 1.0305,
+      "step": 15252
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.060677039050195e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15260/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4603817deb4fe9dbf9231c537a49054e10822b91664f8a6b53bf4ff6aba3ab1b
+size 5304

checkpoint-18312/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": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-18312/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": "4.44.0.dev0"
+}

checkpoint-18312/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71c2cd8a486b54a82fc72e287d658662b88a6f6621145b167b9788934553adf
+size 4976687216

checkpoint-18312/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb205482e80b5d03e63693e387d459b0cb9c97948cde971ff025ba98f1396d
+size 4778622352

checkpoint-18312/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222b40c6fea7def1d5911b059ab36bf97b9328e0251689f78a0a9ebd98cd18d
+size 4932743960

checkpoint-18312/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-18312/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-18312/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21e50781355cf36e59e8987b40d4f501e5f01afc02c8b45e5220fad77c8a73e
+size 3662865184

checkpoint-18312/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7467888ffc5a4e21c63e57b455647d248a5341d8ca3e0fe5f014f36350790312
+size 2179989632

checkpoint-18312/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-18312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71d6120873a6d3ac85c338e59ade013616054346a3a62a4bd108ad32e05f9ba
+size 16177880918

checkpoint-18312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-18312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e65c3d6f29e706fd941a38280ce5628189a6998eac6d29abbeab00ad838d00
+size 1064

checkpoint-18312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4603817deb4fe9dbf9231c537a49054e10822b91664f8a6b53bf4ff6aba3ab1b
+size 5304

checkpoint-21364/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": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-21364/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": "4.44.0.dev0"
+}

checkpoint-21364/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf68f621943bd46f9deea9713413249238bb4a376ce207a5c1f60a185bd9292
+size 4976687216

checkpoint-21364/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb205482e80b5d03e63693e387d459b0cb9c97948cde971ff025ba98f1396d
+size 4778622352