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 sha256:185f31a657671fc6de9c597ecfad1c86476f9a7deb8def6edd0d6467e2db39b0
+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:c61d89c69d34dfec79df98396cb6204d72760bff2d4c90926f4a1101d4bd4c6b
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146a29d9f53e95ab5e4a1a141640a0fe7f00555a62fe3065de8e01365a6e099c
+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:d224f3399e887c5ac7583b336b69b0f7a60adb0535d081b6210ac2178daa9c4d
+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": 0.1132415008580307,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00028755623579611333,
+      "grad_norm": 2.5471084117889404,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.2071,
+      "step": 31
+    },
+    {
+      "epoch": 0.0005751124715922267,
+      "grad_norm": 1.500440001487732,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.126,
+      "step": 62
+    },
+    {
+      "epoch": 0.0008626687073883401,
+      "grad_norm": 1.54880690574646,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.1015,
+      "step": 93
+    },
+    {
+      "epoch": 0.0011502249431844533,
+      "grad_norm": 1.6134709119796753,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.0761,
+      "step": 124
+    },
+    {
+      "epoch": 0.0014377811789805669,
+      "grad_norm": 1.824180006980896,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.0642,
+      "step": 155
+    },
+    {
+      "epoch": 0.0017253374147766802,
+      "grad_norm": 1.415733814239502,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.0362,
+      "step": 186
+    },
+    {
+      "epoch": 0.0020128936505727935,
+      "grad_norm": 1.728509783744812,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.044,
+      "step": 217
+    },
+    {
+      "epoch": 0.0023004498863689066,
+      "grad_norm": 1.602379560470581,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.0404,
+      "step": 248
+    },
+    {
+      "epoch": 0.00258800612216502,
+      "grad_norm": 1.8858306407928467,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.0212,
+      "step": 279
+    },
+    {
+      "epoch": 0.0028755623579611337,
+      "grad_norm": 2.285231351852417,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.0032,
+      "step": 310
+    },
+    {
+      "epoch": 0.003163118593757247,
+      "grad_norm": 1.8043686151504517,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.0031,
+      "step": 341
+    },
+    {
+      "epoch": 0.0034506748295533604,
+      "grad_norm": 1.870897889137268,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.0058,
+      "step": 372
+    },
+    {
+      "epoch": 0.0037382310653494735,
+      "grad_norm": 2.116208791732788,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.0007,
+      "step": 403
+    },
+    {
+      "epoch": 0.004025787301145587,
+      "grad_norm": 2.0111632347106934,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 0.9923,
+      "step": 434
+    },
+    {
+      "epoch": 0.0043133435369417,
+      "grad_norm": 1.7982046604156494,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 0.9867,
+      "step": 465
+    },
+    {
+      "epoch": 0.004600899772737813,
+      "grad_norm": 2.007441759109497,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 0.978,
+      "step": 496
+    },
+    {
+      "epoch": 0.004888456008533927,
+      "grad_norm": 2.805020809173584,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 0.9794,
+      "step": 527
+    },
+    {
+      "epoch": 0.00517601224433004,
+      "grad_norm": 2.376081943511963,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 0.9587,
+      "step": 558
+    },
+    {
+      "epoch": 0.0054635684801261535,
+      "grad_norm": 2.0517630577087402,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 0.9697,
+      "step": 589
+    },
+    {
+      "epoch": 0.0057511247159222675,
+      "grad_norm": 1.7311242818832397,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 0.9582,
+      "step": 620
+    },
+    {
+      "epoch": 0.006038680951718381,
+      "grad_norm": 1.533537745475769,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 0.9561,
+      "step": 651
+    },
+    {
+      "epoch": 0.006326237187514494,
+      "grad_norm": 1.5506970882415771,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 0.951,
+      "step": 682
+    },
+    {
+      "epoch": 0.006613793423310607,
+      "grad_norm": 2.716867685317993,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 0.9511,
+      "step": 713
+    },
+    {
+      "epoch": 0.006901349659106721,
+      "grad_norm": 2.3463616371154785,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 0.9538,
+      "step": 744
+    },
+    {
+      "epoch": 0.007188905894902834,
+      "grad_norm": 1.54783034324646,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.9528,
+      "step": 775
+    },
+    {
+      "epoch": 0.007476462130698947,
+      "grad_norm": 1.2869651317596436,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.944,
+      "step": 806
+    },
+    {
+      "epoch": 0.00776401836649506,
+      "grad_norm": 1.3865717649459839,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.9342,
+      "step": 837
+    },
+    {
+      "epoch": 0.008051574602291174,
+      "grad_norm": 1.8173962831497192,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.94,
+      "step": 868
+    },
+    {
+      "epoch": 0.008339130838087287,
+      "grad_norm": 1.6419012546539307,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.9251,
+      "step": 899
+    },
+    {
+      "epoch": 0.0086266870738834,
+      "grad_norm": 1.5133196115493774,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.9252,
+      "step": 930
+    },
+    {
+      "epoch": 0.008914243309679513,
+      "grad_norm": 1.91935133934021,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.9363,
+      "step": 961
+    },
+    {
+      "epoch": 0.009201799545475627,
+      "grad_norm": 1.592256784439087,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.922,
+      "step": 992
+    },
+    {
+      "epoch": 0.009489355781271741,
+      "grad_norm": 2.3662896156311035,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.922,
+      "step": 1023
+    },
+    {
+      "epoch": 0.009776912017067855,
+      "grad_norm": 2.121152639389038,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.9425,
+      "step": 1054
+    },
+    {
+      "epoch": 0.010064468252863968,
+      "grad_norm": 1.389515995979309,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.913,
+      "step": 1085
+    },
+    {
+      "epoch": 0.01035202448866008,
+      "grad_norm": 1.4310904741287231,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.9201,
+      "step": 1116
+    },
+    {
+      "epoch": 0.010639580724456194,
+      "grad_norm": 1.5803974866867065,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.9261,
+      "step": 1147
+    },
+    {
+      "epoch": 0.010927136960252307,
+      "grad_norm": 1.2364155054092407,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.9076,
+      "step": 1178
+    },
+    {
+      "epoch": 0.01121469319604842,
+      "grad_norm": 1.4545661211013794,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.9108,
+      "step": 1209
+    },
+    {
+      "epoch": 0.011502249431844535,
+      "grad_norm": 1.3160631656646729,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.909,
+      "step": 1240
+    },
+    {
+      "epoch": 0.011789805667640648,
+      "grad_norm": 1.512214183807373,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.8876,
+      "step": 1271
+    },
+    {
+      "epoch": 0.012077361903436761,
+      "grad_norm": 1.4180532693862915,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.8976,
+      "step": 1302
+    },
+    {
+      "epoch": 0.012364918139232874,
+      "grad_norm": 1.4778006076812744,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.8923,
+      "step": 1333
+    },
+    {
+      "epoch": 0.012652474375028987,
+      "grad_norm": 1.8094278573989868,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.9106,
+      "step": 1364
+    },
+    {
+      "epoch": 0.0129400306108251,
+      "grad_norm": 1.361230492591858,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.9017,
+      "step": 1395
+    },
+    {
+      "epoch": 0.013227586846621214,
+      "grad_norm": 1.2361464500427246,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.8999,
+      "step": 1426
+    },
+    {
+      "epoch": 0.013515143082417327,
+      "grad_norm": 1.641925573348999,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.9001,
+      "step": 1457
+    },
+    {
+      "epoch": 0.013802699318213442,
+      "grad_norm": 15.032498359680176,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.957,
+      "step": 1488
+    },
+    {
+      "epoch": 0.014090255554009555,
+      "grad_norm": 1.2676361799240112,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.9501,
+      "step": 1519
+    },
+    {
+      "epoch": 0.014377811789805668,
+      "grad_norm": 1.5450263023376465,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.9151,
+      "step": 1550
+    },
+    {
+      "epoch": 0.014665368025601781,
+      "grad_norm": 1.4152264595031738,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.906,
+      "step": 1581
+    },
+    {
+      "epoch": 0.014952924261397894,
+      "grad_norm": 1.250949740409851,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.9053,
+      "step": 1612
+    },
+    {
+      "epoch": 0.015240480497194007,
+      "grad_norm": 1.3265453577041626,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.9006,
+      "step": 1643
+    },
+    {
+      "epoch": 0.01552803673299012,
+      "grad_norm": 1.1016136407852173,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.8853,
+      "step": 1674
+    },
+    {
+      "epoch": 0.015815592968786235,
+      "grad_norm": 1.6496962308883667,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.8824,
+      "step": 1705
+    },
+    {
+      "epoch": 0.016103149204582348,
+      "grad_norm": 2.5228922367095947,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.883,
+      "step": 1736
+    },
+    {
+      "epoch": 0.01639070544037846,
+      "grad_norm": 1.1221877336502075,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.8668,
+      "step": 1767
+    },
+    {
+      "epoch": 0.016678261676174574,
+      "grad_norm": 1.4403537511825562,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.8819,
+      "step": 1798
+    },
+    {
+      "epoch": 0.016965817911970688,
+      "grad_norm": 1.2584978342056274,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.864,
+      "step": 1829
+    },
+    {
+      "epoch": 0.0172533741477668,
+      "grad_norm": 1.2469295263290405,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.8709,
+      "step": 1860
+    },
+    {
+      "epoch": 0.017540930383562914,
+      "grad_norm": 1.2993371486663818,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.8763,
+      "step": 1891
+    },
+    {
+      "epoch": 0.017828486619359027,
+      "grad_norm": 1.3034465312957764,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.8742,
+      "step": 1922
+    },
+    {
+      "epoch": 0.01811604285515514,
+      "grad_norm": 0.9507549405097961,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.8685,
+      "step": 1953
+    },
+    {
+      "epoch": 0.018403599090951253,
+      "grad_norm": 1.2451794147491455,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.8574,
+      "step": 1984
+    },
+    {
+      "epoch": 0.018691155326747366,
+      "grad_norm": 0.9359011054039001,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.8518,
+      "step": 2015
+    },
+    {
+      "epoch": 0.018978711562543483,
+      "grad_norm": 0.9871286749839783,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.8681,
+      "step": 2046
+    },
+    {
+      "epoch": 0.019266267798339596,
+      "grad_norm": 0.9597110152244568,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.8561,
+      "step": 2077
+    },
+    {
+      "epoch": 0.01955382403413571,
+      "grad_norm": 1.7902615070343018,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.8597,
+      "step": 2108
+    },
+    {
+      "epoch": 0.019841380269931822,
+      "grad_norm": 0.9376184940338135,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.8589,
+      "step": 2139
+    },
+    {
+      "epoch": 0.020128936505727935,
+      "grad_norm": 0.9978942275047302,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.8537,
+      "step": 2170
+    },
+    {
+      "epoch": 0.02041649274152405,
+      "grad_norm": 0.8389673233032227,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.8565,
+      "step": 2201
+    },
+    {
+      "epoch": 0.02070404897732016,
+      "grad_norm": 1.0237621068954468,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.844,
+      "step": 2232
+    },
+    {
+      "epoch": 0.020991605213116275,
+      "grad_norm": 1.0087332725524902,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.8382,
+      "step": 2263
+    },
+    {
+      "epoch": 0.021279161448912388,
+      "grad_norm": 1.0753614902496338,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.8276,
+      "step": 2294
+    },
+    {
+      "epoch": 0.0215667176847085,
+      "grad_norm": 1.0078065395355225,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.84,
+      "step": 2325
+    },
+    {
+      "epoch": 0.021854273920504614,
+      "grad_norm": 0.8615468740463257,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.8462,
+      "step": 2356
+    },
+    {
+      "epoch": 0.022141830156300727,
+      "grad_norm": 1.0752439498901367,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.8335,
+      "step": 2387
+    },
+    {
+      "epoch": 0.02242938639209684,
+      "grad_norm": 1.1604725122451782,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.8368,
+      "step": 2418
+    },
+    {
+      "epoch": 0.022716942627892953,
+      "grad_norm": 1.084244966506958,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.8341,
+      "step": 2449
+    },
+    {
+      "epoch": 0.02300449886368907,
+      "grad_norm": 0.9928577542304993,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.8312,
+      "step": 2480
+    },
+    {
+      "epoch": 0.023292055099485183,
+      "grad_norm": 1.2830171585083008,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.8415,
+      "step": 2511
+    },
+    {
+      "epoch": 0.023579611335281296,
+      "grad_norm": 0.733214795589447,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.8526,
+      "step": 2542
+    },
+    {
+      "epoch": 0.02386716757107741,
+      "grad_norm": 0.7755644917488098,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.8382,
+      "step": 2573
+    },
+    {
+      "epoch": 0.024154723806873522,
+      "grad_norm": 1.127175211906433,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.8321,
+      "step": 2604
+    },
+    {
+      "epoch": 0.024442280042669635,
+      "grad_norm": 0.6953925490379333,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.8153,
+      "step": 2635
+    },
+    {
+      "epoch": 0.02472983627846575,
+      "grad_norm": 0.8521370887756348,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.8232,
+      "step": 2666
+    },
+    {
+      "epoch": 0.02501739251426186,
+      "grad_norm": 0.8186238408088684,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.8172,
+      "step": 2697
+    },
+    {
+      "epoch": 0.025304948750057975,
+      "grad_norm": 0.7999460697174072,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.8157,
+      "step": 2728
+    },
+    {
+      "epoch": 0.025592504985854088,
+      "grad_norm": 1.0013262033462524,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.8269,
+      "step": 2759
+    },
+    {
+      "epoch": 0.0258800612216502,
+      "grad_norm": 0.910980761051178,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.8251,
+      "step": 2790
+    },
+    {
+      "epoch": 0.026167617457446314,
+      "grad_norm": 0.9238119125366211,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.8058,
+      "step": 2821
+    },
+    {
+      "epoch": 0.026455173693242427,
+      "grad_norm": 0.9186171889305115,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.8102,
+      "step": 2852
+    },
+    {
+      "epoch": 0.02674272992903854,
+      "grad_norm": 0.7005239725112915,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.8188,
+      "step": 2883
+    },
+    {
+      "epoch": 0.027030286164834653,
+      "grad_norm": 0.7916774153709412,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.8204,
+      "step": 2914
+    },
+    {
+      "epoch": 0.02731784240063077,
+      "grad_norm": 0.9498996138572693,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.8122,
+      "step": 2945
+    },
+    {
+      "epoch": 0.027605398636426883,
+      "grad_norm": 0.7997952699661255,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.8193,
+      "step": 2976
+    },
+    {
+      "epoch": 0.027892954872222996,
+      "grad_norm": 0.8657526969909668,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.8258,
+      "step": 3007
+    },
+    {
+      "epoch": 0.02818051110801911,
+      "grad_norm": 0.8351128697395325,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.8054,
+      "step": 3038
+    },
+    {
+      "epoch": 0.028468067343815222,
+      "grad_norm": 0.8679622411727905,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.8081,
+      "step": 3069
+    },
+    {
+      "epoch": 0.028755623579611336,
+      "grad_norm": 0.7777401208877563,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.8028,
+      "step": 3100
+    },
+    {
+      "epoch": 0.02904317981540745,
+      "grad_norm": 0.859012246131897,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.8152,
+      "step": 3131
+    },
+    {
+      "epoch": 0.029330736051203562,
+      "grad_norm": 0.7595569491386414,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.8082,
+      "step": 3162
+    },
+    {
+      "epoch": 0.029618292286999675,
+      "grad_norm": 0.8339647650718689,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.8113,
+      "step": 3193
+    },
+    {
+      "epoch": 0.029905848522795788,
+      "grad_norm": 0.8242756128311157,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.8143,
+      "step": 3224
+    },
+    {
+      "epoch": 0.0301934047585919,
+      "grad_norm": 0.9011533856391907,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.8015,
+      "step": 3255
+    },
+    {
+      "epoch": 0.030480960994388014,
+      "grad_norm": 1.2543679475784302,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.8004,
+      "step": 3286
+    },
+    {
+      "epoch": 0.030768517230184127,
+      "grad_norm": 0.8444302678108215,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.8082,
+      "step": 3317
+    },
+    {
+      "epoch": 0.03105607346598024,
+      "grad_norm": 0.8438568711280823,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.7892,
+      "step": 3348
+    },
+    {
+      "epoch": 0.03134362970177636,
+      "grad_norm": 0.9470321536064148,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.7998,
+      "step": 3379
+    },
+    {
+      "epoch": 0.03163118593757247,
+      "grad_norm": 0.7611345648765564,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.7975,
+      "step": 3410
+    },
+    {
+      "epoch": 0.03191874217336858,
+      "grad_norm": 1.0148237943649292,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.8079,
+      "step": 3441
+    },
+    {
+      "epoch": 0.032206298409164696,
+      "grad_norm": 0.6824489235877991,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.7875,
+      "step": 3472
+    },
+    {
+      "epoch": 0.03249385464496081,
+      "grad_norm": 0.7495407462120056,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.7936,
+      "step": 3503
+    },
+    {
+      "epoch": 0.03278141088075692,
+      "grad_norm": 0.6833623647689819,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.794,
+      "step": 3534
+    },
+    {
+      "epoch": 0.033068967116553036,
+      "grad_norm": 0.6844274997711182,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.7944,
+      "step": 3565
+    },
+    {
+      "epoch": 0.03335652335234915,
+      "grad_norm": 0.7401015162467957,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.8006,
+      "step": 3596
+    },
+    {
+      "epoch": 0.03364407958814526,
+      "grad_norm": 1.0470607280731201,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.8011,
+      "step": 3627
+    },
+    {
+      "epoch": 0.033931635823941375,
+      "grad_norm": 0.7898035049438477,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.7995,
+      "step": 3658
+    },
+    {
+      "epoch": 0.03421919205973749,
+      "grad_norm": 0.772084653377533,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.7949,
+      "step": 3689
+    },
+    {
+      "epoch": 0.0345067482955336,
+      "grad_norm": 0.823618471622467,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.7891,
+      "step": 3720
+    },
+    {
+      "epoch": 0.034794304531329714,
+      "grad_norm": 0.8022550940513611,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.7796,
+      "step": 3751
+    },
+    {
+      "epoch": 0.03508186076712583,
+      "grad_norm": 0.7855663895606995,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.7913,
+      "step": 3782
+    },
+    {
+      "epoch": 0.03536941700292194,
+      "grad_norm": 0.6916162967681885,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.7948,
+      "step": 3813
+    },
+    {
+      "epoch": 0.035656973238718054,
+      "grad_norm": 0.7116622924804688,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.7937,
+      "step": 3844
+    },
+    {
+      "epoch": 0.03594452947451417,
+      "grad_norm": 0.6990245580673218,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.7894,
+      "step": 3875
+    },
+    {
+      "epoch": 0.03623208571031028,
+      "grad_norm": 0.7066308259963989,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.7836,
+      "step": 3906
+    },
+    {
+      "epoch": 0.03651964194610639,
+      "grad_norm": 0.6334872841835022,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.7961,
+      "step": 3937
+    },
+    {
+      "epoch": 0.036807198181902506,
+      "grad_norm": 0.8018898963928223,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.7962,
+      "step": 3968
+    },
+    {
+      "epoch": 0.03709475441769862,
+      "grad_norm": 0.8985097408294678,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.7847,
+      "step": 3999
+    },
+    {
+      "epoch": 0.03738231065349473,
+      "grad_norm": 0.7619264125823975,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.7882,
+      "step": 4030
+    },
+    {
+      "epoch": 0.03766986688929085,
+      "grad_norm": 0.6307808756828308,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.7761,
+      "step": 4061
+    },
+    {
+      "epoch": 0.037957423125086966,
+      "grad_norm": 0.6743819117546082,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.7869,
+      "step": 4092
+    },
+    {
+      "epoch": 0.03824497936088308,
+      "grad_norm": 0.7610074877738953,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.7768,
+      "step": 4123
+    },
+    {
+      "epoch": 0.03853253559667919,
+      "grad_norm": 0.653424084186554,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.7802,
+      "step": 4154
+    },
+    {
+      "epoch": 0.038820091832475305,
+      "grad_norm": 1.0586974620819092,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.7911,
+      "step": 4185
+    },
+    {
+      "epoch": 0.03910764806827142,
+      "grad_norm": 0.6271804571151733,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.7784,
+      "step": 4216
+    },
+    {
+      "epoch": 0.03939520430406753,
+      "grad_norm": 0.889215886592865,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.7721,
+      "step": 4247
+    },
+    {
+      "epoch": 0.039682760539863644,
+      "grad_norm": 0.7688327431678772,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.7859,
+      "step": 4278
+    },
+    {
+      "epoch": 0.03997031677565976,
+      "grad_norm": 0.8260688185691833,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.7719,
+      "step": 4309
+    },
+    {
+      "epoch": 0.04025787301145587,
+      "grad_norm": 0.7527140378952026,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.7833,
+      "step": 4340
+    },
+    {
+      "epoch": 0.040545429247251984,
+      "grad_norm": 0.7240214347839355,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.7806,
+      "step": 4371
+    },
+    {
+      "epoch": 0.0408329854830481,
+      "grad_norm": 0.7488278746604919,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.7893,
+      "step": 4402
+    },
+    {
+      "epoch": 0.04112054171884421,
+      "grad_norm": 0.7927774786949158,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.7867,
+      "step": 4433
+    },
+    {
+      "epoch": 0.04140809795464032,
+      "grad_norm": 0.6409322619438171,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.7764,
+      "step": 4464
+    },
+    {
+      "epoch": 0.041695654190436436,
+      "grad_norm": 0.6869925856590271,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.7861,
+      "step": 4495
+    },
+    {
+      "epoch": 0.04198321042623255,
+      "grad_norm": 0.8485197424888611,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.7826,
+      "step": 4526
+    },
+    {
+      "epoch": 0.04227076666202866,
+      "grad_norm": 0.6266471743583679,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.7658,
+      "step": 4557
+    },
+    {
+      "epoch": 0.042558322897824775,
+      "grad_norm": 0.8114103674888611,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.7775,
+      "step": 4588
+    },
+    {
+      "epoch": 0.04284587913362089,
+      "grad_norm": 0.698353111743927,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.7756,
+      "step": 4619
+    },
+    {
+      "epoch": 0.043133435369417,
+      "grad_norm": 0.6825971603393555,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.7716,
+      "step": 4650
+    },
+    {
+      "epoch": 0.043420991605213115,
+      "grad_norm": 0.8550017476081848,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.7813,
+      "step": 4681
+    },
+    {
+      "epoch": 0.04370854784100923,
+      "grad_norm": 0.7881748676300049,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.7661,
+      "step": 4712
+    },
+    {
+      "epoch": 0.04399610407680534,
+      "grad_norm": 0.7000054121017456,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.7648,
+      "step": 4743
+    },
+    {
+      "epoch": 0.044283660312601454,
+      "grad_norm": 0.727118194103241,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.7715,
+      "step": 4774
+    },
+    {
+      "epoch": 0.04457121654839757,
+      "grad_norm": 0.6390218138694763,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.7684,
+      "step": 4805
+    },
+    {
+      "epoch": 0.04485877278419368,
+      "grad_norm": 0.8063361644744873,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.7654,
+      "step": 4836
+    },
+    {
+      "epoch": 0.045146329019989793,
+      "grad_norm": 0.7509976625442505,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.7701,
+      "step": 4867
+    },
+    {
+      "epoch": 0.04543388525578591,
+      "grad_norm": 0.6991444826126099,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.7679,
+      "step": 4898
+    },
+    {
+      "epoch": 0.04572144149158202,
+      "grad_norm": 0.835519552230835,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.7754,
+      "step": 4929
+    },
+    {
+      "epoch": 0.04600899772737814,
+      "grad_norm": 0.7925782203674316,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.7649,
+      "step": 4960
+    },
+    {
+      "epoch": 0.04629655396317425,
+      "grad_norm": 0.6192532777786255,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.7764,
+      "step": 4991
+    },
+    {
+      "epoch": 0.046584110198970366,
+      "grad_norm": 0.7094298005104065,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.7743,
+      "step": 5022
+    },
+    {
+      "epoch": 0.04687166643476648,
+      "grad_norm": 0.5982211232185364,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.7769,
+      "step": 5053
+    },
+    {
+      "epoch": 0.04715922267056259,
+      "grad_norm": 0.6520153284072876,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.7647,
+      "step": 5084
+    },
+    {
+      "epoch": 0.047446778906358705,
+      "grad_norm": 0.6328307390213013,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.7668,
+      "step": 5115
+    },
+    {
+      "epoch": 0.04773433514215482,
+      "grad_norm": 0.6715372204780579,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.77,
+      "step": 5146
+    },
+    {
+      "epoch": 0.04802189137795093,
+      "grad_norm": 0.6676992774009705,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.7692,
+      "step": 5177
+    },
+    {
+      "epoch": 0.048309447613747045,
+      "grad_norm": 0.7889059782028198,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.761,
+      "step": 5208
+    },
+    {
+      "epoch": 0.04859700384954316,
+      "grad_norm": 0.7142347097396851,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.7444,
+      "step": 5239
+    },
+    {
+      "epoch": 0.04888456008533927,
+      "grad_norm": 0.7596989274024963,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.7401,
+      "step": 5270
+    },
+    {
+      "epoch": 0.049172116321135384,
+      "grad_norm": 0.5763289928436279,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.7627,
+      "step": 5301
+    },
+    {
+      "epoch": 0.0494596725569315,
+      "grad_norm": 0.6867230534553528,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.7652,
+      "step": 5332
+    },
+    {
+      "epoch": 0.04974722879272761,
+      "grad_norm": 0.8485914468765259,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.7754,
+      "step": 5363
+    },
+    {
+      "epoch": 0.05003478502852372,
+      "grad_norm": 0.7543194890022278,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.7544,
+      "step": 5394
+    },
+    {
+      "epoch": 0.050322341264319836,
+      "grad_norm": 0.5923686623573303,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.7457,
+      "step": 5425
+    },
+    {
+      "epoch": 0.05060989750011595,
+      "grad_norm": 0.6586946249008179,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.7625,
+      "step": 5456
+    },
+    {
+      "epoch": 0.05089745373591206,
+      "grad_norm": 0.712864875793457,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.7451,
+      "step": 5487
+    },
+    {
+      "epoch": 0.051185009971708176,
+      "grad_norm": 0.7251986861228943,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.7532,
+      "step": 5518
+    },
+    {
+      "epoch": 0.05147256620750429,
+      "grad_norm": 0.747039258480072,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.7548,
+      "step": 5549
+    },
+    {
+      "epoch": 0.0517601224433004,
+      "grad_norm": 0.7192988395690918,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.7568,
+      "step": 5580
+    },
+    {
+      "epoch": 0.052047678679096515,
+      "grad_norm": 0.6581113934516907,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.7674,
+      "step": 5611
+    },
+    {
+      "epoch": 0.05233523491489263,
+      "grad_norm": 0.661508321762085,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.7538,
+      "step": 5642
+    },
+    {
+      "epoch": 0.05262279115068874,
+      "grad_norm": 0.8347408175468445,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.7714,
+      "step": 5673
+    },
+    {
+      "epoch": 0.052910347386484854,
+      "grad_norm": 0.6756936311721802,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.7443,
+      "step": 5704
+    },
+    {
+      "epoch": 0.05319790362228097,
+      "grad_norm": 0.6768369674682617,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.7389,
+      "step": 5735
+    },
+    {
+      "epoch": 0.05348545985807708,
+      "grad_norm": 0.6765073537826538,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.7443,
+      "step": 5766
+    },
+    {
+      "epoch": 0.053773016093873194,
+      "grad_norm": 0.7619781494140625,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.7496,
+      "step": 5797
+    },
+    {
+      "epoch": 0.05406057232966931,
+      "grad_norm": 0.7346686124801636,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.7512,
+      "step": 5828
+    },
+    {
+      "epoch": 0.05434812856546543,
+      "grad_norm": 0.7577638030052185,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.7561,
+      "step": 5859
+    },
+    {
+      "epoch": 0.05463568480126154,
+      "grad_norm": 0.6721853613853455,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.766,
+      "step": 5890
+    },
+    {
+      "epoch": 0.05492324103705765,
+      "grad_norm": 0.678697407245636,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.7665,
+      "step": 5921
+    },
+    {
+      "epoch": 0.055210797272853766,
+      "grad_norm": 0.7274826169013977,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.7431,
+      "step": 5952
+    },
+    {
+      "epoch": 0.05549835350864988,
+      "grad_norm": 0.6908119916915894,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.7408,
+      "step": 5983
+    },
+    {
+      "epoch": 0.05578590974444599,
+      "grad_norm": 0.734859049320221,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.7591,
+      "step": 6014
+    },
+    {
+      "epoch": 0.056073465980242106,
+      "grad_norm": 0.7401076555252075,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.756,
+      "step": 6045
+    },
+    {
+      "epoch": 0.05636102221603822,
+      "grad_norm": 0.7856413125991821,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.7465,
+      "step": 6076
+    },
+    {
+      "epoch": 0.05664857845183433,
+      "grad_norm": 0.6996341347694397,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.7421,
+      "step": 6107
+    },
+    {
+      "epoch": 0.056936134687630445,
+      "grad_norm": 0.7988335490226746,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.7524,
+      "step": 6138
+    },
+    {
+      "epoch": 0.05722369092342656,
+      "grad_norm": 0.68621426820755,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.7468,
+      "step": 6169
+    },
+    {
+      "epoch": 0.05751124715922267,
+      "grad_norm": 0.6664344072341919,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.7515,
+      "step": 6200
+    },
+    {
+      "epoch": 0.057798803395018784,
+      "grad_norm": 0.7224786281585693,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.7467,
+      "step": 6231
+    },
+    {
+      "epoch": 0.0580863596308149,
+      "grad_norm": 0.5921575427055359,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.7563,
+      "step": 6262
+    },
+    {
+      "epoch": 0.05837391586661101,
+      "grad_norm": 0.6673355102539062,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.7523,
+      "step": 6293
+    },
+    {
+      "epoch": 0.058661472102407124,
+      "grad_norm": 0.7031881809234619,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.7497,
+      "step": 6324
+    },
+    {
+      "epoch": 0.05894902833820324,
+      "grad_norm": 0.6450571417808533,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.7357,
+      "step": 6355
+    },
+    {
+      "epoch": 0.05923658457399935,
+      "grad_norm": 0.6376838684082031,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.7534,
+      "step": 6386
+    },
+    {
+      "epoch": 0.05952414080979546,
+      "grad_norm": 0.6044135689735413,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.7413,
+      "step": 6417
+    },
+    {
+      "epoch": 0.059811697045591576,
+      "grad_norm": 0.696363627910614,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.7573,
+      "step": 6448
+    },
+    {
+      "epoch": 0.06009925328138769,
+      "grad_norm": 1.9165210723876953,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.7553,
+      "step": 6479
+    },
+    {
+      "epoch": 0.0603868095171838,
+      "grad_norm": 1.0885388851165771,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.7611,
+      "step": 6510
+    },
+    {
+      "epoch": 0.060674365752979915,
+      "grad_norm": 0.8365141153335571,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.763,
+      "step": 6541
+    },
+    {
+      "epoch": 0.06096192198877603,
+      "grad_norm": 0.7544219493865967,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.747,
+      "step": 6572
+    },
+    {
+      "epoch": 0.06124947822457214,
+      "grad_norm": 0.821266233921051,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.7462,
+      "step": 6603
+    },
+    {
+      "epoch": 0.061537034460368255,
+      "grad_norm": 0.7296980023384094,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.7494,
+      "step": 6634
+    },
+    {
+      "epoch": 0.06182459069616437,
+      "grad_norm": 0.6230852007865906,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.7417,
+      "step": 6665
+    },
+    {
+      "epoch": 0.06211214693196048,
+      "grad_norm": 0.6954329013824463,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.7388,
+      "step": 6696
+    },
+    {
+      "epoch": 0.062399703167756594,
+      "grad_norm": 0.6082637906074524,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.7339,
+      "step": 6727
+    },
+    {
+      "epoch": 0.06268725940355271,
+      "grad_norm": 0.739402711391449,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.7433,
+      "step": 6758
+    },
+    {
+      "epoch": 0.06297481563934883,
+      "grad_norm": 0.6120406985282898,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.7457,
+      "step": 6789
+    },
+    {
+      "epoch": 0.06326237187514494,
+      "grad_norm": 0.6660128831863403,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.7497,
+      "step": 6820
+    },
+    {
+      "epoch": 0.06354992811094105,
+      "grad_norm": 0.7525910139083862,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.7531,
+      "step": 6851
+    },
+    {
+      "epoch": 0.06383748434673717,
+      "grad_norm": 0.7022217512130737,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.7448,
+      "step": 6882
+    },
+    {
+      "epoch": 0.06412504058253328,
+      "grad_norm": 0.8050118088722229,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.7584,
+      "step": 6913
+    },
+    {
+      "epoch": 0.06441259681832939,
+      "grad_norm": 0.7408604025840759,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.7355,
+      "step": 6944
+    },
+    {
+      "epoch": 0.0647001530541255,
+      "grad_norm": 0.6935440301895142,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.736,
+      "step": 6975
+    },
+    {
+      "epoch": 0.06498770928992162,
+      "grad_norm": 0.7600308060646057,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.7355,
+      "step": 7006
+    },
+    {
+      "epoch": 0.06527526552571773,
+      "grad_norm": 0.5767653584480286,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.7319,
+      "step": 7037
+    },
+    {
+      "epoch": 0.06556282176151385,
+      "grad_norm": 0.696086049079895,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.7332,
+      "step": 7068
+    },
+    {
+      "epoch": 0.06585037799730996,
+      "grad_norm": 0.6155373454093933,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.7417,
+      "step": 7099
+    },
+    {
+      "epoch": 0.06613793423310607,
+      "grad_norm": 0.5616543292999268,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.7533,
+      "step": 7130
+    },
+    {
+      "epoch": 0.06642549046890218,
+      "grad_norm": 0.6647605299949646,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.7511,
+      "step": 7161
+    },
+    {
+      "epoch": 0.0667130467046983,
+      "grad_norm": 0.5980858206748962,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.7412,
+      "step": 7192
+    },
+    {
+      "epoch": 0.06700060294049441,
+      "grad_norm": 0.7701022624969482,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.7371,
+      "step": 7223
+    },
+    {
+      "epoch": 0.06728815917629052,
+      "grad_norm": 0.6251057386398315,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.7409,
+      "step": 7254
+    },
+    {
+      "epoch": 0.06757571541208664,
+      "grad_norm": 0.6283906698226929,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.7354,
+      "step": 7285
+    },
+    {
+      "epoch": 0.06786327164788275,
+      "grad_norm": 0.7811240553855896,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.7369,
+      "step": 7316
+    },
+    {
+      "epoch": 0.06815082788367886,
+      "grad_norm": 0.8049167394638062,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.7323,
+      "step": 7347
+    },
+    {
+      "epoch": 0.06843838411947498,
+      "grad_norm": 0.6499640345573425,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.7474,
+      "step": 7378
+    },
+    {
+      "epoch": 0.06872594035527109,
+      "grad_norm": 0.6651905179023743,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.7436,
+      "step": 7409
+    },
+    {
+      "epoch": 0.0690134965910672,
+      "grad_norm": 0.6399815082550049,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.7406,
+      "step": 7440
+    },
+    {
+      "epoch": 0.06930105282686332,
+      "grad_norm": 0.6342321634292603,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.7305,
+      "step": 7471
+    },
+    {
+      "epoch": 0.06958860906265943,
+      "grad_norm": 0.6198817491531372,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.7368,
+      "step": 7502
+    },
+    {
+      "epoch": 0.06987616529845554,
+      "grad_norm": 0.6942329406738281,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.7356,
+      "step": 7533
+    },
+    {
+      "epoch": 0.07016372153425166,
+      "grad_norm": 0.5913597941398621,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.7317,
+      "step": 7564
+    },
+    {
+      "epoch": 0.07045127777004777,
+      "grad_norm": 0.5913899540901184,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.7362,
+      "step": 7595
+    },
+    {
+      "epoch": 0.07073883400584388,
+      "grad_norm": 0.5804397463798523,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.7236,
+      "step": 7626
+    },
+    {
+      "epoch": 0.07102639024164,
+      "grad_norm": 0.5622512698173523,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.7329,
+      "step": 7657
+    },
+    {
+      "epoch": 0.07131394647743611,
+      "grad_norm": 5.153666973114014,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.7362,
+      "step": 7688
+    },
+    {
+      "epoch": 0.07160150271323222,
+      "grad_norm": 0.6316568851470947,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.7276,
+      "step": 7719
+    },
+    {
+      "epoch": 0.07188905894902833,
+      "grad_norm": 0.6307201981544495,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.7348,
+      "step": 7750
+    },
+    {
+      "epoch": 0.07217661518482445,
+      "grad_norm": 0.6287425756454468,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.7397,
+      "step": 7781
+    },
+    {
+      "epoch": 0.07246417142062056,
+      "grad_norm": 0.9809737205505371,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.7372,
+      "step": 7812
+    },
+    {
+      "epoch": 0.07275172765641667,
+      "grad_norm": 0.6115898489952087,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.7492,
+      "step": 7843
+    },
+    {
+      "epoch": 0.07303928389221279,
+      "grad_norm": 0.733198344707489,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.7378,
+      "step": 7874
+    },
+    {
+      "epoch": 0.0733268401280089,
+      "grad_norm": 0.6508429646492004,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.7285,
+      "step": 7905
+    },
+    {
+      "epoch": 0.07361439636380501,
+      "grad_norm": 0.6079477071762085,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.7341,
+      "step": 7936
+    },
+    {
+      "epoch": 0.07390195259960113,
+      "grad_norm": 0.5894839763641357,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.7286,
+      "step": 7967
+    },
+    {
+      "epoch": 0.07418950883539724,
+      "grad_norm": 0.6230615377426147,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.7257,
+      "step": 7998
+    },
+    {
+      "epoch": 0.07447706507119335,
+      "grad_norm": 0.7338290810585022,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.7265,
+      "step": 8029
+    },
+    {
+      "epoch": 0.07476462130698946,
+      "grad_norm": 0.6040816903114319,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.7294,
+      "step": 8060
+    },
+    {
+      "epoch": 0.07505217754278559,
+      "grad_norm": 0.5885149240493774,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.7275,
+      "step": 8091
+    },
+    {
+      "epoch": 0.0753397337785817,
+      "grad_norm": 0.626339316368103,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.7302,
+      "step": 8122
+    },
+    {
+      "epoch": 0.07562729001437782,
+      "grad_norm": 4.402633190155029,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.7333,
+      "step": 8153
+    },
+    {
+      "epoch": 0.07591484625017393,
+      "grad_norm": 0.5842500329017639,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.7354,
+      "step": 8184
+    },
+    {
+      "epoch": 0.07620240248597004,
+      "grad_norm": 0.6811164021492004,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.7281,
+      "step": 8215
+    },
+    {
+      "epoch": 0.07648995872176616,
+      "grad_norm": 0.8114293217658997,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.7371,
+      "step": 8246
+    },
+    {
+      "epoch": 0.07677751495756227,
+      "grad_norm": 0.6718847751617432,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.7271,
+      "step": 8277
+    },
+    {
+      "epoch": 0.07706507119335838,
+      "grad_norm": 0.6244426965713501,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.7264,
+      "step": 8308
+    },
+    {
+      "epoch": 0.0773526274291545,
+      "grad_norm": 0.8671194911003113,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.7345,
+      "step": 8339
+    },
+    {
+      "epoch": 0.07764018366495061,
+      "grad_norm": 0.5993788838386536,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.7174,
+      "step": 8370
+    },
+    {
+      "epoch": 0.07792773990074672,
+      "grad_norm": 0.6373441815376282,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.7337,
+      "step": 8401
+    },
+    {
+      "epoch": 0.07821529613654284,
+      "grad_norm": 0.6656855344772339,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.7277,
+      "step": 8432
+    },
+    {
+      "epoch": 0.07850285237233895,
+      "grad_norm": 0.6019161939620972,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.7289,
+      "step": 8463
+    },
+    {
+      "epoch": 0.07879040860813506,
+      "grad_norm": 0.6489233374595642,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.7225,
+      "step": 8494
+    },
+    {
+      "epoch": 0.07907796484393118,
+      "grad_norm": 0.5784976482391357,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.7311,
+      "step": 8525
+    },
+    {
+      "epoch": 0.07936552107972729,
+      "grad_norm": 0.6519568562507629,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.7216,
+      "step": 8556
+    },
+    {
+      "epoch": 0.0796530773155234,
+      "grad_norm": 0.6497238278388977,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.7208,
+      "step": 8587
+    },
+    {
+      "epoch": 0.07994063355131951,
+      "grad_norm": 0.629414439201355,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.728,
+      "step": 8618
+    },
+    {
+      "epoch": 0.08022818978711563,
+      "grad_norm": 0.6700971126556396,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.7253,
+      "step": 8649
+    },
+    {
+      "epoch": 0.08051574602291174,
+      "grad_norm": 0.6660225987434387,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.7287,
+      "step": 8680
+    },
+    {
+      "epoch": 0.08080330225870785,
+      "grad_norm": 0.6064980626106262,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.7242,
+      "step": 8711
+    },
+    {
+      "epoch": 0.08109085849450397,
+      "grad_norm": 0.66336590051651,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.7261,
+      "step": 8742
+    },
+    {
+      "epoch": 0.08137841473030008,
+      "grad_norm": 0.6016912460327148,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.726,
+      "step": 8773
+    },
+    {
+      "epoch": 0.0816659709660962,
+      "grad_norm": 0.6544851064682007,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.7324,
+      "step": 8804
+    },
+    {
+      "epoch": 0.0819535272018923,
+      "grad_norm": 0.721031904220581,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.717,
+      "step": 8835
+    },
+    {
+      "epoch": 0.08224108343768842,
+      "grad_norm": 0.6204259395599365,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.7178,
+      "step": 8866
+    },
+    {
+      "epoch": 0.08252863967348453,
+      "grad_norm": 0.665336012840271,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.7367,
+      "step": 8897
+    },
+    {
+      "epoch": 0.08281619590928065,
+      "grad_norm": 0.6388088464736938,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.7249,
+      "step": 8928
+    },
+    {
+      "epoch": 0.08310375214507676,
+      "grad_norm": 0.6215826272964478,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.7239,
+      "step": 8959
+    },
+    {
+      "epoch": 0.08339130838087287,
+      "grad_norm": 0.6228152513504028,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.7255,
+      "step": 8990
+    },
+    {
+      "epoch": 0.08367886461666899,
+      "grad_norm": 0.6137133240699768,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.7286,
+      "step": 9021
+    },
+    {
+      "epoch": 0.0839664208524651,
+      "grad_norm": 0.5644983053207397,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.7352,
+      "step": 9052
+    },
+    {
+      "epoch": 0.08425397708826121,
+      "grad_norm": 0.6456722021102905,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.7273,
+      "step": 9083
+    },
+    {
+      "epoch": 0.08454153332405732,
+      "grad_norm": 0.618363618850708,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.7136,
+      "step": 9114
+    },
+    {
+      "epoch": 0.08482908955985344,
+      "grad_norm": 0.521994948387146,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.7086,
+      "step": 9145
+    },
+    {
+      "epoch": 0.08511664579564955,
+      "grad_norm": 0.723540186882019,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.7183,
+      "step": 9176
+    },
+    {
+      "epoch": 0.08540420203144566,
+      "grad_norm": 0.6049785614013672,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.7174,
+      "step": 9207
+    },
+    {
+      "epoch": 0.08569175826724178,
+      "grad_norm": 0.5865082740783691,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.7075,
+      "step": 9238
+    },
+    {
+      "epoch": 0.08597931450303789,
+      "grad_norm": 0.657616913318634,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.7251,
+      "step": 9269
+    },
+    {
+      "epoch": 0.086266870738834,
+      "grad_norm": 0.5859720706939697,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.7179,
+      "step": 9300
+    },
+    {
+      "epoch": 0.08655442697463012,
+      "grad_norm": 0.6350371241569519,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.728,
+      "step": 9331
+    },
+    {
+      "epoch": 0.08684198321042623,
+      "grad_norm": 0.5636146664619446,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.7269,
+      "step": 9362
+    },
+    {
+      "epoch": 0.08712953944622234,
+      "grad_norm": 0.52867192029953,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.7134,
+      "step": 9393
+    },
+    {
+      "epoch": 0.08741709568201846,
+      "grad_norm": 0.6418184638023376,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.7234,
+      "step": 9424
+    },
+    {
+      "epoch": 0.08770465191781457,
+      "grad_norm": 0.602602481842041,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.7157,
+      "step": 9455
+    },
+    {
+      "epoch": 0.08799220815361068,
+      "grad_norm": 0.6151993274688721,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.7154,
+      "step": 9486
+    },
+    {
+      "epoch": 0.0882797643894068,
+      "grad_norm": 0.6821918487548828,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.7128,
+      "step": 9517
+    },
+    {
+      "epoch": 0.08856732062520291,
+      "grad_norm": 0.5447763204574585,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.7232,
+      "step": 9548
+    },
+    {
+      "epoch": 0.08885487686099902,
+      "grad_norm": 0.6219198703765869,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.7171,
+      "step": 9579
+    },
+    {
+      "epoch": 0.08914243309679513,
+      "grad_norm": 0.57777339220047,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.7105,
+      "step": 9610
+    },
+    {
+      "epoch": 0.08942998933259125,
+      "grad_norm": 0.5366658568382263,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.7148,
+      "step": 9641
+    },
+    {
+      "epoch": 0.08971754556838736,
+      "grad_norm": 0.5971750020980835,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.7077,
+      "step": 9672
+    },
+    {
+      "epoch": 0.09000510180418347,
+      "grad_norm": 0.5600515007972717,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.7105,
+      "step": 9703
+    },
+    {
+      "epoch": 0.09029265803997959,
+      "grad_norm": 0.6229792237281799,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.7161,
+      "step": 9734
+    },
+    {
+      "epoch": 0.0905802142757757,
+      "grad_norm": 0.7581937313079834,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.7227,
+      "step": 9765
+    },
+    {
+      "epoch": 0.09086777051157181,
+      "grad_norm": 0.6748283505439758,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.7058,
+      "step": 9796
+    },
+    {
+      "epoch": 0.09115532674736793,
+      "grad_norm": 0.5807577967643738,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.7237,
+      "step": 9827
+    },
+    {
+      "epoch": 0.09144288298316404,
+      "grad_norm": 0.6818577647209167,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.7177,
+      "step": 9858
+    },
+    {
+      "epoch": 0.09173043921896017,
+      "grad_norm": 0.5779188275337219,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.7154,
+      "step": 9889
+    },
+    {
+      "epoch": 0.09201799545475628,
+      "grad_norm": 0.6254588961601257,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.7116,
+      "step": 9920
+    },
+    {
+      "epoch": 0.09230555169055239,
+      "grad_norm": 0.6518847942352295,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.7145,
+      "step": 9951
+    },
+    {
+      "epoch": 0.0925931079263485,
+      "grad_norm": 0.6086714863777161,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.7126,
+      "step": 9982
+    },
+    {
+      "epoch": 0.09288066416214462,
+      "grad_norm": 0.750381588935852,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.7391,
+      "step": 10013
+    },
+    {
+      "epoch": 0.09316822039794073,
+      "grad_norm": 0.7088913321495056,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.7116,
+      "step": 10044
+    },
+    {
+      "epoch": 0.09345577663373685,
+      "grad_norm": 0.6793993711471558,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.7124,
+      "step": 10075
+    },
+    {
+      "epoch": 0.09374333286953296,
+      "grad_norm": 0.6571323871612549,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.7199,
+      "step": 10106
+    },
+    {
+      "epoch": 0.09403088910532907,
+      "grad_norm": 0.6068087816238403,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.725,
+      "step": 10137
+    },
+    {
+      "epoch": 0.09431844534112518,
+      "grad_norm": 0.5739994049072266,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.7013,
+      "step": 10168
+    },
+    {
+      "epoch": 0.0946060015769213,
+      "grad_norm": 0.5300189256668091,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.7241,
+      "step": 10199
+    },
+    {
+      "epoch": 0.09489355781271741,
+      "grad_norm": 0.6328433752059937,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.7111,
+      "step": 10230
+    },
+    {
+      "epoch": 0.09518111404851352,
+      "grad_norm": 0.6738958358764648,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.7106,
+      "step": 10261
+    },
+    {
+      "epoch": 0.09546867028430964,
+      "grad_norm": 0.573836624622345,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.7178,
+      "step": 10292
+    },
+    {
+      "epoch": 0.09575622652010575,
+      "grad_norm": 0.5532362461090088,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.7084,
+      "step": 10323
+    },
+    {
+      "epoch": 0.09604378275590186,
+      "grad_norm": 0.75803142786026,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.7084,
+      "step": 10354
+    },
+    {
+      "epoch": 0.09633133899169798,
+      "grad_norm": 0.6860505938529968,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.7016,
+      "step": 10385
+    },
+    {
+      "epoch": 0.09661889522749409,
+      "grad_norm": 0.6912726759910583,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.7278,
+      "step": 10416
+    },
+    {
+      "epoch": 0.0969064514632902,
+      "grad_norm": 0.626269519329071,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.7146,
+      "step": 10447
+    },
+    {
+      "epoch": 0.09719400769908632,
+      "grad_norm": 0.5607821941375732,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.7157,
+      "step": 10478
+    },
+    {
+      "epoch": 0.09748156393488243,
+      "grad_norm": 0.5527504682540894,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.7103,
+      "step": 10509
+    },
+    {
+      "epoch": 0.09776912017067854,
+      "grad_norm": 0.6478459239006042,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.7147,
+      "step": 10540
+    },
+    {
+      "epoch": 0.09805667640647465,
+      "grad_norm": 0.6617260575294495,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.7181,
+      "step": 10571
+    },
+    {
+      "epoch": 0.09834423264227077,
+      "grad_norm": 0.5579579472541809,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.7155,
+      "step": 10602
+    },
+    {
+      "epoch": 0.09863178887806688,
+      "grad_norm": 0.6320039629936218,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.7049,
+      "step": 10633
+    },
+    {
+      "epoch": 0.098919345113863,
+      "grad_norm": 0.5697253942489624,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.7127,
+      "step": 10664
+    },
+    {
+      "epoch": 0.09920690134965911,
+      "grad_norm": 0.5650231242179871,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.7051,
+      "step": 10695
+    },
+    {
+      "epoch": 0.09949445758545522,
+      "grad_norm": 0.6272993087768555,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.7119,
+      "step": 10726
+    },
+    {
+      "epoch": 0.09978201382125133,
+      "grad_norm": 0.6033383011817932,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.706,
+      "step": 10757
+    },
+    {
+      "epoch": 0.10006957005704745,
+      "grad_norm": 0.5815847516059875,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.7186,
+      "step": 10788
+    },
+    {
+      "epoch": 0.10035712629284356,
+      "grad_norm": 0.5461300611495972,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.7125,
+      "step": 10819
+    },
+    {
+      "epoch": 0.10064468252863967,
+      "grad_norm": 0.5513074398040771,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.7055,
+      "step": 10850
+    },
+    {
+      "epoch": 0.10093223876443579,
+      "grad_norm": 0.6083746552467346,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.7324,
+      "step": 10881
+    },
+    {
+      "epoch": 0.1012197950002319,
+      "grad_norm": 0.5546435117721558,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.6997,
+      "step": 10912
+    },
+    {
+      "epoch": 0.10150735123602801,
+      "grad_norm": 0.601056694984436,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.7087,
+      "step": 10943
+    },
+    {
+      "epoch": 0.10179490747182413,
+      "grad_norm": 0.6214995980262756,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.729,
+      "step": 10974
+    },
+    {
+      "epoch": 0.10208246370762024,
+      "grad_norm": 0.5371711850166321,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.708,
+      "step": 11005
+    },
+    {
+      "epoch": 0.10237001994341635,
+      "grad_norm": 0.5961845517158508,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.7047,
+      "step": 11036
+    },
+    {
+      "epoch": 0.10265757617921246,
+      "grad_norm": 0.6839886903762817,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.7126,
+      "step": 11067
+    },
+    {
+      "epoch": 0.10294513241500858,
+      "grad_norm": 0.6624526977539062,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.7085,
+      "step": 11098
+    },
+    {
+      "epoch": 0.10323268865080469,
+      "grad_norm": 0.5941864848136902,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.7055,
+      "step": 11129
+    },
+    {
+      "epoch": 0.1035202448866008,
+      "grad_norm": 0.6362475156784058,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.7229,
+      "step": 11160
+    },
+    {
+      "epoch": 0.10380780112239692,
+      "grad_norm": 0.5098447799682617,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.7116,
+      "step": 11191
+    },
+    {
+      "epoch": 0.10409535735819303,
+      "grad_norm": 0.5661705136299133,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.7043,
+      "step": 11222
+    },
+    {
+      "epoch": 0.10438291359398914,
+      "grad_norm": 0.6132655143737793,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.7066,
+      "step": 11253
+    },
+    {
+      "epoch": 0.10467046982978526,
+      "grad_norm": 0.6077197790145874,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.7062,
+      "step": 11284
+    },
+    {
+      "epoch": 0.10495802606558137,
+      "grad_norm": 0.5256394147872925,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.7053,
+      "step": 11315
+    },
+    {
+      "epoch": 0.10524558230137748,
+      "grad_norm": 0.5592128038406372,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.7057,
+      "step": 11346
+    },
+    {
+      "epoch": 0.1055331385371736,
+      "grad_norm": 0.4883192777633667,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.6976,
+      "step": 11377
+    },
+    {
+      "epoch": 0.10582069477296971,
+      "grad_norm": 0.7926296591758728,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.6941,
+      "step": 11408
+    },
+    {
+      "epoch": 0.10610825100876582,
+      "grad_norm": 0.6039475202560425,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.7062,
+      "step": 11439
+    },
+    {
+      "epoch": 0.10639580724456194,
+      "grad_norm": 0.5560294985771179,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.6908,
+      "step": 11470
+    },
+    {
+      "epoch": 0.10668336348035805,
+      "grad_norm": 0.5322378277778625,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.7005,
+      "step": 11501
+    },
+    {
+      "epoch": 0.10697091971615416,
+      "grad_norm": 0.5655946135520935,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.7038,
+      "step": 11532
+    },
+    {
+      "epoch": 0.10725847595195027,
+      "grad_norm": 0.6242902278900146,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.7151,
+      "step": 11563
+    },
+    {
+      "epoch": 0.10754603218774639,
+      "grad_norm": 0.5343348383903503,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.7112,
+      "step": 11594
+    },
+    {
+      "epoch": 0.1078335884235425,
+      "grad_norm": 0.5832471251487732,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.695,
+      "step": 11625
+    },
+    {
+      "epoch": 0.10812114465933861,
+      "grad_norm": 0.6098005771636963,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.6952,
+      "step": 11656
+    },
+    {
+      "epoch": 0.10840870089513474,
+      "grad_norm": 0.6541092395782471,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.7094,
+      "step": 11687
+    },
+    {
+      "epoch": 0.10869625713093085,
+      "grad_norm": 0.5949205160140991,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.7146,
+      "step": 11718
+    },
+    {
+      "epoch": 0.10898381336672697,
+      "grad_norm": 0.5494295954704285,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.7019,
+      "step": 11749
+    },
+    {
+      "epoch": 0.10927136960252308,
+      "grad_norm": 0.5022011995315552,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.7023,
+      "step": 11780
+    },
+    {
+      "epoch": 0.1095589258383192,
+      "grad_norm": 0.6179025173187256,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.7083,
+      "step": 11811
+    },
+    {
+      "epoch": 0.1098464820741153,
+      "grad_norm": 0.5961601734161377,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.7037,
+      "step": 11842
+    },
+    {
+      "epoch": 0.11013403830991142,
+      "grad_norm": 0.6176908612251282,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.6984,
+      "step": 11873
+    },
+    {
+      "epoch": 0.11042159454570753,
+      "grad_norm": 0.5871501564979553,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.6938,
+      "step": 11904
+    },
+    {
+      "epoch": 0.11070915078150365,
+      "grad_norm": 0.5729032754898071,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.6976,
+      "step": 11935
+    },
+    {
+      "epoch": 0.11099670701729976,
+      "grad_norm": 0.6106701493263245,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.6922,
+      "step": 11966
+    },
+    {
+      "epoch": 0.11128426325309587,
+      "grad_norm": 0.604791522026062,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.6963,
+      "step": 11997
+    },
+    {
+      "epoch": 0.11157181948889199,
+      "grad_norm": 0.6141258478164673,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.7048,
+      "step": 12028
+    },
+    {
+      "epoch": 0.1118593757246881,
+      "grad_norm": 0.5770751237869263,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.6976,
+      "step": 12059
+    },
+    {
+      "epoch": 0.11214693196048421,
+      "grad_norm": 0.6507471203804016,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.7133,
+      "step": 12090
+    },
+    {
+      "epoch": 0.11243448819628032,
+      "grad_norm": 0.5432878732681274,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.7123,
+      "step": 12121
+    },
+    {
+      "epoch": 0.11272204443207644,
+      "grad_norm": 0.5892463326454163,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.7013,
+      "step": 12152
+    },
+    {
+      "epoch": 0.11300960066787255,
+      "grad_norm": 0.5415503978729248,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.7096,
+      "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 sha256:0a811c1ee32ac5fb3baeb7b42fe04c2c91fcf0074b460464e158e3f772388342
+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 sha256:69bed2f8b4428154afa6cfc4735067a34a16b1a2290787772fb483e61a3c7ed8
+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:abd264641b15ccefcef43efbb6328ffd96ffdb9fc56e650dd256b9df684bcd61
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091def6cabee884395bebd2c686e1b41281f6fd74af19b1fabc16c98d7b43d55
+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 sha256:79c9cc373ba4a749afcddaeef25458100168c5b219d4d756f04aa4e30d3da2a9
+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": 0.14155187607253839,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00028755623579611333,
+      "grad_norm": 2.5471084117889404,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.2071,
+      "step": 31
+    },
+    {
+      "epoch": 0.0005751124715922267,
+      "grad_norm": 1.500440001487732,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.126,
+      "step": 62
+    },
+    {
+      "epoch": 0.0008626687073883401,
+      "grad_norm": 1.54880690574646,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.1015,
+      "step": 93
+    },
+    {
+      "epoch": 0.0011502249431844533,
+      "grad_norm": 1.6134709119796753,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.0761,
+      "step": 124
+    },
+    {
+      "epoch": 0.0014377811789805669,
+      "grad_norm": 1.824180006980896,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.0642,
+      "step": 155
+    },
+    {
+      "epoch": 0.0017253374147766802,
+      "grad_norm": 1.415733814239502,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.0362,
+      "step": 186
+    },
+    {
+      "epoch": 0.0020128936505727935,
+      "grad_norm": 1.728509783744812,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.044,
+      "step": 217
+    },
+    {
+      "epoch": 0.0023004498863689066,
+      "grad_norm": 1.602379560470581,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.0404,
+      "step": 248
+    },
+    {
+      "epoch": 0.00258800612216502,
+      "grad_norm": 1.8858306407928467,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.0212,
+      "step": 279
+    },
+    {
+      "epoch": 0.0028755623579611337,
+      "grad_norm": 2.285231351852417,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.0032,
+      "step": 310
+    },
+    {
+      "epoch": 0.003163118593757247,
+      "grad_norm": 1.8043686151504517,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.0031,
+      "step": 341
+    },
+    {
+      "epoch": 0.0034506748295533604,
+      "grad_norm": 1.870897889137268,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.0058,
+      "step": 372
+    },
+    {
+      "epoch": 0.0037382310653494735,
+      "grad_norm": 2.116208791732788,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.0007,
+      "step": 403
+    },
+    {
+      "epoch": 0.004025787301145587,
+      "grad_norm": 2.0111632347106934,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 0.9923,
+      "step": 434
+    },
+    {
+      "epoch": 0.0043133435369417,
+      "grad_norm": 1.7982046604156494,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 0.9867,
+      "step": 465
+    },
+    {
+      "epoch": 0.004600899772737813,
+      "grad_norm": 2.007441759109497,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 0.978,
+      "step": 496
+    },
+    {
+      "epoch": 0.004888456008533927,
+      "grad_norm": 2.805020809173584,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 0.9794,
+      "step": 527
+    },
+    {
+      "epoch": 0.00517601224433004,
+      "grad_norm": 2.376081943511963,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 0.9587,
+      "step": 558
+    },
+    {
+      "epoch": 0.0054635684801261535,
+      "grad_norm": 2.0517630577087402,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 0.9697,
+      "step": 589
+    },
+    {
+      "epoch": 0.0057511247159222675,
+      "grad_norm": 1.7311242818832397,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 0.9582,
+      "step": 620
+    },
+    {
+      "epoch": 0.006038680951718381,
+      "grad_norm": 1.533537745475769,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 0.9561,
+      "step": 651
+    },
+    {
+      "epoch": 0.006326237187514494,
+      "grad_norm": 1.5506970882415771,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 0.951,
+      "step": 682
+    },
+    {
+      "epoch": 0.006613793423310607,
+      "grad_norm": 2.716867685317993,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 0.9511,
+      "step": 713
+    },
+    {
+      "epoch": 0.006901349659106721,
+      "grad_norm": 2.3463616371154785,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 0.9538,
+      "step": 744
+    },
+    {
+      "epoch": 0.007188905894902834,
+      "grad_norm": 1.54783034324646,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.9528,
+      "step": 775
+    },
+    {
+      "epoch": 0.007476462130698947,
+      "grad_norm": 1.2869651317596436,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.944,
+      "step": 806
+    },
+    {
+      "epoch": 0.00776401836649506,
+      "grad_norm": 1.3865717649459839,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.9342,
+      "step": 837
+    },
+    {
+      "epoch": 0.008051574602291174,
+      "grad_norm": 1.8173962831497192,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.94,
+      "step": 868
+    },
+    {
+      "epoch": 0.008339130838087287,
+      "grad_norm": 1.6419012546539307,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.9251,
+      "step": 899
+    },
+    {
+      "epoch": 0.0086266870738834,
+      "grad_norm": 1.5133196115493774,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.9252,
+      "step": 930
+    },
+    {
+      "epoch": 0.008914243309679513,
+      "grad_norm": 1.91935133934021,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.9363,
+      "step": 961
+    },
+    {
+      "epoch": 0.009201799545475627,
+      "grad_norm": 1.592256784439087,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.922,
+      "step": 992
+    },
+    {
+      "epoch": 0.009489355781271741,
+      "grad_norm": 2.3662896156311035,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.922,
+      "step": 1023
+    },
+    {
+      "epoch": 0.009776912017067855,
+      "grad_norm": 2.121152639389038,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.9425,
+      "step": 1054
+    },
+    {
+      "epoch": 0.010064468252863968,
+      "grad_norm": 1.389515995979309,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.913,
+      "step": 1085
+    },
+    {
+      "epoch": 0.01035202448866008,
+      "grad_norm": 1.4310904741287231,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.9201,
+      "step": 1116
+    },
+    {
+      "epoch": 0.010639580724456194,
+      "grad_norm": 1.5803974866867065,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.9261,
+      "step": 1147
+    },
+    {
+      "epoch": 0.010927136960252307,
+      "grad_norm": 1.2364155054092407,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.9076,
+      "step": 1178
+    },
+    {
+      "epoch": 0.01121469319604842,
+      "grad_norm": 1.4545661211013794,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.9108,
+      "step": 1209
+    },
+    {
+      "epoch": 0.011502249431844535,
+      "grad_norm": 1.3160631656646729,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.909,
+      "step": 1240
+    },
+    {
+      "epoch": 0.011789805667640648,
+      "grad_norm": 1.512214183807373,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.8876,
+      "step": 1271
+    },
+    {
+      "epoch": 0.012077361903436761,
+      "grad_norm": 1.4180532693862915,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.8976,
+      "step": 1302
+    },
+    {
+      "epoch": 0.012364918139232874,
+      "grad_norm": 1.4778006076812744,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.8923,
+      "step": 1333
+    },
+    {
+      "epoch": 0.012652474375028987,
+      "grad_norm": 1.8094278573989868,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.9106,
+      "step": 1364
+    },
+    {
+      "epoch": 0.0129400306108251,
+      "grad_norm": 1.361230492591858,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.9017,
+      "step": 1395
+    },
+    {
+      "epoch": 0.013227586846621214,
+      "grad_norm": 1.2361464500427246,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.8999,
+      "step": 1426
+    },
+    {
+      "epoch": 0.013515143082417327,
+      "grad_norm": 1.641925573348999,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.9001,
+      "step": 1457
+    },
+    {
+      "epoch": 0.013802699318213442,
+      "grad_norm": 15.032498359680176,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.957,
+      "step": 1488
+    },
+    {
+      "epoch": 0.014090255554009555,
+      "grad_norm": 1.2676361799240112,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.9501,
+      "step": 1519
+    },
+    {
+      "epoch": 0.014377811789805668,
+      "grad_norm": 1.5450263023376465,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.9151,
+      "step": 1550
+    },
+    {
+      "epoch": 0.014665368025601781,
+      "grad_norm": 1.4152264595031738,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.906,
+      "step": 1581
+    },
+    {
+      "epoch": 0.014952924261397894,
+      "grad_norm": 1.250949740409851,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.9053,
+      "step": 1612
+    },
+    {
+      "epoch": 0.015240480497194007,
+      "grad_norm": 1.3265453577041626,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.9006,
+      "step": 1643
+    },
+    {
+      "epoch": 0.01552803673299012,
+      "grad_norm": 1.1016136407852173,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.8853,
+      "step": 1674
+    },
+    {
+      "epoch": 0.015815592968786235,
+      "grad_norm": 1.6496962308883667,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.8824,
+      "step": 1705
+    },
+    {
+      "epoch": 0.016103149204582348,
+      "grad_norm": 2.5228922367095947,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.883,
+      "step": 1736
+    },
+    {
+      "epoch": 0.01639070544037846,
+      "grad_norm": 1.1221877336502075,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.8668,
+      "step": 1767
+    },
+    {
+      "epoch": 0.016678261676174574,
+      "grad_norm": 1.4403537511825562,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.8819,
+      "step": 1798
+    },
+    {
+      "epoch": 0.016965817911970688,
+      "grad_norm": 1.2584978342056274,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.864,
+      "step": 1829
+    },
+    {
+      "epoch": 0.0172533741477668,
+      "grad_norm": 1.2469295263290405,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.8709,
+      "step": 1860
+    },
+    {
+      "epoch": 0.017540930383562914,
+      "grad_norm": 1.2993371486663818,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.8763,
+      "step": 1891
+    },
+    {
+      "epoch": 0.017828486619359027,
+      "grad_norm": 1.3034465312957764,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.8742,
+      "step": 1922
+    },
+    {
+      "epoch": 0.01811604285515514,
+      "grad_norm": 0.9507549405097961,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.8685,
+      "step": 1953
+    },
+    {
+      "epoch": 0.018403599090951253,
+      "grad_norm": 1.2451794147491455,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.8574,
+      "step": 1984
+    },
+    {
+      "epoch": 0.018691155326747366,
+      "grad_norm": 0.9359011054039001,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.8518,
+      "step": 2015
+    },
+    {
+      "epoch": 0.018978711562543483,
+      "grad_norm": 0.9871286749839783,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.8681,
+      "step": 2046
+    },
+    {
+      "epoch": 0.019266267798339596,
+      "grad_norm": 0.9597110152244568,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.8561,
+      "step": 2077
+    },
+    {
+      "epoch": 0.01955382403413571,
+      "grad_norm": 1.7902615070343018,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.8597,
+      "step": 2108
+    },
+    {
+      "epoch": 0.019841380269931822,
+      "grad_norm": 0.9376184940338135,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.8589,
+      "step": 2139
+    },
+    {
+      "epoch": 0.020128936505727935,
+      "grad_norm": 0.9978942275047302,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.8537,
+      "step": 2170
+    },
+    {
+      "epoch": 0.02041649274152405,
+      "grad_norm": 0.8389673233032227,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.8565,
+      "step": 2201
+    },
+    {
+      "epoch": 0.02070404897732016,
+      "grad_norm": 1.0237621068954468,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.844,
+      "step": 2232
+    },
+    {
+      "epoch": 0.020991605213116275,
+      "grad_norm": 1.0087332725524902,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.8382,
+      "step": 2263
+    },
+    {
+      "epoch": 0.021279161448912388,
+      "grad_norm": 1.0753614902496338,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.8276,
+      "step": 2294
+    },
+    {
+      "epoch": 0.0215667176847085,
+      "grad_norm": 1.0078065395355225,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.84,
+      "step": 2325
+    },
+    {
+      "epoch": 0.021854273920504614,
+      "grad_norm": 0.8615468740463257,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.8462,
+      "step": 2356
+    },
+    {
+      "epoch": 0.022141830156300727,
+      "grad_norm": 1.0752439498901367,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.8335,
+      "step": 2387
+    },
+    {
+      "epoch": 0.02242938639209684,
+      "grad_norm": 1.1604725122451782,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.8368,
+      "step": 2418
+    },
+    {
+      "epoch": 0.022716942627892953,
+      "grad_norm": 1.084244966506958,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.8341,
+      "step": 2449
+    },
+    {
+      "epoch": 0.02300449886368907,
+      "grad_norm": 0.9928577542304993,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.8312,
+      "step": 2480
+    },
+    {
+      "epoch": 0.023292055099485183,
+      "grad_norm": 1.2830171585083008,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.8415,
+      "step": 2511
+    },
+    {
+      "epoch": 0.023579611335281296,
+      "grad_norm": 0.733214795589447,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.8526,
+      "step": 2542
+    },
+    {
+      "epoch": 0.02386716757107741,
+      "grad_norm": 0.7755644917488098,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.8382,
+      "step": 2573
+    },
+    {
+      "epoch": 0.024154723806873522,
+      "grad_norm": 1.127175211906433,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.8321,
+      "step": 2604
+    },
+    {
+      "epoch": 0.024442280042669635,
+      "grad_norm": 0.6953925490379333,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.8153,
+      "step": 2635
+    },
+    {
+      "epoch": 0.02472983627846575,
+      "grad_norm": 0.8521370887756348,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.8232,
+      "step": 2666
+    },
+    {
+      "epoch": 0.02501739251426186,
+      "grad_norm": 0.8186238408088684,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.8172,
+      "step": 2697
+    },
+    {
+      "epoch": 0.025304948750057975,
+      "grad_norm": 0.7999460697174072,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.8157,
+      "step": 2728
+    },
+    {
+      "epoch": 0.025592504985854088,
+      "grad_norm": 1.0013262033462524,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.8269,
+      "step": 2759
+    },
+    {
+      "epoch": 0.0258800612216502,
+      "grad_norm": 0.910980761051178,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.8251,
+      "step": 2790
+    },
+    {
+      "epoch": 0.026167617457446314,
+      "grad_norm": 0.9238119125366211,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.8058,
+      "step": 2821
+    },
+    {
+      "epoch": 0.026455173693242427,
+      "grad_norm": 0.9186171889305115,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.8102,
+      "step": 2852
+    },
+    {
+      "epoch": 0.02674272992903854,
+      "grad_norm": 0.7005239725112915,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.8188,
+      "step": 2883
+    },
+    {
+      "epoch": 0.027030286164834653,
+      "grad_norm": 0.7916774153709412,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.8204,
+      "step": 2914
+    },
+    {
+      "epoch": 0.02731784240063077,
+      "grad_norm": 0.9498996138572693,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.8122,
+      "step": 2945
+    },
+    {
+      "epoch": 0.027605398636426883,
+      "grad_norm": 0.7997952699661255,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.8193,
+      "step": 2976
+    },
+    {
+      "epoch": 0.027892954872222996,
+      "grad_norm": 0.8657526969909668,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.8258,
+      "step": 3007
+    },
+    {
+      "epoch": 0.02818051110801911,
+      "grad_norm": 0.8351128697395325,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.8054,
+      "step": 3038
+    },
+    {
+      "epoch": 0.028468067343815222,
+      "grad_norm": 0.8679622411727905,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.8081,
+      "step": 3069
+    },
+    {
+      "epoch": 0.028755623579611336,
+      "grad_norm": 0.7777401208877563,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.8028,
+      "step": 3100
+    },
+    {
+      "epoch": 0.02904317981540745,
+      "grad_norm": 0.859012246131897,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.8152,
+      "step": 3131
+    },
+    {
+      "epoch": 0.029330736051203562,
+      "grad_norm": 0.7595569491386414,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.8082,
+      "step": 3162
+    },
+    {
+      "epoch": 0.029618292286999675,
+      "grad_norm": 0.8339647650718689,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.8113,
+      "step": 3193
+    },
+    {
+      "epoch": 0.029905848522795788,
+      "grad_norm": 0.8242756128311157,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.8143,
+      "step": 3224
+    },
+    {
+      "epoch": 0.0301934047585919,
+      "grad_norm": 0.9011533856391907,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.8015,
+      "step": 3255
+    },
+    {
+      "epoch": 0.030480960994388014,
+      "grad_norm": 1.2543679475784302,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.8004,
+      "step": 3286
+    },
+    {
+      "epoch": 0.030768517230184127,
+      "grad_norm": 0.8444302678108215,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.8082,
+      "step": 3317
+    },
+    {
+      "epoch": 0.03105607346598024,
+      "grad_norm": 0.8438568711280823,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.7892,
+      "step": 3348
+    },
+    {
+      "epoch": 0.03134362970177636,
+      "grad_norm": 0.9470321536064148,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.7998,
+      "step": 3379
+    },
+    {
+      "epoch": 0.03163118593757247,
+      "grad_norm": 0.7611345648765564,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.7975,
+      "step": 3410
+    },
+    {
+      "epoch": 0.03191874217336858,
+      "grad_norm": 1.0148237943649292,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.8079,
+      "step": 3441
+    },
+    {
+      "epoch": 0.032206298409164696,
+      "grad_norm": 0.6824489235877991,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.7875,
+      "step": 3472
+    },
+    {
+      "epoch": 0.03249385464496081,
+      "grad_norm": 0.7495407462120056,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.7936,
+      "step": 3503
+    },
+    {
+      "epoch": 0.03278141088075692,
+      "grad_norm": 0.6833623647689819,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.794,
+      "step": 3534
+    },
+    {
+      "epoch": 0.033068967116553036,
+      "grad_norm": 0.6844274997711182,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.7944,
+      "step": 3565
+    },
+    {
+      "epoch": 0.03335652335234915,
+      "grad_norm": 0.7401015162467957,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.8006,
+      "step": 3596
+    },
+    {
+      "epoch": 0.03364407958814526,
+      "grad_norm": 1.0470607280731201,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.8011,
+      "step": 3627
+    },
+    {
+      "epoch": 0.033931635823941375,
+      "grad_norm": 0.7898035049438477,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.7995,
+      "step": 3658
+    },
+    {
+      "epoch": 0.03421919205973749,
+      "grad_norm": 0.772084653377533,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.7949,
+      "step": 3689
+    },
+    {
+      "epoch": 0.0345067482955336,
+      "grad_norm": 0.823618471622467,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.7891,
+      "step": 3720
+    },
+    {
+      "epoch": 0.034794304531329714,
+      "grad_norm": 0.8022550940513611,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.7796,
+      "step": 3751
+    },
+    {
+      "epoch": 0.03508186076712583,
+      "grad_norm": 0.7855663895606995,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.7913,
+      "step": 3782
+    },
+    {
+      "epoch": 0.03536941700292194,
+      "grad_norm": 0.6916162967681885,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.7948,
+      "step": 3813
+    },
+    {
+      "epoch": 0.035656973238718054,
+      "grad_norm": 0.7116622924804688,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.7937,
+      "step": 3844
+    },
+    {
+      "epoch": 0.03594452947451417,
+      "grad_norm": 0.6990245580673218,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.7894,
+      "step": 3875
+    },
+    {
+      "epoch": 0.03623208571031028,
+      "grad_norm": 0.7066308259963989,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.7836,
+      "step": 3906
+    },
+    {
+      "epoch": 0.03651964194610639,
+      "grad_norm": 0.6334872841835022,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.7961,
+      "step": 3937
+    },
+    {
+      "epoch": 0.036807198181902506,
+      "grad_norm": 0.8018898963928223,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.7962,
+      "step": 3968
+    },
+    {
+      "epoch": 0.03709475441769862,
+      "grad_norm": 0.8985097408294678,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.7847,
+      "step": 3999
+    },
+    {
+      "epoch": 0.03738231065349473,
+      "grad_norm": 0.7619264125823975,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.7882,
+      "step": 4030
+    },
+    {
+      "epoch": 0.03766986688929085,
+      "grad_norm": 0.6307808756828308,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.7761,
+      "step": 4061
+    },
+    {
+      "epoch": 0.037957423125086966,
+      "grad_norm": 0.6743819117546082,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.7869,
+      "step": 4092
+    },
+    {
+      "epoch": 0.03824497936088308,
+      "grad_norm": 0.7610074877738953,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.7768,
+      "step": 4123
+    },
+    {
+      "epoch": 0.03853253559667919,
+      "grad_norm": 0.653424084186554,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.7802,
+      "step": 4154
+    },
+    {
+      "epoch": 0.038820091832475305,
+      "grad_norm": 1.0586974620819092,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.7911,
+      "step": 4185
+    },
+    {
+      "epoch": 0.03910764806827142,
+      "grad_norm": 0.6271804571151733,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.7784,
+      "step": 4216
+    },
+    {
+      "epoch": 0.03939520430406753,
+      "grad_norm": 0.889215886592865,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.7721,
+      "step": 4247
+    },
+    {
+      "epoch": 0.039682760539863644,
+      "grad_norm": 0.7688327431678772,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.7859,
+      "step": 4278
+    },
+    {
+      "epoch": 0.03997031677565976,
+      "grad_norm": 0.8260688185691833,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.7719,
+      "step": 4309
+    },
+    {
+      "epoch": 0.04025787301145587,
+      "grad_norm": 0.7527140378952026,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.7833,
+      "step": 4340
+    },
+    {
+      "epoch": 0.040545429247251984,
+      "grad_norm": 0.7240214347839355,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.7806,
+      "step": 4371
+    },
+    {
+      "epoch": 0.0408329854830481,
+      "grad_norm": 0.7488278746604919,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.7893,
+      "step": 4402
+    },
+    {
+      "epoch": 0.04112054171884421,
+      "grad_norm": 0.7927774786949158,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.7867,
+      "step": 4433
+    },
+    {
+      "epoch": 0.04140809795464032,
+      "grad_norm": 0.6409322619438171,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.7764,
+      "step": 4464
+    },
+    {
+      "epoch": 0.041695654190436436,
+      "grad_norm": 0.6869925856590271,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.7861,
+      "step": 4495
+    },
+    {
+      "epoch": 0.04198321042623255,
+      "grad_norm": 0.8485197424888611,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.7826,
+      "step": 4526
+    },
+    {
+      "epoch": 0.04227076666202866,
+      "grad_norm": 0.6266471743583679,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.7658,
+      "step": 4557
+    },
+    {
+      "epoch": 0.042558322897824775,
+      "grad_norm": 0.8114103674888611,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.7775,
+      "step": 4588
+    },
+    {
+      "epoch": 0.04284587913362089,
+      "grad_norm": 0.698353111743927,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.7756,
+      "step": 4619
+    },
+    {
+      "epoch": 0.043133435369417,
+      "grad_norm": 0.6825971603393555,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.7716,
+      "step": 4650
+    },
+    {
+      "epoch": 0.043420991605213115,
+      "grad_norm": 0.8550017476081848,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.7813,
+      "step": 4681
+    },
+    {
+      "epoch": 0.04370854784100923,
+      "grad_norm": 0.7881748676300049,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.7661,
+      "step": 4712
+    },
+    {
+      "epoch": 0.04399610407680534,
+      "grad_norm": 0.7000054121017456,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.7648,
+      "step": 4743
+    },
+    {
+      "epoch": 0.044283660312601454,
+      "grad_norm": 0.727118194103241,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.7715,
+      "step": 4774
+    },
+    {
+      "epoch": 0.04457121654839757,
+      "grad_norm": 0.6390218138694763,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.7684,
+      "step": 4805
+    },
+    {
+      "epoch": 0.04485877278419368,
+      "grad_norm": 0.8063361644744873,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.7654,
+      "step": 4836
+    },
+    {
+      "epoch": 0.045146329019989793,
+      "grad_norm": 0.7509976625442505,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.7701,
+      "step": 4867
+    },
+    {
+      "epoch": 0.04543388525578591,
+      "grad_norm": 0.6991444826126099,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.7679,
+      "step": 4898
+    },
+    {
+      "epoch": 0.04572144149158202,
+      "grad_norm": 0.835519552230835,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.7754,
+      "step": 4929
+    },
+    {
+      "epoch": 0.04600899772737814,
+      "grad_norm": 0.7925782203674316,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.7649,
+      "step": 4960
+    },
+    {
+      "epoch": 0.04629655396317425,
+      "grad_norm": 0.6192532777786255,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.7764,
+      "step": 4991
+    },
+    {
+      "epoch": 0.046584110198970366,
+      "grad_norm": 0.7094298005104065,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.7743,
+      "step": 5022
+    },
+    {
+      "epoch": 0.04687166643476648,
+      "grad_norm": 0.5982211232185364,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.7769,
+      "step": 5053
+    },
+    {
+      "epoch": 0.04715922267056259,
+      "grad_norm": 0.6520153284072876,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.7647,
+      "step": 5084
+    },
+    {
+      "epoch": 0.047446778906358705,
+      "grad_norm": 0.6328307390213013,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.7668,
+      "step": 5115
+    },
+    {
+      "epoch": 0.04773433514215482,
+      "grad_norm": 0.6715372204780579,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.77,
+      "step": 5146
+    },
+    {
+      "epoch": 0.04802189137795093,
+      "grad_norm": 0.6676992774009705,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.7692,
+      "step": 5177
+    },
+    {
+      "epoch": 0.048309447613747045,
+      "grad_norm": 0.7889059782028198,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.761,
+      "step": 5208
+    },
+    {
+      "epoch": 0.04859700384954316,
+      "grad_norm": 0.7142347097396851,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.7444,
+      "step": 5239
+    },
+    {
+      "epoch": 0.04888456008533927,
+      "grad_norm": 0.7596989274024963,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.7401,
+      "step": 5270
+    },
+    {
+      "epoch": 0.049172116321135384,
+      "grad_norm": 0.5763289928436279,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.7627,
+      "step": 5301
+    },
+    {
+      "epoch": 0.0494596725569315,
+      "grad_norm": 0.6867230534553528,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.7652,
+      "step": 5332
+    },
+    {
+      "epoch": 0.04974722879272761,
+      "grad_norm": 0.8485914468765259,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.7754,
+      "step": 5363
+    },
+    {
+      "epoch": 0.05003478502852372,
+      "grad_norm": 0.7543194890022278,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.7544,
+      "step": 5394
+    },
+    {
+      "epoch": 0.050322341264319836,
+      "grad_norm": 0.5923686623573303,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.7457,
+      "step": 5425
+    },
+    {
+      "epoch": 0.05060989750011595,
+      "grad_norm": 0.6586946249008179,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.7625,
+      "step": 5456
+    },
+    {
+      "epoch": 0.05089745373591206,
+      "grad_norm": 0.712864875793457,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.7451,
+      "step": 5487
+    },
+    {
+      "epoch": 0.051185009971708176,
+      "grad_norm": 0.7251986861228943,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.7532,
+      "step": 5518
+    },
+    {
+      "epoch": 0.05147256620750429,
+      "grad_norm": 0.747039258480072,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.7548,
+      "step": 5549
+    },
+    {
+      "epoch": 0.0517601224433004,
+      "grad_norm": 0.7192988395690918,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.7568,
+      "step": 5580
+    },
+    {
+      "epoch": 0.052047678679096515,
+      "grad_norm": 0.6581113934516907,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.7674,
+      "step": 5611
+    },
+    {
+      "epoch": 0.05233523491489263,
+      "grad_norm": 0.661508321762085,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.7538,
+      "step": 5642
+    },
+    {
+      "epoch": 0.05262279115068874,
+      "grad_norm": 0.8347408175468445,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.7714,
+      "step": 5673
+    },
+    {
+      "epoch": 0.052910347386484854,
+      "grad_norm": 0.6756936311721802,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.7443,
+      "step": 5704
+    },
+    {
+      "epoch": 0.05319790362228097,
+      "grad_norm": 0.6768369674682617,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.7389,
+      "step": 5735
+    },
+    {
+      "epoch": 0.05348545985807708,
+      "grad_norm": 0.6765073537826538,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.7443,
+      "step": 5766
+    },
+    {
+      "epoch": 0.053773016093873194,
+      "grad_norm": 0.7619781494140625,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.7496,
+      "step": 5797
+    },
+    {
+      "epoch": 0.05406057232966931,
+      "grad_norm": 0.7346686124801636,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.7512,
+      "step": 5828
+    },
+    {
+      "epoch": 0.05434812856546543,
+      "grad_norm": 0.7577638030052185,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.7561,
+      "step": 5859
+    },
+    {
+      "epoch": 0.05463568480126154,
+      "grad_norm": 0.6721853613853455,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.766,
+      "step": 5890
+    },
+    {
+      "epoch": 0.05492324103705765,
+      "grad_norm": 0.678697407245636,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.7665,
+      "step": 5921
+    },
+    {
+      "epoch": 0.055210797272853766,
+      "grad_norm": 0.7274826169013977,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.7431,
+      "step": 5952
+    },
+    {
+      "epoch": 0.05549835350864988,
+      "grad_norm": 0.6908119916915894,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.7408,
+      "step": 5983
+    },
+    {
+      "epoch": 0.05578590974444599,
+      "grad_norm": 0.734859049320221,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.7591,
+      "step": 6014
+    },
+    {
+      "epoch": 0.056073465980242106,
+      "grad_norm": 0.7401076555252075,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.756,
+      "step": 6045
+    },
+    {
+      "epoch": 0.05636102221603822,
+      "grad_norm": 0.7856413125991821,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.7465,
+      "step": 6076
+    },
+    {
+      "epoch": 0.05664857845183433,
+      "grad_norm": 0.6996341347694397,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.7421,
+      "step": 6107
+    },
+    {
+      "epoch": 0.056936134687630445,
+      "grad_norm": 0.7988335490226746,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.7524,
+      "step": 6138
+    },
+    {
+      "epoch": 0.05722369092342656,
+      "grad_norm": 0.68621426820755,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.7468,
+      "step": 6169
+    },
+    {
+      "epoch": 0.05751124715922267,
+      "grad_norm": 0.6664344072341919,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.7515,
+      "step": 6200
+    },
+    {
+      "epoch": 0.057798803395018784,
+      "grad_norm": 0.7224786281585693,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.7467,
+      "step": 6231
+    },
+    {
+      "epoch": 0.0580863596308149,
+      "grad_norm": 0.5921575427055359,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.7563,
+      "step": 6262
+    },
+    {
+      "epoch": 0.05837391586661101,
+      "grad_norm": 0.6673355102539062,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.7523,
+      "step": 6293
+    },
+    {
+      "epoch": 0.058661472102407124,
+      "grad_norm": 0.7031881809234619,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.7497,
+      "step": 6324
+    },
+    {
+      "epoch": 0.05894902833820324,
+      "grad_norm": 0.6450571417808533,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.7357,
+      "step": 6355
+    },
+    {
+      "epoch": 0.05923658457399935,
+      "grad_norm": 0.6376838684082031,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.7534,
+      "step": 6386
+    },
+    {
+      "epoch": 0.05952414080979546,
+      "grad_norm": 0.6044135689735413,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.7413,
+      "step": 6417
+    },
+    {
+      "epoch": 0.059811697045591576,
+      "grad_norm": 0.696363627910614,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.7573,
+      "step": 6448
+    },
+    {
+      "epoch": 0.06009925328138769,
+      "grad_norm": 1.9165210723876953,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.7553,
+      "step": 6479
+    },
+    {
+      "epoch": 0.0603868095171838,
+      "grad_norm": 1.0885388851165771,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.7611,
+      "step": 6510
+    },
+    {
+      "epoch": 0.060674365752979915,
+      "grad_norm": 0.8365141153335571,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.763,
+      "step": 6541
+    },
+    {
+      "epoch": 0.06096192198877603,
+      "grad_norm": 0.7544219493865967,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.747,
+      "step": 6572
+    },
+    {
+      "epoch": 0.06124947822457214,
+      "grad_norm": 0.821266233921051,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.7462,
+      "step": 6603
+    },
+    {
+      "epoch": 0.061537034460368255,
+      "grad_norm": 0.7296980023384094,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.7494,
+      "step": 6634
+    },
+    {
+      "epoch": 0.06182459069616437,
+      "grad_norm": 0.6230852007865906,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.7417,
+      "step": 6665
+    },
+    {
+      "epoch": 0.06211214693196048,
+      "grad_norm": 0.6954329013824463,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.7388,
+      "step": 6696
+    },
+    {
+      "epoch": 0.062399703167756594,
+      "grad_norm": 0.6082637906074524,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.7339,
+      "step": 6727
+    },
+    {
+      "epoch": 0.06268725940355271,
+      "grad_norm": 0.739402711391449,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.7433,
+      "step": 6758
+    },
+    {
+      "epoch": 0.06297481563934883,
+      "grad_norm": 0.6120406985282898,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.7457,
+      "step": 6789
+    },
+    {
+      "epoch": 0.06326237187514494,
+      "grad_norm": 0.6660128831863403,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.7497,
+      "step": 6820
+    },
+    {
+      "epoch": 0.06354992811094105,
+      "grad_norm": 0.7525910139083862,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.7531,
+      "step": 6851
+    },
+    {
+      "epoch": 0.06383748434673717,
+      "grad_norm": 0.7022217512130737,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.7448,
+      "step": 6882
+    },
+    {
+      "epoch": 0.06412504058253328,
+      "grad_norm": 0.8050118088722229,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.7584,
+      "step": 6913
+    },
+    {
+      "epoch": 0.06441259681832939,
+      "grad_norm": 0.7408604025840759,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.7355,
+      "step": 6944
+    },
+    {
+      "epoch": 0.0647001530541255,
+      "grad_norm": 0.6935440301895142,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.736,
+      "step": 6975
+    },
+    {
+      "epoch": 0.06498770928992162,
+      "grad_norm": 0.7600308060646057,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.7355,
+      "step": 7006
+    },
+    {
+      "epoch": 0.06527526552571773,
+      "grad_norm": 0.5767653584480286,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.7319,
+      "step": 7037
+    },
+    {
+      "epoch": 0.06556282176151385,
+      "grad_norm": 0.696086049079895,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.7332,
+      "step": 7068
+    },
+    {
+      "epoch": 0.06585037799730996,
+      "grad_norm": 0.6155373454093933,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.7417,
+      "step": 7099
+    },
+    {
+      "epoch": 0.06613793423310607,
+      "grad_norm": 0.5616543292999268,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.7533,
+      "step": 7130
+    },
+    {
+      "epoch": 0.06642549046890218,
+      "grad_norm": 0.6647605299949646,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.7511,
+      "step": 7161
+    },
+    {
+      "epoch": 0.0667130467046983,
+      "grad_norm": 0.5980858206748962,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.7412,
+      "step": 7192
+    },
+    {
+      "epoch": 0.06700060294049441,
+      "grad_norm": 0.7701022624969482,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.7371,
+      "step": 7223
+    },
+    {
+      "epoch": 0.06728815917629052,
+      "grad_norm": 0.6251057386398315,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.7409,
+      "step": 7254
+    },
+    {
+      "epoch": 0.06757571541208664,
+      "grad_norm": 0.6283906698226929,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.7354,
+      "step": 7285
+    },
+    {
+      "epoch": 0.06786327164788275,
+      "grad_norm": 0.7811240553855896,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.7369,
+      "step": 7316
+    },
+    {
+      "epoch": 0.06815082788367886,
+      "grad_norm": 0.8049167394638062,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.7323,
+      "step": 7347
+    },
+    {
+      "epoch": 0.06843838411947498,
+      "grad_norm": 0.6499640345573425,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.7474,
+      "step": 7378
+    },
+    {
+      "epoch": 0.06872594035527109,
+      "grad_norm": 0.6651905179023743,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.7436,
+      "step": 7409
+    },
+    {
+      "epoch": 0.0690134965910672,
+      "grad_norm": 0.6399815082550049,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.7406,
+      "step": 7440
+    },
+    {
+      "epoch": 0.06930105282686332,
+      "grad_norm": 0.6342321634292603,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.7305,
+      "step": 7471
+    },
+    {
+      "epoch": 0.06958860906265943,
+      "grad_norm": 0.6198817491531372,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.7368,
+      "step": 7502
+    },
+    {
+      "epoch": 0.06987616529845554,
+      "grad_norm": 0.6942329406738281,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.7356,
+      "step": 7533
+    },
+    {
+      "epoch": 0.07016372153425166,
+      "grad_norm": 0.5913597941398621,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.7317,
+      "step": 7564
+    },
+    {
+      "epoch": 0.07045127777004777,
+      "grad_norm": 0.5913899540901184,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.7362,
+      "step": 7595
+    },
+    {
+      "epoch": 0.07073883400584388,
+      "grad_norm": 0.5804397463798523,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.7236,
+      "step": 7626
+    },
+    {
+      "epoch": 0.07102639024164,
+      "grad_norm": 0.5622512698173523,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.7329,
+      "step": 7657
+    },
+    {
+      "epoch": 0.07131394647743611,
+      "grad_norm": 5.153666973114014,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.7362,
+      "step": 7688
+    },
+    {
+      "epoch": 0.07160150271323222,
+      "grad_norm": 0.6316568851470947,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.7276,
+      "step": 7719
+    },
+    {
+      "epoch": 0.07188905894902833,
+      "grad_norm": 0.6307201981544495,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.7348,
+      "step": 7750
+    },
+    {
+      "epoch": 0.07217661518482445,
+      "grad_norm": 0.6287425756454468,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.7397,
+      "step": 7781
+    },
+    {
+      "epoch": 0.07246417142062056,
+      "grad_norm": 0.9809737205505371,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.7372,
+      "step": 7812
+    },
+    {
+      "epoch": 0.07275172765641667,
+      "grad_norm": 0.6115898489952087,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.7492,
+      "step": 7843
+    },
+    {
+      "epoch": 0.07303928389221279,
+      "grad_norm": 0.733198344707489,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.7378,
+      "step": 7874
+    },
+    {
+      "epoch": 0.0733268401280089,
+      "grad_norm": 0.6508429646492004,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.7285,
+      "step": 7905
+    },
+    {
+      "epoch": 0.07361439636380501,
+      "grad_norm": 0.6079477071762085,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.7341,
+      "step": 7936
+    },
+    {
+      "epoch": 0.07390195259960113,
+      "grad_norm": 0.5894839763641357,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.7286,
+      "step": 7967
+    },
+    {
+      "epoch": 0.07418950883539724,
+      "grad_norm": 0.6230615377426147,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.7257,
+      "step": 7998
+    },
+    {
+      "epoch": 0.07447706507119335,
+      "grad_norm": 0.7338290810585022,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.7265,
+      "step": 8029
+    },
+    {
+      "epoch": 0.07476462130698946,
+      "grad_norm": 0.6040816903114319,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.7294,
+      "step": 8060
+    },
+    {
+      "epoch": 0.07505217754278559,
+      "grad_norm": 0.5885149240493774,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.7275,
+      "step": 8091
+    },
+    {
+      "epoch": 0.0753397337785817,
+      "grad_norm": 0.626339316368103,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.7302,
+      "step": 8122
+    },
+    {
+      "epoch": 0.07562729001437782,
+      "grad_norm": 4.402633190155029,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.7333,
+      "step": 8153
+    },
+    {
+      "epoch": 0.07591484625017393,
+      "grad_norm": 0.5842500329017639,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.7354,
+      "step": 8184
+    },
+    {
+      "epoch": 0.07620240248597004,
+      "grad_norm": 0.6811164021492004,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.7281,
+      "step": 8215
+    },
+    {
+      "epoch": 0.07648995872176616,
+      "grad_norm": 0.8114293217658997,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.7371,
+      "step": 8246
+    },
+    {
+      "epoch": 0.07677751495756227,
+      "grad_norm": 0.6718847751617432,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.7271,
+      "step": 8277
+    },
+    {
+      "epoch": 0.07706507119335838,
+      "grad_norm": 0.6244426965713501,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.7264,
+      "step": 8308
+    },
+    {
+      "epoch": 0.0773526274291545,
+      "grad_norm": 0.8671194911003113,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.7345,
+      "step": 8339
+    },
+    {
+      "epoch": 0.07764018366495061,
+      "grad_norm": 0.5993788838386536,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.7174,
+      "step": 8370
+    },
+    {
+      "epoch": 0.07792773990074672,
+      "grad_norm": 0.6373441815376282,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.7337,
+      "step": 8401
+    },
+    {
+      "epoch": 0.07821529613654284,
+      "grad_norm": 0.6656855344772339,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.7277,
+      "step": 8432
+    },
+    {
+      "epoch": 0.07850285237233895,
+      "grad_norm": 0.6019161939620972,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.7289,
+      "step": 8463
+    },
+    {
+      "epoch": 0.07879040860813506,
+      "grad_norm": 0.6489233374595642,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.7225,
+      "step": 8494
+    },
+    {
+      "epoch": 0.07907796484393118,
+      "grad_norm": 0.5784976482391357,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.7311,
+      "step": 8525
+    },
+    {
+      "epoch": 0.07936552107972729,
+      "grad_norm": 0.6519568562507629,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.7216,
+      "step": 8556
+    },
+    {
+      "epoch": 0.0796530773155234,
+      "grad_norm": 0.6497238278388977,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.7208,
+      "step": 8587
+    },
+    {
+      "epoch": 0.07994063355131951,
+      "grad_norm": 0.629414439201355,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.728,
+      "step": 8618
+    },
+    {
+      "epoch": 0.08022818978711563,
+      "grad_norm": 0.6700971126556396,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.7253,
+      "step": 8649
+    },
+    {
+      "epoch": 0.08051574602291174,
+      "grad_norm": 0.6660225987434387,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.7287,
+      "step": 8680
+    },
+    {
+      "epoch": 0.08080330225870785,
+      "grad_norm": 0.6064980626106262,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.7242,
+      "step": 8711
+    },
+    {
+      "epoch": 0.08109085849450397,
+      "grad_norm": 0.66336590051651,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.7261,
+      "step": 8742
+    },
+    {
+      "epoch": 0.08137841473030008,
+      "grad_norm": 0.6016912460327148,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.726,
+      "step": 8773
+    },
+    {
+      "epoch": 0.0816659709660962,
+      "grad_norm": 0.6544851064682007,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.7324,
+      "step": 8804
+    },
+    {
+      "epoch": 0.0819535272018923,
+      "grad_norm": 0.721031904220581,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.717,
+      "step": 8835
+    },
+    {
+      "epoch": 0.08224108343768842,
+      "grad_norm": 0.6204259395599365,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.7178,
+      "step": 8866
+    },
+    {
+      "epoch": 0.08252863967348453,
+      "grad_norm": 0.665336012840271,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.7367,
+      "step": 8897
+    },
+    {
+      "epoch": 0.08281619590928065,
+      "grad_norm": 0.6388088464736938,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.7249,
+      "step": 8928
+    },
+    {
+      "epoch": 0.08310375214507676,
+      "grad_norm": 0.6215826272964478,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.7239,
+      "step": 8959
+    },
+    {
+      "epoch": 0.08339130838087287,
+      "grad_norm": 0.6228152513504028,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.7255,
+      "step": 8990
+    },
+    {
+      "epoch": 0.08367886461666899,
+      "grad_norm": 0.6137133240699768,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.7286,
+      "step": 9021
+    },
+    {
+      "epoch": 0.0839664208524651,
+      "grad_norm": 0.5644983053207397,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.7352,
+      "step": 9052
+    },
+    {
+      "epoch": 0.08425397708826121,
+      "grad_norm": 0.6456722021102905,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.7273,
+      "step": 9083
+    },
+    {
+      "epoch": 0.08454153332405732,
+      "grad_norm": 0.618363618850708,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.7136,
+      "step": 9114
+    },
+    {
+      "epoch": 0.08482908955985344,
+      "grad_norm": 0.521994948387146,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.7086,
+      "step": 9145
+    },
+    {
+      "epoch": 0.08511664579564955,
+      "grad_norm": 0.723540186882019,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.7183,
+      "step": 9176
+    },
+    {
+      "epoch": 0.08540420203144566,
+      "grad_norm": 0.6049785614013672,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.7174,
+      "step": 9207
+    },
+    {
+      "epoch": 0.08569175826724178,
+      "grad_norm": 0.5865082740783691,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.7075,
+      "step": 9238
+    },
+    {
+      "epoch": 0.08597931450303789,
+      "grad_norm": 0.657616913318634,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.7251,
+      "step": 9269
+    },
+    {
+      "epoch": 0.086266870738834,
+      "grad_norm": 0.5859720706939697,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.7179,
+      "step": 9300
+    },
+    {
+      "epoch": 0.08655442697463012,
+      "grad_norm": 0.6350371241569519,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.728,
+      "step": 9331
+    },
+    {
+      "epoch": 0.08684198321042623,
+      "grad_norm": 0.5636146664619446,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.7269,
+      "step": 9362
+    },
+    {
+      "epoch": 0.08712953944622234,
+      "grad_norm": 0.52867192029953,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.7134,
+      "step": 9393
+    },
+    {
+      "epoch": 0.08741709568201846,
+      "grad_norm": 0.6418184638023376,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.7234,
+      "step": 9424
+    },
+    {
+      "epoch": 0.08770465191781457,
+      "grad_norm": 0.602602481842041,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.7157,
+      "step": 9455
+    },
+    {
+      "epoch": 0.08799220815361068,
+      "grad_norm": 0.6151993274688721,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.7154,
+      "step": 9486
+    },
+    {
+      "epoch": 0.0882797643894068,
+      "grad_norm": 0.6821918487548828,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.7128,
+      "step": 9517
+    },
+    {
+      "epoch": 0.08856732062520291,
+      "grad_norm": 0.5447763204574585,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.7232,
+      "step": 9548
+    },
+    {
+      "epoch": 0.08885487686099902,
+      "grad_norm": 0.6219198703765869,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.7171,
+      "step": 9579
+    },
+    {
+      "epoch": 0.08914243309679513,
+      "grad_norm": 0.57777339220047,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.7105,
+      "step": 9610
+    },
+    {
+      "epoch": 0.08942998933259125,
+      "grad_norm": 0.5366658568382263,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.7148,
+      "step": 9641
+    },
+    {
+      "epoch": 0.08971754556838736,
+      "grad_norm": 0.5971750020980835,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.7077,
+      "step": 9672
+    },
+    {
+      "epoch": 0.09000510180418347,
+      "grad_norm": 0.5600515007972717,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.7105,
+      "step": 9703
+    },
+    {
+      "epoch": 0.09029265803997959,
+      "grad_norm": 0.6229792237281799,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.7161,
+      "step": 9734
+    },
+    {
+      "epoch": 0.0905802142757757,
+      "grad_norm": 0.7581937313079834,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.7227,
+      "step": 9765
+    },
+    {
+      "epoch": 0.09086777051157181,
+      "grad_norm": 0.6748283505439758,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.7058,
+      "step": 9796
+    },
+    {
+      "epoch": 0.09115532674736793,
+      "grad_norm": 0.5807577967643738,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.7237,
+      "step": 9827
+    },
+    {
+      "epoch": 0.09144288298316404,
+      "grad_norm": 0.6818577647209167,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.7177,
+      "step": 9858
+    },
+    {
+      "epoch": 0.09173043921896017,
+      "grad_norm": 0.5779188275337219,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.7154,
+      "step": 9889
+    },
+    {
+      "epoch": 0.09201799545475628,
+      "grad_norm": 0.6254588961601257,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.7116,
+      "step": 9920
+    },
+    {
+      "epoch": 0.09230555169055239,
+      "grad_norm": 0.6518847942352295,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.7145,
+      "step": 9951
+    },
+    {
+      "epoch": 0.0925931079263485,
+      "grad_norm": 0.6086714863777161,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.7126,
+      "step": 9982
+    },
+    {
+      "epoch": 0.09288066416214462,
+      "grad_norm": 0.750381588935852,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.7391,
+      "step": 10013
+    },
+    {
+      "epoch": 0.09316822039794073,
+      "grad_norm": 0.7088913321495056,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.7116,
+      "step": 10044
+    },
+    {
+      "epoch": 0.09345577663373685,
+      "grad_norm": 0.6793993711471558,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.7124,
+      "step": 10075
+    },
+    {
+      "epoch": 0.09374333286953296,
+      "grad_norm": 0.6571323871612549,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.7199,
+      "step": 10106
+    },
+    {
+      "epoch": 0.09403088910532907,
+      "grad_norm": 0.6068087816238403,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.725,
+      "step": 10137
+    },
+    {
+      "epoch": 0.09431844534112518,
+      "grad_norm": 0.5739994049072266,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.7013,
+      "step": 10168
+    },
+    {
+      "epoch": 0.0946060015769213,
+      "grad_norm": 0.5300189256668091,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.7241,
+      "step": 10199
+    },
+    {
+      "epoch": 0.09489355781271741,
+      "grad_norm": 0.6328433752059937,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.7111,
+      "step": 10230
+    },
+    {
+      "epoch": 0.09518111404851352,
+      "grad_norm": 0.6738958358764648,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.7106,
+      "step": 10261
+    },
+    {
+      "epoch": 0.09546867028430964,
+      "grad_norm": 0.573836624622345,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.7178,
+      "step": 10292
+    },
+    {
+      "epoch": 0.09575622652010575,
+      "grad_norm": 0.5532362461090088,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.7084,
+      "step": 10323
+    },
+    {
+      "epoch": 0.09604378275590186,
+      "grad_norm": 0.75803142786026,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.7084,
+      "step": 10354
+    },
+    {
+      "epoch": 0.09633133899169798,
+      "grad_norm": 0.6860505938529968,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.7016,
+      "step": 10385
+    },
+    {
+      "epoch": 0.09661889522749409,
+      "grad_norm": 0.6912726759910583,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.7278,
+      "step": 10416
+    },
+    {
+      "epoch": 0.0969064514632902,
+      "grad_norm": 0.626269519329071,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.7146,
+      "step": 10447
+    },
+    {
+      "epoch": 0.09719400769908632,
+      "grad_norm": 0.5607821941375732,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.7157,
+      "step": 10478
+    },
+    {
+      "epoch": 0.09748156393488243,
+      "grad_norm": 0.5527504682540894,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.7103,
+      "step": 10509
+    },
+    {
+      "epoch": 0.09776912017067854,
+      "grad_norm": 0.6478459239006042,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.7147,
+      "step": 10540
+    },
+    {
+      "epoch": 0.09805667640647465,
+      "grad_norm": 0.6617260575294495,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.7181,
+      "step": 10571
+    },
+    {
+      "epoch": 0.09834423264227077,
+      "grad_norm": 0.5579579472541809,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.7155,
+      "step": 10602
+    },
+    {
+      "epoch": 0.09863178887806688,
+      "grad_norm": 0.6320039629936218,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.7049,
+      "step": 10633
+    },
+    {
+      "epoch": 0.098919345113863,
+      "grad_norm": 0.5697253942489624,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.7127,
+      "step": 10664
+    },
+    {
+      "epoch": 0.09920690134965911,
+      "grad_norm": 0.5650231242179871,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.7051,
+      "step": 10695
+    },
+    {
+      "epoch": 0.09949445758545522,
+      "grad_norm": 0.6272993087768555,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.7119,
+      "step": 10726
+    },
+    {
+      "epoch": 0.09978201382125133,
+      "grad_norm": 0.6033383011817932,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.706,
+      "step": 10757
+    },
+    {
+      "epoch": 0.10006957005704745,
+      "grad_norm": 0.5815847516059875,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.7186,
+      "step": 10788
+    },
+    {
+      "epoch": 0.10035712629284356,
+      "grad_norm": 0.5461300611495972,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.7125,
+      "step": 10819
+    },
+    {
+      "epoch": 0.10064468252863967,
+      "grad_norm": 0.5513074398040771,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.7055,
+      "step": 10850
+    },
+    {
+      "epoch": 0.10093223876443579,
+      "grad_norm": 0.6083746552467346,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.7324,
+      "step": 10881
+    },
+    {
+      "epoch": 0.1012197950002319,
+      "grad_norm": 0.5546435117721558,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.6997,
+      "step": 10912
+    },
+    {
+      "epoch": 0.10150735123602801,
+      "grad_norm": 0.601056694984436,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.7087,
+      "step": 10943
+    },
+    {
+      "epoch": 0.10179490747182413,
+      "grad_norm": 0.6214995980262756,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.729,
+      "step": 10974
+    },
+    {
+      "epoch": 0.10208246370762024,
+      "grad_norm": 0.5371711850166321,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.708,
+      "step": 11005
+    },
+    {
+      "epoch": 0.10237001994341635,
+      "grad_norm": 0.5961845517158508,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.7047,
+      "step": 11036
+    },
+    {
+      "epoch": 0.10265757617921246,
+      "grad_norm": 0.6839886903762817,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.7126,
+      "step": 11067
+    },
+    {
+      "epoch": 0.10294513241500858,
+      "grad_norm": 0.6624526977539062,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.7085,
+      "step": 11098
+    },
+    {
+      "epoch": 0.10323268865080469,
+      "grad_norm": 0.5941864848136902,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.7055,
+      "step": 11129
+    },
+    {
+      "epoch": 0.1035202448866008,
+      "grad_norm": 0.6362475156784058,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.7229,
+      "step": 11160
+    },
+    {
+      "epoch": 0.10380780112239692,
+      "grad_norm": 0.5098447799682617,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.7116,
+      "step": 11191
+    },
+    {
+      "epoch": 0.10409535735819303,
+      "grad_norm": 0.5661705136299133,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.7043,
+      "step": 11222
+    },
+    {
+      "epoch": 0.10438291359398914,
+      "grad_norm": 0.6132655143737793,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.7066,
+      "step": 11253
+    },
+    {
+      "epoch": 0.10467046982978526,
+      "grad_norm": 0.6077197790145874,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.7062,
+      "step": 11284
+    },
+    {
+      "epoch": 0.10495802606558137,
+      "grad_norm": 0.5256394147872925,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.7053,
+      "step": 11315
+    },
+    {
+      "epoch": 0.10524558230137748,
+      "grad_norm": 0.5592128038406372,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.7057,
+      "step": 11346
+    },
+    {
+      "epoch": 0.1055331385371736,
+      "grad_norm": 0.4883192777633667,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.6976,
+      "step": 11377
+    },
+    {
+      "epoch": 0.10582069477296971,
+      "grad_norm": 0.7926296591758728,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.6941,
+      "step": 11408
+    },
+    {
+      "epoch": 0.10610825100876582,
+      "grad_norm": 0.6039475202560425,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.7062,
+      "step": 11439
+    },
+    {
+      "epoch": 0.10639580724456194,
+      "grad_norm": 0.5560294985771179,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.6908,
+      "step": 11470
+    },
+    {
+      "epoch": 0.10668336348035805,
+      "grad_norm": 0.5322378277778625,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.7005,
+      "step": 11501
+    },
+    {
+      "epoch": 0.10697091971615416,
+      "grad_norm": 0.5655946135520935,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.7038,
+      "step": 11532
+    },
+    {
+      "epoch": 0.10725847595195027,
+      "grad_norm": 0.6242902278900146,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.7151,
+      "step": 11563
+    },
+    {
+      "epoch": 0.10754603218774639,
+      "grad_norm": 0.5343348383903503,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.7112,
+      "step": 11594
+    },
+    {
+      "epoch": 0.1078335884235425,
+      "grad_norm": 0.5832471251487732,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.695,
+      "step": 11625
+    },
+    {
+      "epoch": 0.10812114465933861,
+      "grad_norm": 0.6098005771636963,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.6952,
+      "step": 11656
+    },
+    {
+      "epoch": 0.10840870089513474,
+      "grad_norm": 0.6541092395782471,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.7094,
+      "step": 11687
+    },
+    {
+      "epoch": 0.10869625713093085,
+      "grad_norm": 0.5949205160140991,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.7146,
+      "step": 11718
+    },
+    {
+      "epoch": 0.10898381336672697,
+      "grad_norm": 0.5494295954704285,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.7019,
+      "step": 11749
+    },
+    {
+      "epoch": 0.10927136960252308,
+      "grad_norm": 0.5022011995315552,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.7023,
+      "step": 11780
+    },
+    {
+      "epoch": 0.1095589258383192,
+      "grad_norm": 0.6179025173187256,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.7083,
+      "step": 11811
+    },
+    {
+      "epoch": 0.1098464820741153,
+      "grad_norm": 0.5961601734161377,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.7037,
+      "step": 11842
+    },
+    {
+      "epoch": 0.11013403830991142,
+      "grad_norm": 0.6176908612251282,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.6984,
+      "step": 11873
+    },
+    {
+      "epoch": 0.11042159454570753,
+      "grad_norm": 0.5871501564979553,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.6938,
+      "step": 11904
+    },
+    {
+      "epoch": 0.11070915078150365,
+      "grad_norm": 0.5729032754898071,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.6976,
+      "step": 11935
+    },
+    {
+      "epoch": 0.11099670701729976,
+      "grad_norm": 0.6106701493263245,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.6922,
+      "step": 11966
+    },
+    {
+      "epoch": 0.11128426325309587,
+      "grad_norm": 0.604791522026062,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.6963,
+      "step": 11997
+    },
+    {
+      "epoch": 0.11157181948889199,
+      "grad_norm": 0.6141258478164673,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.7048,
+      "step": 12028
+    },
+    {
+      "epoch": 0.1118593757246881,
+      "grad_norm": 0.5770751237869263,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.6976,
+      "step": 12059
+    },
+    {
+      "epoch": 0.11214693196048421,
+      "grad_norm": 0.6507471203804016,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.7133,
+      "step": 12090
+    },
+    {
+      "epoch": 0.11243448819628032,
+      "grad_norm": 0.5432878732681274,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.7123,
+      "step": 12121
+    },
+    {
+      "epoch": 0.11272204443207644,
+      "grad_norm": 0.5892463326454163,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.7013,
+      "step": 12152
+    },
+    {
+      "epoch": 0.11300960066787255,
+      "grad_norm": 0.5415503978729248,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.7096,
+      "step": 12183
+    },
+    {
+      "epoch": 0.11329715690366866,
+      "grad_norm": 0.5742498636245728,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 0.7064,
+      "step": 12214
+    },
+    {
+      "epoch": 0.11358471313946478,
+      "grad_norm": 0.5886706113815308,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 0.6972,
+      "step": 12245
+    },
+    {
+      "epoch": 0.11387226937526089,
+      "grad_norm": 2.7756686210632324,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 0.6991,
+      "step": 12276
+    },
+    {
+      "epoch": 0.114159825611057,
+      "grad_norm": 0.5667555332183838,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 0.6875,
+      "step": 12307
+    },
+    {
+      "epoch": 0.11444738184685312,
+      "grad_norm": 0.6421839594841003,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 0.6957,
+      "step": 12338
+    },
+    {
+      "epoch": 0.11473493808264923,
+      "grad_norm": 0.6332064867019653,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 0.7107,
+      "step": 12369
+    },
+    {
+      "epoch": 0.11502249431844534,
+      "grad_norm": 0.575236439704895,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 0.7008,
+      "step": 12400
+    },
+    {
+      "epoch": 0.11531005055424146,
+      "grad_norm": 0.5423835515975952,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 0.6925,
+      "step": 12431
+    },
+    {
+      "epoch": 0.11559760679003757,
+      "grad_norm": 0.5887306332588196,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 0.6941,
+      "step": 12462
+    },
+    {
+      "epoch": 0.11588516302583368,
+      "grad_norm": 0.6004140377044678,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 0.6789,
+      "step": 12493
+    },
+    {
+      "epoch": 0.1161727192616298,
+      "grad_norm": 0.5156278610229492,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 0.6968,
+      "step": 12524
+    },
+    {
+      "epoch": 0.11646027549742591,
+      "grad_norm": 0.4995116889476776,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 0.6968,
+      "step": 12555
+    },
+    {
+      "epoch": 0.11674783173322202,
+      "grad_norm": 0.5860235095024109,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 0.6905,
+      "step": 12586
+    },
+    {
+      "epoch": 0.11703538796901813,
+      "grad_norm": 0.5904795527458191,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 0.7003,
+      "step": 12617
+    },
+    {
+      "epoch": 0.11732294420481425,
+      "grad_norm": 0.5522101521492004,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 0.6968,
+      "step": 12648
+    },
+    {
+      "epoch": 0.11761050044061036,
+      "grad_norm": 0.5596745610237122,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 0.6844,
+      "step": 12679
+    },
+    {
+      "epoch": 0.11789805667640647,
+      "grad_norm": 0.6061542630195618,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 0.7055,
+      "step": 12710
+    },
+    {
+      "epoch": 0.11818561291220259,
+      "grad_norm": 0.5262192487716675,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 0.691,
+      "step": 12741
+    },
+    {
+      "epoch": 0.1184731691479987,
+      "grad_norm": 0.5930072665214539,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 0.696,
+      "step": 12772
+    },
+    {
+      "epoch": 0.11876072538379481,
+      "grad_norm": 0.5710198283195496,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 0.6979,
+      "step": 12803
+    },
+    {
+      "epoch": 0.11904828161959093,
+      "grad_norm": 0.6593298316001892,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 0.7015,
+      "step": 12834
+    },
+    {
+      "epoch": 0.11933583785538704,
+      "grad_norm": 0.5754159092903137,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 0.6905,
+      "step": 12865
+    },
+    {
+      "epoch": 0.11962339409118315,
+      "grad_norm": 0.8572949171066284,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 0.6888,
+      "step": 12896
+    },
+    {
+      "epoch": 0.11991095032697927,
+      "grad_norm": 0.7124003767967224,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 0.7075,
+      "step": 12927
+    },
+    {
+      "epoch": 0.12019850656277538,
+      "grad_norm": 0.6125847697257996,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 0.706,
+      "step": 12958
+    },
+    {
+      "epoch": 0.12048606279857149,
+      "grad_norm": 0.5412183403968811,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 0.6834,
+      "step": 12989
+    },
+    {
+      "epoch": 0.1207736190343676,
+      "grad_norm": 0.5900364518165588,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 0.7043,
+      "step": 13020
+    },
+    {
+      "epoch": 0.12106117527016372,
+      "grad_norm": 0.570388674736023,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 0.6915,
+      "step": 13051
+    },
+    {
+      "epoch": 0.12134873150595983,
+      "grad_norm": 0.6373887062072754,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 0.6819,
+      "step": 13082
+    },
+    {
+      "epoch": 0.12163628774175594,
+      "grad_norm": 0.6626436710357666,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 0.7045,
+      "step": 13113
+    },
+    {
+      "epoch": 0.12192384397755206,
+      "grad_norm": 0.5196493864059448,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 0.6854,
+      "step": 13144
+    },
+    {
+      "epoch": 0.12221140021334817,
+      "grad_norm": 0.6594944000244141,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 0.6959,
+      "step": 13175
+    },
+    {
+      "epoch": 0.12249895644914428,
+      "grad_norm": 0.5820755958557129,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 0.6994,
+      "step": 13206
+    },
+    {
+      "epoch": 0.1227865126849404,
+      "grad_norm": 0.5696197748184204,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 0.6927,
+      "step": 13237
+    },
+    {
+      "epoch": 0.12307406892073651,
+      "grad_norm": 0.5652363300323486,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 0.6921,
+      "step": 13268
+    },
+    {
+      "epoch": 0.12336162515653262,
+      "grad_norm": 0.5531406402587891,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 0.6817,
+      "step": 13299
+    },
+    {
+      "epoch": 0.12364918139232874,
+      "grad_norm": 0.6967798471450806,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 0.7046,
+      "step": 13330
+    },
+    {
+      "epoch": 0.12393673762812485,
+      "grad_norm": 0.5255029201507568,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 0.7002,
+      "step": 13361
+    },
+    {
+      "epoch": 0.12422429386392096,
+      "grad_norm": 0.6225217580795288,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 0.7001,
+      "step": 13392
+    },
+    {
+      "epoch": 0.12451185009971708,
+      "grad_norm": 0.5642330646514893,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 0.6931,
+      "step": 13423
+    },
+    {
+      "epoch": 0.12479940633551319,
+      "grad_norm": 0.5942896008491516,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 0.688,
+      "step": 13454
+    },
+    {
+      "epoch": 0.1250869625713093,
+      "grad_norm": 0.5836249589920044,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 0.7032,
+      "step": 13485
+    },
+    {
+      "epoch": 0.12537451880710543,
+      "grad_norm": 0.5641030669212341,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 0.6994,
+      "step": 13516
+    },
+    {
+      "epoch": 0.12566207504290153,
+      "grad_norm": 0.5812942385673523,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 0.6901,
+      "step": 13547
+    },
+    {
+      "epoch": 0.12594963127869765,
+      "grad_norm": 0.5939679741859436,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 0.6869,
+      "step": 13578
+    },
+    {
+      "epoch": 0.12623718751449375,
+      "grad_norm": 0.5453142523765564,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 0.6776,
+      "step": 13609
+    },
+    {
+      "epoch": 0.12652474375028988,
+      "grad_norm": 0.4835115671157837,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 0.6971,
+      "step": 13640
+    },
+    {
+      "epoch": 0.12681229998608598,
+      "grad_norm": 0.5290993452072144,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 0.6833,
+      "step": 13671
+    },
+    {
+      "epoch": 0.1270998562218821,
+      "grad_norm": 4.066009044647217,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 0.6904,
+      "step": 13702
+    },
+    {
+      "epoch": 0.1273874124576782,
+      "grad_norm": 0.5854982137680054,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 0.6845,
+      "step": 13733
+    },
+    {
+      "epoch": 0.12767496869347433,
+      "grad_norm": 0.5767256617546082,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 0.7101,
+      "step": 13764
+    },
+    {
+      "epoch": 0.12796252492927043,
+      "grad_norm": 0.5740492343902588,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 0.6905,
+      "step": 13795
+    },
+    {
+      "epoch": 0.12825008116506656,
+      "grad_norm": 0.6937960386276245,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 0.6908,
+      "step": 13826
+    },
+    {
+      "epoch": 0.12853763740086266,
+      "grad_norm": 0.6835616827011108,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 0.6952,
+      "step": 13857
+    },
+    {
+      "epoch": 0.12882519363665879,
+      "grad_norm": 0.6329163312911987,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 0.6927,
+      "step": 13888
+    },
+    {
+      "epoch": 0.12911274987245488,
+      "grad_norm": 0.6035836338996887,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 0.6924,
+      "step": 13919
+    },
+    {
+      "epoch": 0.129400306108251,
+      "grad_norm": 0.6920346617698669,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 0.6894,
+      "step": 13950
+    },
+    {
+      "epoch": 0.1296878623440471,
+      "grad_norm": 0.5432500243186951,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 0.7057,
+      "step": 13981
+    },
+    {
+      "epoch": 0.12997541857984324,
+      "grad_norm": 0.5386407375335693,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 0.6901,
+      "step": 14012
+    },
+    {
+      "epoch": 0.13026297481563934,
+      "grad_norm": 0.5241833329200745,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 0.6961,
+      "step": 14043
+    },
+    {
+      "epoch": 0.13055053105143546,
+      "grad_norm": 0.5723391771316528,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 0.6981,
+      "step": 14074
+    },
+    {
+      "epoch": 0.13083808728723156,
+      "grad_norm": 0.5394178032875061,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 0.695,
+      "step": 14105
+    },
+    {
+      "epoch": 0.1311256435230277,
+      "grad_norm": 0.6392977833747864,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 0.6898,
+      "step": 14136
+    },
+    {
+      "epoch": 0.1314131997588238,
+      "grad_norm": 0.5407607555389404,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 0.6981,
+      "step": 14167
+    },
+    {
+      "epoch": 0.13170075599461992,
+      "grad_norm": 0.556535542011261,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 0.6885,
+      "step": 14198
+    },
+    {
+      "epoch": 0.13198831223041602,
+      "grad_norm": 0.6277481913566589,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 0.6832,
+      "step": 14229
+    },
+    {
+      "epoch": 0.13227586846621214,
+      "grad_norm": 0.6777597665786743,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 0.6962,
+      "step": 14260
+    },
+    {
+      "epoch": 0.13256342470200824,
+      "grad_norm": 0.5808172225952148,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 0.6906,
+      "step": 14291
+    },
+    {
+      "epoch": 0.13285098093780437,
+      "grad_norm": 0.5503218770027161,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 0.7,
+      "step": 14322
+    },
+    {
+      "epoch": 0.13313853717360047,
+      "grad_norm": 0.5720141530036926,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 0.7009,
+      "step": 14353
+    },
+    {
+      "epoch": 0.1334260934093966,
+      "grad_norm": 0.5629698038101196,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 0.6931,
+      "step": 14384
+    },
+    {
+      "epoch": 0.13371364964519272,
+      "grad_norm": 0.5493198037147522,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 0.6794,
+      "step": 14415
+    },
+    {
+      "epoch": 0.13400120588098882,
+      "grad_norm": 0.4900459945201874,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 0.7053,
+      "step": 14446
+    },
+    {
+      "epoch": 0.13428876211678495,
+      "grad_norm": 0.5763978958129883,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 0.6889,
+      "step": 14477
+    },
+    {
+      "epoch": 0.13457631835258105,
+      "grad_norm": 0.546836793422699,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 0.6869,
+      "step": 14508
+    },
+    {
+      "epoch": 0.13486387458837718,
+      "grad_norm": 0.7777213454246521,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 0.7098,
+      "step": 14539
+    },
+    {
+      "epoch": 0.13515143082417327,
+      "grad_norm": 0.6182757019996643,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 0.6931,
+      "step": 14570
+    },
+    {
+      "epoch": 0.1354389870599694,
+      "grad_norm": 0.5483623743057251,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 0.6824,
+      "step": 14601
+    },
+    {
+      "epoch": 0.1357265432957655,
+      "grad_norm": 0.5870161056518555,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 0.6979,
+      "step": 14632
+    },
+    {
+      "epoch": 0.13601409953156163,
+      "grad_norm": 0.5810563564300537,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 0.6803,
+      "step": 14663
+    },
+    {
+      "epoch": 0.13630165576735773,
+      "grad_norm": 0.594388484954834,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 0.6772,
+      "step": 14694
+    },
+    {
+      "epoch": 0.13658921200315385,
+      "grad_norm": 0.5352759957313538,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 0.6847,
+      "step": 14725
+    },
+    {
+      "epoch": 0.13687676823894995,
+      "grad_norm": 0.5735815763473511,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 0.6948,
+      "step": 14756
+    },
+    {
+      "epoch": 0.13716432447474608,
+      "grad_norm": 0.6059151291847229,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 0.6844,
+      "step": 14787
+    },
+    {
+      "epoch": 0.13745188071054218,
+      "grad_norm": 0.5839948058128357,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 0.6901,
+      "step": 14818
+    },
+    {
+      "epoch": 0.1377394369463383,
+      "grad_norm": 0.5841077566146851,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 0.693,
+      "step": 14849
+    },
+    {
+      "epoch": 0.1380269931821344,
+      "grad_norm": 0.5443329811096191,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 0.6862,
+      "step": 14880
+    },
+    {
+      "epoch": 0.13831454941793053,
+      "grad_norm": 0.5152838826179504,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 0.6775,
+      "step": 14911
+    },
+    {
+      "epoch": 0.13860210565372663,
+      "grad_norm": 0.5750979781150818,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 0.675,
+      "step": 14942
+    },
+    {
+      "epoch": 0.13888966188952276,
+      "grad_norm": 0.5725698471069336,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 0.7076,
+      "step": 14973
+    },
+    {
+      "epoch": 0.13917721812531886,
+      "grad_norm": 0.5778638124465942,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 0.6988,
+      "step": 15004
+    },
+    {
+      "epoch": 0.13946477436111498,
+      "grad_norm": 0.5429561138153076,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 0.6968,
+      "step": 15035
+    },
+    {
+      "epoch": 0.13975233059691108,
+      "grad_norm": 0.6476013660430908,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 0.6852,
+      "step": 15066
+    },
+    {
+      "epoch": 0.1400398868327072,
+      "grad_norm": 0.5936187505722046,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 0.6798,
+      "step": 15097
+    },
+    {
+      "epoch": 0.1403274430685033,
+      "grad_norm": 0.5265310406684875,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 0.6775,
+      "step": 15128
+    },
+    {
+      "epoch": 0.14061499930429944,
+      "grad_norm": 0.5264164209365845,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 0.691,
+      "step": 15159
+    },
+    {
+      "epoch": 0.14090255554009554,
+      "grad_norm": 0.739185631275177,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 0.6796,
+      "step": 15190
+    },
+    {
+      "epoch": 0.14119011177589166,
+      "grad_norm": 0.7786234617233276,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 0.6798,
+      "step": 15221
+    },
+    {
+      "epoch": 0.14147766801168776,
+      "grad_norm": 0.605093240737915,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 0.6846,
+      "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 sha256:0a811c1ee32ac5fb3baeb7b42fe04c2c91fcf0074b460464e158e3f772388342
+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 sha256:3c4b6fb4308525a0953aed6801b6707bff5cddb5ed37c6be414e158261ccd4f9
+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 sha256:6a1f0917045a4a40fa3229c6c44ffbb3b23065170e56a851339fdcdbe390e599
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250f42b4b336eb049c598461d4a04f583b9ba6ea01b24bb1fe3e4e94620e886b
+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:b70300e5d19bfde5041ddf934ad8909c10790de5b9cf71b66b9dd7bc8133aaaa
+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 sha256:0a811c1ee32ac5fb3baeb7b42fe04c2c91fcf0074b460464e158e3f772388342
+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 sha256:58cc8acb591114762398d4dc8899ddf2d4ddf3a50e002ea9c6b56947ee439100
+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