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-15260/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-15260/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "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:d9b8fbfd7bab9de40a72947556349d6436e8032340f88ed201c2055478081678
+size 4976687216

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faab92c079dee70573da2aa38bf83c1a2a2858fbee7104c30f77e30eb62ed67f
+size 4778622352

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d579560f2723d4a62b22ef6ec0d935dfbc2ddf0f14fc9efeac83bf5b586bf9d6
+size 4932743960

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089cf99962fd351ceb590220ea351f1d18937b35376077982b276416f768317a
+size 4932743992

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b61bee4a8b5e41f744ec0820def58c39c0c333e6787b7e24146468348f082a0
+size 4998852296

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c764e1a0c9df6ce4b311ed7ec49e51ee53eb4cc9049f5c9034802ff51cd8851d
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e482d2199315ff01e45c971e2290782f44cd5f1d7316f07675b49a0b99872ffb
+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:e56f24e519a611d502f8feef92f8424ac583414c49e76e389c26ef01451e10bb
+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": 1.9455794095993042,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.1457,
+      "step": 31
+    },
+    {
+      "epoch": 0.0005751124715922267,
+      "grad_norm": 1.4712188243865967,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.0982,
+      "step": 62
+    },
+    {
+      "epoch": 0.0008626687073883401,
+      "grad_norm": 1.4395982027053833,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.0874,
+      "step": 93
+    },
+    {
+      "epoch": 0.0011502249431844533,
+      "grad_norm": 1.635319709777832,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.0666,
+      "step": 124
+    },
+    {
+      "epoch": 0.0014377811789805669,
+      "grad_norm": 1.7644890546798706,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.0566,
+      "step": 155
+    },
+    {
+      "epoch": 0.0017253374147766802,
+      "grad_norm": 1.4304418563842773,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.0297,
+      "step": 186
+    },
+    {
+      "epoch": 0.0020128936505727935,
+      "grad_norm": 1.7738460302352905,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.0381,
+      "step": 217
+    },
+    {
+      "epoch": 0.0023004498863689066,
+      "grad_norm": 1.5791255235671997,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.0349,
+      "step": 248
+    },
+    {
+      "epoch": 0.00258800612216502,
+      "grad_norm": 1.8046092987060547,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.0162,
+      "step": 279
+    },
+    {
+      "epoch": 0.0028755623579611337,
+      "grad_norm": 2.3568904399871826,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 0.9985,
+      "step": 310
+    },
+    {
+      "epoch": 0.003163118593757247,
+      "grad_norm": 1.7427752017974854,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 0.9988,
+      "step": 341
+    },
+    {
+      "epoch": 0.0034506748295533604,
+      "grad_norm": 2.1790356636047363,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.0013,
+      "step": 372
+    },
+    {
+      "epoch": 0.0037382310653494735,
+      "grad_norm": 1.9367269277572632,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 0.9964,
+      "step": 403
+    },
+    {
+      "epoch": 0.004025787301145587,
+      "grad_norm": 2.1018896102905273,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 0.9887,
+      "step": 434
+    },
+    {
+      "epoch": 0.0043133435369417,
+      "grad_norm": 1.754103660583496,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 0.9825,
+      "step": 465
+    },
+    {
+      "epoch": 0.004600899772737813,
+      "grad_norm": 1.9631413221359253,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 0.9743,
+      "step": 496
+    },
+    {
+      "epoch": 0.004888456008533927,
+      "grad_norm": 2.701847553253174,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 0.9757,
+      "step": 527
+    },
+    {
+      "epoch": 0.00517601224433004,
+      "grad_norm": 2.436610460281372,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 0.9554,
+      "step": 558
+    },
+    {
+      "epoch": 0.0054635684801261535,
+      "grad_norm": 2.111328363418579,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 0.966,
+      "step": 589
+    },
+    {
+      "epoch": 0.0057511247159222675,
+      "grad_norm": 1.7960383892059326,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 0.9542,
+      "step": 620
+    },
+    {
+      "epoch": 0.006038680951718381,
+      "grad_norm": 1.5837233066558838,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 0.9525,
+      "step": 651
+    },
+    {
+      "epoch": 0.006326237187514494,
+      "grad_norm": 1.5429449081420898,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 0.9474,
+      "step": 682
+    },
+    {
+      "epoch": 0.006613793423310607,
+      "grad_norm": 2.7319698333740234,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 0.9475,
+      "step": 713
+    },
+    {
+      "epoch": 0.006901349659106721,
+      "grad_norm": 2.2479138374328613,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 0.9513,
+      "step": 744
+    },
+    {
+      "epoch": 0.007188905894902834,
+      "grad_norm": 1.517256498336792,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.9488,
+      "step": 775
+    },
+    {
+      "epoch": 0.007476462130698947,
+      "grad_norm": 1.5688025951385498,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.94,
+      "step": 806
+    },
+    {
+      "epoch": 0.00776401836649506,
+      "grad_norm": 1.5743234157562256,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.9313,
+      "step": 837
+    },
+    {
+      "epoch": 0.008051574602291174,
+      "grad_norm": 2.008028507232666,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.9361,
+      "step": 868
+    },
+    {
+      "epoch": 0.008339130838087287,
+      "grad_norm": 1.65324866771698,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.9219,
+      "step": 899
+    },
+    {
+      "epoch": 0.0086266870738834,
+      "grad_norm": 1.5716785192489624,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.9227,
+      "step": 930
+    },
+    {
+      "epoch": 0.008914243309679513,
+      "grad_norm": 1.7367960214614868,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.9339,
+      "step": 961
+    },
+    {
+      "epoch": 0.009201799545475627,
+      "grad_norm": 1.3708274364471436,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.9181,
+      "step": 992
+    },
+    {
+      "epoch": 0.009489355781271741,
+      "grad_norm": 2.4203550815582275,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.9196,
+      "step": 1023
+    },
+    {
+      "epoch": 0.009776912017067855,
+      "grad_norm": 1.926921010017395,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.9285,
+      "step": 1054
+    },
+    {
+      "epoch": 0.010064468252863968,
+      "grad_norm": 1.27815842628479,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.9083,
+      "step": 1085
+    },
+    {
+      "epoch": 0.01035202448866008,
+      "grad_norm": 1.1785378456115723,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.9171,
+      "step": 1116
+    },
+    {
+      "epoch": 0.010639580724456194,
+      "grad_norm": 1.4379056692123413,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.9228,
+      "step": 1147
+    },
+    {
+      "epoch": 0.010927136960252307,
+      "grad_norm": 1.2898954153060913,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.9049,
+      "step": 1178
+    },
+    {
+      "epoch": 0.01121469319604842,
+      "grad_norm": 1.3358045816421509,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.9065,
+      "step": 1209
+    },
+    {
+      "epoch": 0.011502249431844535,
+      "grad_norm": 1.3427420854568481,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.9043,
+      "step": 1240
+    },
+    {
+      "epoch": 0.011789805667640648,
+      "grad_norm": 1.602563738822937,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.8835,
+      "step": 1271
+    },
+    {
+      "epoch": 0.012077361903436761,
+      "grad_norm": 1.4587140083312988,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.8932,
+      "step": 1302
+    },
+    {
+      "epoch": 0.012364918139232874,
+      "grad_norm": 1.4665412902832031,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.889,
+      "step": 1333
+    },
+    {
+      "epoch": 0.012652474375028987,
+      "grad_norm": 1.1323597431182861,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.9121,
+      "step": 1364
+    },
+    {
+      "epoch": 0.0129400306108251,
+      "grad_norm": 1.342729091644287,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.8945,
+      "step": 1395
+    },
+    {
+      "epoch": 0.013227586846621214,
+      "grad_norm": 1.1981477737426758,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.8945,
+      "step": 1426
+    },
+    {
+      "epoch": 0.013515143082417327,
+      "grad_norm": 1.2309355735778809,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.8912,
+      "step": 1457
+    },
+    {
+      "epoch": 0.013802699318213442,
+      "grad_norm": 1.352373480796814,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.8807,
+      "step": 1488
+    },
+    {
+      "epoch": 0.014090255554009555,
+      "grad_norm": 1.0303138494491577,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.8901,
+      "step": 1519
+    },
+    {
+      "epoch": 0.014377811789805668,
+      "grad_norm": 1.3504307270050049,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.8822,
+      "step": 1550
+    },
+    {
+      "epoch": 0.014665368025601781,
+      "grad_norm": 1.4113889932632446,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.8784,
+      "step": 1581
+    },
+    {
+      "epoch": 0.014952924261397894,
+      "grad_norm": 1.0135654211044312,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.8848,
+      "step": 1612
+    },
+    {
+      "epoch": 0.015240480497194007,
+      "grad_norm": 1.190436601638794,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.8833,
+      "step": 1643
+    },
+    {
+      "epoch": 0.01552803673299012,
+      "grad_norm": 1.0690772533416748,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.871,
+      "step": 1674
+    },
+    {
+      "epoch": 0.015815592968786235,
+      "grad_norm": 1.8002996444702148,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.8676,
+      "step": 1705
+    },
+    {
+      "epoch": 0.016103149204582348,
+      "grad_norm": 1.1526492834091187,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.8663,
+      "step": 1736
+    },
+    {
+      "epoch": 0.01639070544037846,
+      "grad_norm": 1.0163888931274414,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.8499,
+      "step": 1767
+    },
+    {
+      "epoch": 0.016678261676174574,
+      "grad_norm": 1.2611489295959473,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.8662,
+      "step": 1798
+    },
+    {
+      "epoch": 0.016965817911970688,
+      "grad_norm": 1.2373474836349487,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.8502,
+      "step": 1829
+    },
+    {
+      "epoch": 0.0172533741477668,
+      "grad_norm": 1.1296851634979248,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.8484,
+      "step": 1860
+    },
+    {
+      "epoch": 0.017540930383562914,
+      "grad_norm": 1.0827291011810303,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.8544,
+      "step": 1891
+    },
+    {
+      "epoch": 0.017828486619359027,
+      "grad_norm": 1.3426434993743896,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.857,
+      "step": 1922
+    },
+    {
+      "epoch": 0.01811604285515514,
+      "grad_norm": 1.201955795288086,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.8603,
+      "step": 1953
+    },
+    {
+      "epoch": 0.018403599090951253,
+      "grad_norm": 1.3037333488464355,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.8452,
+      "step": 1984
+    },
+    {
+      "epoch": 0.018691155326747366,
+      "grad_norm": 0.8663549423217773,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.8372,
+      "step": 2015
+    },
+    {
+      "epoch": 0.018978711562543483,
+      "grad_norm": 0.9077154397964478,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.8541,
+      "step": 2046
+    },
+    {
+      "epoch": 0.019266267798339596,
+      "grad_norm": 0.9359773397445679,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.843,
+      "step": 2077
+    },
+    {
+      "epoch": 0.01955382403413571,
+      "grad_norm": 1.0448205471038818,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.8461,
+      "step": 2108
+    },
+    {
+      "epoch": 0.019841380269931822,
+      "grad_norm": 1.0004512071609497,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.8451,
+      "step": 2139
+    },
+    {
+      "epoch": 0.020128936505727935,
+      "grad_norm": 0.9513603448867798,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.8404,
+      "step": 2170
+    },
+    {
+      "epoch": 0.02041649274152405,
+      "grad_norm": 0.8558681607246399,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.8436,
+      "step": 2201
+    },
+    {
+      "epoch": 0.02070404897732016,
+      "grad_norm": 1.0582232475280762,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.8317,
+      "step": 2232
+    },
+    {
+      "epoch": 0.020991605213116275,
+      "grad_norm": 0.8992099761962891,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.8263,
+      "step": 2263
+    },
+    {
+      "epoch": 0.021279161448912388,
+      "grad_norm": 1.0153640508651733,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.816,
+      "step": 2294
+    },
+    {
+      "epoch": 0.0215667176847085,
+      "grad_norm": 0.8875217437744141,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.8287,
+      "step": 2325
+    },
+    {
+      "epoch": 0.021854273920504614,
+      "grad_norm": 0.9286942481994629,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.8359,
+      "step": 2356
+    },
+    {
+      "epoch": 0.022141830156300727,
+      "grad_norm": 1.0928508043289185,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.8214,
+      "step": 2387
+    },
+    {
+      "epoch": 0.02242938639209684,
+      "grad_norm": 1.0555698871612549,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.8254,
+      "step": 2418
+    },
+    {
+      "epoch": 0.022716942627892953,
+      "grad_norm": 0.7832269668579102,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.822,
+      "step": 2449
+    },
+    {
+      "epoch": 0.02300449886368907,
+      "grad_norm": 0.9921287298202515,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.8266,
+      "step": 2480
+    },
+    {
+      "epoch": 0.023292055099485183,
+      "grad_norm": 0.9082629084587097,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.8309,
+      "step": 2511
+    },
+    {
+      "epoch": 0.023579611335281296,
+      "grad_norm": 0.6366026401519775,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.8246,
+      "step": 2542
+    },
+    {
+      "epoch": 0.02386716757107741,
+      "grad_norm": 0.7414658665657043,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.8231,
+      "step": 2573
+    },
+    {
+      "epoch": 0.024154723806873522,
+      "grad_norm": 1.1124039888381958,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.819,
+      "step": 2604
+    },
+    {
+      "epoch": 0.024442280042669635,
+      "grad_norm": 0.7437085509300232,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.8018,
+      "step": 2635
+    },
+    {
+      "epoch": 0.02472983627846575,
+      "grad_norm": 0.809686541557312,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.8117,
+      "step": 2666
+    },
+    {
+      "epoch": 0.02501739251426186,
+      "grad_norm": 0.8334315419197083,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.8065,
+      "step": 2697
+    },
+    {
+      "epoch": 0.025304948750057975,
+      "grad_norm": 0.8860774636268616,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.8051,
+      "step": 2728
+    },
+    {
+      "epoch": 0.025592504985854088,
+      "grad_norm": 1.0246986150741577,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.817,
+      "step": 2759
+    },
+    {
+      "epoch": 0.0258800612216502,
+      "grad_norm": 0.9289675354957581,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.8166,
+      "step": 2790
+    },
+    {
+      "epoch": 0.026167617457446314,
+      "grad_norm": 0.8356702327728271,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.7965,
+      "step": 2821
+    },
+    {
+      "epoch": 0.026455173693242427,
+      "grad_norm": 0.8671677708625793,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.8011,
+      "step": 2852
+    },
+    {
+      "epoch": 0.02674272992903854,
+      "grad_norm": 0.7215815186500549,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.8101,
+      "step": 2883
+    },
+    {
+      "epoch": 0.027030286164834653,
+      "grad_norm": 0.7657960057258606,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.8125,
+      "step": 2914
+    },
+    {
+      "epoch": 0.02731784240063077,
+      "grad_norm": 0.9577224254608154,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.8057,
+      "step": 2945
+    },
+    {
+      "epoch": 0.027605398636426883,
+      "grad_norm": 0.8292474746704102,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.8124,
+      "step": 2976
+    },
+    {
+      "epoch": 0.027892954872222996,
+      "grad_norm": 0.7864797711372375,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.8188,
+      "step": 3007
+    },
+    {
+      "epoch": 0.02818051110801911,
+      "grad_norm": 0.7558257579803467,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.8007,
+      "step": 3038
+    },
+    {
+      "epoch": 0.028468067343815222,
+      "grad_norm": 0.8115010857582092,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.8031,
+      "step": 3069
+    },
+    {
+      "epoch": 0.028755623579611336,
+      "grad_norm": 0.7696826457977295,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.7943,
+      "step": 3100
+    },
+    {
+      "epoch": 0.02904317981540745,
+      "grad_norm": 0.8541676998138428,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.8076,
+      "step": 3131
+    },
+    {
+      "epoch": 0.029330736051203562,
+      "grad_norm": 0.8071252107620239,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.8013,
+      "step": 3162
+    },
+    {
+      "epoch": 0.029618292286999675,
+      "grad_norm": 0.7903591990470886,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.8044,
+      "step": 3193
+    },
+    {
+      "epoch": 0.029905848522795788,
+      "grad_norm": 0.8176108002662659,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.8071,
+      "step": 3224
+    },
+    {
+      "epoch": 0.0301934047585919,
+      "grad_norm": 0.8619785308837891,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.7933,
+      "step": 3255
+    },
+    {
+      "epoch": 0.030480960994388014,
+      "grad_norm": 0.9317312240600586,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.7923,
+      "step": 3286
+    },
+    {
+      "epoch": 0.030768517230184127,
+      "grad_norm": 4.923175811767578,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.8053,
+      "step": 3317
+    },
+    {
+      "epoch": 0.03105607346598024,
+      "grad_norm": 0.8844607472419739,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.7995,
+      "step": 3348
+    },
+    {
+      "epoch": 0.03134362970177636,
+      "grad_norm": 0.9158428311347961,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.7944,
+      "step": 3379
+    },
+    {
+      "epoch": 0.03163118593757247,
+      "grad_norm": 0.7781556844711304,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.7916,
+      "step": 3410
+    },
+    {
+      "epoch": 0.03191874217336858,
+      "grad_norm": 0.9503144025802612,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.8013,
+      "step": 3441
+    },
+    {
+      "epoch": 0.032206298409164696,
+      "grad_norm": 0.7559428215026855,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.7816,
+      "step": 3472
+    },
+    {
+      "epoch": 0.03249385464496081,
+      "grad_norm": 0.7235283851623535,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.7884,
+      "step": 3503
+    },
+    {
+      "epoch": 0.03278141088075692,
+      "grad_norm": 0.6889526844024658,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.7869,
+      "step": 3534
+    },
+    {
+      "epoch": 0.033068967116553036,
+      "grad_norm": 0.6442049741744995,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.7882,
+      "step": 3565
+    },
+    {
+      "epoch": 0.03335652335234915,
+      "grad_norm": 0.7874131798744202,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.7943,
+      "step": 3596
+    },
+    {
+      "epoch": 0.03364407958814526,
+      "grad_norm": 0.9890303611755371,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.7953,
+      "step": 3627
+    },
+    {
+      "epoch": 0.033931635823941375,
+      "grad_norm": 0.7489719390869141,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.7941,
+      "step": 3658
+    },
+    {
+      "epoch": 0.03421919205973749,
+      "grad_norm": 1.4524290561676025,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.7871,
+      "step": 3689
+    },
+    {
+      "epoch": 0.0345067482955336,
+      "grad_norm": 0.9255936145782471,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.7832,
+      "step": 3720
+    },
+    {
+      "epoch": 0.034794304531329714,
+      "grad_norm": 0.7341301441192627,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.7739,
+      "step": 3751
+    },
+    {
+      "epoch": 0.03508186076712583,
+      "grad_norm": 0.8778953552246094,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.7825,
+      "step": 3782
+    },
+    {
+      "epoch": 0.03536941700292194,
+      "grad_norm": 0.7216904163360596,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.7897,
+      "step": 3813
+    },
+    {
+      "epoch": 0.035656973238718054,
+      "grad_norm": 0.682104766368866,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.7883,
+      "step": 3844
+    },
+    {
+      "epoch": 0.03594452947451417,
+      "grad_norm": 0.6915758848190308,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.7833,
+      "step": 3875
+    },
+    {
+      "epoch": 0.03623208571031028,
+      "grad_norm": 0.69737309217453,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.7761,
+      "step": 3906
+    },
+    {
+      "epoch": 0.03651964194610639,
+      "grad_norm": 0.6854519844055176,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.7836,
+      "step": 3937
+    },
+    {
+      "epoch": 0.036807198181902506,
+      "grad_norm": 0.7395520806312561,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.7879,
+      "step": 3968
+    },
+    {
+      "epoch": 0.03709475441769862,
+      "grad_norm": 0.8215503096580505,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.7789,
+      "step": 3999
+    },
+    {
+      "epoch": 0.03738231065349473,
+      "grad_norm": 0.7327520251274109,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.7822,
+      "step": 4030
+    },
+    {
+      "epoch": 0.03766986688929085,
+      "grad_norm": 0.6182845234870911,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.7706,
+      "step": 4061
+    },
+    {
+      "epoch": 0.037957423125086966,
+      "grad_norm": 0.6680454611778259,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.783,
+      "step": 4092
+    },
+    {
+      "epoch": 0.03824497936088308,
+      "grad_norm": 0.7800632119178772,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.7712,
+      "step": 4123
+    },
+    {
+      "epoch": 0.03853253559667919,
+      "grad_norm": 1.3335139751434326,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.7773,
+      "step": 4154
+    },
+    {
+      "epoch": 0.038820091832475305,
+      "grad_norm": 0.851414144039154,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.7887,
+      "step": 4185
+    },
+    {
+      "epoch": 0.03910764806827142,
+      "grad_norm": 0.9367514252662659,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.7665,
+      "step": 4216
+    },
+    {
+      "epoch": 0.03939520430406753,
+      "grad_norm": 0.9181923270225525,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.7656,
+      "step": 4247
+    },
+    {
+      "epoch": 0.039682760539863644,
+      "grad_norm": 0.7090054154396057,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.78,
+      "step": 4278
+    },
+    {
+      "epoch": 0.03997031677565976,
+      "grad_norm": 0.7867220640182495,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.7642,
+      "step": 4309
+    },
+    {
+      "epoch": 0.04025787301145587,
+      "grad_norm": 0.6757919788360596,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.7761,
+      "step": 4340
+    },
+    {
+      "epoch": 0.040545429247251984,
+      "grad_norm": 0.7119040489196777,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.7749,
+      "step": 4371
+    },
+    {
+      "epoch": 0.0408329854830481,
+      "grad_norm": 0.7401456236839294,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.7827,
+      "step": 4402
+    },
+    {
+      "epoch": 0.04112054171884421,
+      "grad_norm": 0.7937046885490417,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.7803,
+      "step": 4433
+    },
+    {
+      "epoch": 0.04140809795464032,
+      "grad_norm": 0.6040141582489014,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.7716,
+      "step": 4464
+    },
+    {
+      "epoch": 0.041695654190436436,
+      "grad_norm": 0.6961768269538879,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.7823,
+      "step": 4495
+    },
+    {
+      "epoch": 0.04198321042623255,
+      "grad_norm": 0.842772901058197,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.7803,
+      "step": 4526
+    },
+    {
+      "epoch": 0.04227076666202866,
+      "grad_norm": 0.7007623314857483,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.7621,
+      "step": 4557
+    },
+    {
+      "epoch": 0.042558322897824775,
+      "grad_norm": 0.8964999914169312,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.7725,
+      "step": 4588
+    },
+    {
+      "epoch": 0.04284587913362089,
+      "grad_norm": 0.6525081396102905,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.7713,
+      "step": 4619
+    },
+    {
+      "epoch": 0.043133435369417,
+      "grad_norm": 0.7347533106803894,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.7678,
+      "step": 4650
+    },
+    {
+      "epoch": 0.043420991605213115,
+      "grad_norm": 0.898430585861206,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.7768,
+      "step": 4681
+    },
+    {
+      "epoch": 0.04370854784100923,
+      "grad_norm": 0.8022106289863586,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.7613,
+      "step": 4712
+    },
+    {
+      "epoch": 0.04399610407680534,
+      "grad_norm": 0.6806633472442627,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.7611,
+      "step": 4743
+    },
+    {
+      "epoch": 0.044283660312601454,
+      "grad_norm": 0.6868746280670166,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.768,
+      "step": 4774
+    },
+    {
+      "epoch": 0.04457121654839757,
+      "grad_norm": 0.6708130836486816,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.7656,
+      "step": 4805
+    },
+    {
+      "epoch": 0.04485877278419368,
+      "grad_norm": 0.8395335078239441,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.7606,
+      "step": 4836
+    },
+    {
+      "epoch": 0.045146329019989793,
+      "grad_norm": 0.7094994783401489,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.7588,
+      "step": 4867
+    },
+    {
+      "epoch": 0.04543388525578591,
+      "grad_norm": 0.7718915343284607,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.7605,
+      "step": 4898
+    },
+    {
+      "epoch": 0.04572144149158202,
+      "grad_norm": 0.7593154311180115,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.7699,
+      "step": 4929
+    },
+    {
+      "epoch": 0.04600899772737814,
+      "grad_norm": 0.7768173217773438,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.7655,
+      "step": 4960
+    },
+    {
+      "epoch": 0.04629655396317425,
+      "grad_norm": 22.10868263244629,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.7834,
+      "step": 4991
+    },
+    {
+      "epoch": 0.046584110198970366,
+      "grad_norm": 0.7258509993553162,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.7762,
+      "step": 5022
+    },
+    {
+      "epoch": 0.04687166643476648,
+      "grad_norm": 0.6087211966514587,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.7764,
+      "step": 5053
+    },
+    {
+      "epoch": 0.04715922267056259,
+      "grad_norm": 0.7252562642097473,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.764,
+      "step": 5084
+    },
+    {
+      "epoch": 0.047446778906358705,
+      "grad_norm": 0.6546025276184082,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.7662,
+      "step": 5115
+    },
+    {
+      "epoch": 0.04773433514215482,
+      "grad_norm": 0.8831254243850708,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.7671,
+      "step": 5146
+    },
+    {
+      "epoch": 0.04802189137795093,
+      "grad_norm": 0.6685829162597656,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.7673,
+      "step": 5177
+    },
+    {
+      "epoch": 0.048309447613747045,
+      "grad_norm": 0.8013454079627991,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.7584,
+      "step": 5208
+    },
+    {
+      "epoch": 0.04859700384954316,
+      "grad_norm": 0.7176809906959534,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.741,
+      "step": 5239
+    },
+    {
+      "epoch": 0.04888456008533927,
+      "grad_norm": 0.7257890701293945,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.737,
+      "step": 5270
+    },
+    {
+      "epoch": 0.049172116321135384,
+      "grad_norm": 0.5510952472686768,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.7593,
+      "step": 5301
+    },
+    {
+      "epoch": 0.0494596725569315,
+      "grad_norm": 0.6861957907676697,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.7628,
+      "step": 5332
+    },
+    {
+      "epoch": 0.04974722879272761,
+      "grad_norm": 0.8587688207626343,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.7727,
+      "step": 5363
+    },
+    {
+      "epoch": 0.05003478502852372,
+      "grad_norm": 0.8064201474189758,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.7518,
+      "step": 5394
+    },
+    {
+      "epoch": 0.050322341264319836,
+      "grad_norm": 0.616675853729248,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.7441,
+      "step": 5425
+    },
+    {
+      "epoch": 0.05060989750011595,
+      "grad_norm": 0.649145245552063,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.7616,
+      "step": 5456
+    },
+    {
+      "epoch": 0.05089745373591206,
+      "grad_norm": 0.7101767063140869,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.7415,
+      "step": 5487
+    },
+    {
+      "epoch": 0.051185009971708176,
+      "grad_norm": 0.707365095615387,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.75,
+      "step": 5518
+    },
+    {
+      "epoch": 0.05147256620750429,
+      "grad_norm": 0.84593266248703,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.7518,
+      "step": 5549
+    },
+    {
+      "epoch": 0.0517601224433004,
+      "grad_norm": 0.7127841711044312,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.7542,
+      "step": 5580
+    },
+    {
+      "epoch": 0.052047678679096515,
+      "grad_norm": 0.6939860582351685,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.7644,
+      "step": 5611
+    },
+    {
+      "epoch": 0.05233523491489263,
+      "grad_norm": 0.6775111556053162,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.7527,
+      "step": 5642
+    },
+    {
+      "epoch": 0.05262279115068874,
+      "grad_norm": 0.714107096195221,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.7688,
+      "step": 5673
+    },
+    {
+      "epoch": 0.052910347386484854,
+      "grad_norm": 0.6642836928367615,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.7419,
+      "step": 5704
+    },
+    {
+      "epoch": 0.05319790362228097,
+      "grad_norm": 0.6652647852897644,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.7364,
+      "step": 5735
+    },
+    {
+      "epoch": 0.05348545985807708,
+      "grad_norm": 0.7523749470710754,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.7417,
+      "step": 5766
+    },
+    {
+      "epoch": 0.053773016093873194,
+      "grad_norm": 0.7240698337554932,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.7475,
+      "step": 5797
+    },
+    {
+      "epoch": 0.05406057232966931,
+      "grad_norm": 0.6656080484390259,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.7549,
+      "step": 5828
+    },
+    {
+      "epoch": 0.05434812856546543,
+      "grad_norm": 0.7825058102607727,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.7617,
+      "step": 5859
+    },
+    {
+      "epoch": 0.05463568480126154,
+      "grad_norm": 0.6925270557403564,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.7645,
+      "step": 5890
+    },
+    {
+      "epoch": 0.05492324103705765,
+      "grad_norm": 0.6845418810844421,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.7651,
+      "step": 5921
+    },
+    {
+      "epoch": 0.055210797272853766,
+      "grad_norm": 0.7644496560096741,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.7416,
+      "step": 5952
+    },
+    {
+      "epoch": 0.05549835350864988,
+      "grad_norm": 0.6768073439598083,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.7382,
+      "step": 5983
+    },
+    {
+      "epoch": 0.05578590974444599,
+      "grad_norm": 0.7582330107688904,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.7576,
+      "step": 6014
+    },
+    {
+      "epoch": 0.056073465980242106,
+      "grad_norm": 0.7167056202888489,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.7531,
+      "step": 6045
+    },
+    {
+      "epoch": 0.05636102221603822,
+      "grad_norm": 0.7577204704284668,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.7435,
+      "step": 6076
+    },
+    {
+      "epoch": 0.05664857845183433,
+      "grad_norm": 0.6813349723815918,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.7394,
+      "step": 6107
+    },
+    {
+      "epoch": 0.056936134687630445,
+      "grad_norm": 0.7912815809249878,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.7497,
+      "step": 6138
+    },
+    {
+      "epoch": 0.05722369092342656,
+      "grad_norm": 0.6915249228477478,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.7442,
+      "step": 6169
+    },
+    {
+      "epoch": 0.05751124715922267,
+      "grad_norm": 0.6465253829956055,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.748,
+      "step": 6200
+    },
+    {
+      "epoch": 0.057798803395018784,
+      "grad_norm": 0.7075664401054382,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.7436,
+      "step": 6231
+    },
+    {
+      "epoch": 0.0580863596308149,
+      "grad_norm": 0.5963169932365417,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.7528,
+      "step": 6262
+    },
+    {
+      "epoch": 0.05837391586661101,
+      "grad_norm": 0.7071893811225891,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.7481,
+      "step": 6293
+    },
+    {
+      "epoch": 0.058661472102407124,
+      "grad_norm": 0.6649565696716309,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.7462,
+      "step": 6324
+    },
+    {
+      "epoch": 0.05894902833820324,
+      "grad_norm": 0.6576278209686279,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.7313,
+      "step": 6355
+    },
+    {
+      "epoch": 0.05923658457399935,
+      "grad_norm": 0.6180335283279419,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.7498,
+      "step": 6386
+    },
+    {
+      "epoch": 0.05952414080979546,
+      "grad_norm": 0.5831409096717834,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.7361,
+      "step": 6417
+    },
+    {
+      "epoch": 0.059811697045591576,
+      "grad_norm": 0.6521987318992615,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.7501,
+      "step": 6448
+    },
+    {
+      "epoch": 0.06009925328138769,
+      "grad_norm": 0.6368945240974426,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.7456,
+      "step": 6479
+    },
+    {
+      "epoch": 0.0603868095171838,
+      "grad_norm": 0.6165626049041748,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.7438,
+      "step": 6510
+    },
+    {
+      "epoch": 0.060674365752979915,
+      "grad_norm": 0.7067050337791443,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.7499,
+      "step": 6541
+    },
+    {
+      "epoch": 0.06096192198877603,
+      "grad_norm": 0.7632570862770081,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.7356,
+      "step": 6572
+    },
+    {
+      "epoch": 0.06124947822457214,
+      "grad_norm": 0.838828980922699,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.7384,
+      "step": 6603
+    },
+    {
+      "epoch": 0.061537034460368255,
+      "grad_norm": 0.7371137142181396,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.7423,
+      "step": 6634
+    },
+    {
+      "epoch": 0.06182459069616437,
+      "grad_norm": 0.6346718072891235,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.7354,
+      "step": 6665
+    },
+    {
+      "epoch": 0.06211214693196048,
+      "grad_norm": 0.6456010341644287,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.7342,
+      "step": 6696
+    },
+    {
+      "epoch": 0.062399703167756594,
+      "grad_norm": 0.6201857924461365,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.7282,
+      "step": 6727
+    },
+    {
+      "epoch": 0.06268725940355271,
+      "grad_norm": 0.6899628043174744,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.7375,
+      "step": 6758
+    },
+    {
+      "epoch": 0.06297481563934883,
+      "grad_norm": 0.599892258644104,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.7409,
+      "step": 6789
+    },
+    {
+      "epoch": 0.06326237187514494,
+      "grad_norm": 0.6443545818328857,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.7455,
+      "step": 6820
+    },
+    {
+      "epoch": 0.06354992811094105,
+      "grad_norm": 0.7208391427993774,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.7491,
+      "step": 6851
+    },
+    {
+      "epoch": 0.06383748434673717,
+      "grad_norm": 0.7535425424575806,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.7396,
+      "step": 6882
+    },
+    {
+      "epoch": 0.06412504058253328,
+      "grad_norm": 0.8142176866531372,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.7525,
+      "step": 6913
+    },
+    {
+      "epoch": 0.06441259681832939,
+      "grad_norm": 0.7619569897651672,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.7308,
+      "step": 6944
+    },
+    {
+      "epoch": 0.0647001530541255,
+      "grad_norm": 0.6831880807876587,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.7323,
+      "step": 6975
+    },
+    {
+      "epoch": 0.06498770928992162,
+      "grad_norm": 0.7584510445594788,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.7305,
+      "step": 7006
+    },
+    {
+      "epoch": 0.06527526552571773,
+      "grad_norm": 0.5771958827972412,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.7292,
+      "step": 7037
+    },
+    {
+      "epoch": 0.06556282176151385,
+      "grad_norm": 0.6861974596977234,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.7301,
+      "step": 7068
+    },
+    {
+      "epoch": 0.06585037799730996,
+      "grad_norm": 0.6061118841171265,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.738,
+      "step": 7099
+    },
+    {
+      "epoch": 0.06613793423310607,
+      "grad_norm": 0.5882508158683777,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.7499,
+      "step": 7130
+    },
+    {
+      "epoch": 0.06642549046890218,
+      "grad_norm": 0.6508737206459045,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.7484,
+      "step": 7161
+    },
+    {
+      "epoch": 0.0667130467046983,
+      "grad_norm": 0.5774248242378235,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.7351,
+      "step": 7192
+    },
+    {
+      "epoch": 0.06700060294049441,
+      "grad_norm": 0.8253674507141113,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.7329,
+      "step": 7223
+    },
+    {
+      "epoch": 0.06728815917629052,
+      "grad_norm": 0.6259687542915344,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.7375,
+      "step": 7254
+    },
+    {
+      "epoch": 0.06757571541208664,
+      "grad_norm": 0.6426525115966797,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.732,
+      "step": 7285
+    },
+    {
+      "epoch": 0.06786327164788275,
+      "grad_norm": 0.7058547139167786,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.7344,
+      "step": 7316
+    },
+    {
+      "epoch": 0.06815082788367886,
+      "grad_norm": 0.5909351706504822,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.7298,
+      "step": 7347
+    },
+    {
+      "epoch": 0.06843838411947498,
+      "grad_norm": 0.6617700457572937,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.7443,
+      "step": 7378
+    },
+    {
+      "epoch": 0.06872594035527109,
+      "grad_norm": 0.6690764427185059,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.7407,
+      "step": 7409
+    },
+    {
+      "epoch": 0.0690134965910672,
+      "grad_norm": 0.6452279686927795,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.7375,
+      "step": 7440
+    },
+    {
+      "epoch": 0.06930105282686332,
+      "grad_norm": 0.6305842399597168,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.7274,
+      "step": 7471
+    },
+    {
+      "epoch": 0.06958860906265943,
+      "grad_norm": 0.6651537418365479,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.7333,
+      "step": 7502
+    },
+    {
+      "epoch": 0.06987616529845554,
+      "grad_norm": 0.7118179202079773,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.7322,
+      "step": 7533
+    },
+    {
+      "epoch": 0.07016372153425166,
+      "grad_norm": 0.618417501449585,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.7286,
+      "step": 7564
+    },
+    {
+      "epoch": 0.07045127777004777,
+      "grad_norm": 0.5909223556518555,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.7338,
+      "step": 7595
+    },
+    {
+      "epoch": 0.07073883400584388,
+      "grad_norm": 0.6071949601173401,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.7218,
+      "step": 7626
+    },
+    {
+      "epoch": 0.07102639024164,
+      "grad_norm": 0.5909284353256226,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.7307,
+      "step": 7657
+    },
+    {
+      "epoch": 0.07131394647743611,
+      "grad_norm": 0.5202866792678833,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.7335,
+      "step": 7688
+    },
+    {
+      "epoch": 0.07160150271323222,
+      "grad_norm": 0.6365333795547485,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.724,
+      "step": 7719
+    },
+    {
+      "epoch": 0.07188905894902833,
+      "grad_norm": 0.62083500623703,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.7324,
+      "step": 7750
+    },
+    {
+      "epoch": 0.07217661518482445,
+      "grad_norm": 0.651817262172699,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.737,
+      "step": 7781
+    },
+    {
+      "epoch": 0.07246417142062056,
+      "grad_norm": 0.7566159963607788,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.7341,
+      "step": 7812
+    },
+    {
+      "epoch": 0.07275172765641667,
+      "grad_norm": 0.5911855697631836,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.7457,
+      "step": 7843
+    },
+    {
+      "epoch": 0.07303928389221279,
+      "grad_norm": 0.730266273021698,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.7341,
+      "step": 7874
+    },
+    {
+      "epoch": 0.0733268401280089,
+      "grad_norm": 0.813572883605957,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.7241,
+      "step": 7905
+    },
+    {
+      "epoch": 0.07361439636380501,
+      "grad_norm": 0.6070415377616882,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.7225,
+      "step": 7936
+    },
+    {
+      "epoch": 0.07390195259960113,
+      "grad_norm": 0.6287768483161926,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.7244,
+      "step": 7967
+    },
+    {
+      "epoch": 0.07418950883539724,
+      "grad_norm": 0.6290640830993652,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.7214,
+      "step": 7998
+    },
+    {
+      "epoch": 0.07447706507119335,
+      "grad_norm": 0.7656108140945435,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.7232,
+      "step": 8029
+    },
+    {
+      "epoch": 0.07476462130698946,
+      "grad_norm": 0.5660067796707153,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.7256,
+      "step": 8060
+    },
+    {
+      "epoch": 0.07505217754278559,
+      "grad_norm": 0.5883699655532837,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.7252,
+      "step": 8091
+    },
+    {
+      "epoch": 0.0753397337785817,
+      "grad_norm": 0.6301703453063965,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.7273,
+      "step": 8122
+    },
+    {
+      "epoch": 0.07562729001437782,
+      "grad_norm": 0.8404330015182495,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.7256,
+      "step": 8153
+    },
+    {
+      "epoch": 0.07591484625017393,
+      "grad_norm": 0.5907132625579834,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.7316,
+      "step": 8184
+    },
+    {
+      "epoch": 0.07620240248597004,
+      "grad_norm": 0.6496497988700867,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.7247,
+      "step": 8215
+    },
+    {
+      "epoch": 0.07648995872176616,
+      "grad_norm": 0.8407059907913208,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.7335,
+      "step": 8246
+    },
+    {
+      "epoch": 0.07677751495756227,
+      "grad_norm": 0.6478541493415833,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.7237,
+      "step": 8277
+    },
+    {
+      "epoch": 0.07706507119335838,
+      "grad_norm": 0.591346263885498,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.7234,
+      "step": 8308
+    },
+    {
+      "epoch": 0.0773526274291545,
+      "grad_norm": 0.7245597839355469,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.7311,
+      "step": 8339
+    },
+    {
+      "epoch": 0.07764018366495061,
+      "grad_norm": 0.5755163431167603,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.7138,
+      "step": 8370
+    },
+    {
+      "epoch": 0.07792773990074672,
+      "grad_norm": 0.6150103211402893,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.7283,
+      "step": 8401
+    },
+    {
+      "epoch": 0.07821529613654284,
+      "grad_norm": 0.6257421374320984,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.7243,
+      "step": 8432
+    },
+    {
+      "epoch": 0.07850285237233895,
+      "grad_norm": 0.5830650329589844,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.7258,
+      "step": 8463
+    },
+    {
+      "epoch": 0.07879040860813506,
+      "grad_norm": 0.6041871905326843,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.7195,
+      "step": 8494
+    },
+    {
+      "epoch": 0.07907796484393118,
+      "grad_norm": 0.599134624004364,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.727,
+      "step": 8525
+    },
+    {
+      "epoch": 0.07936552107972729,
+      "grad_norm": 0.6479268670082092,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.719,
+      "step": 8556
+    },
+    {
+      "epoch": 0.0796530773155234,
+      "grad_norm": 0.6495187282562256,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.7183,
+      "step": 8587
+    },
+    {
+      "epoch": 0.07994063355131951,
+      "grad_norm": 0.633544385433197,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.7251,
+      "step": 8618
+    },
+    {
+      "epoch": 0.08022818978711563,
+      "grad_norm": 0.6535078287124634,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.7221,
+      "step": 8649
+    },
+    {
+      "epoch": 0.08051574602291174,
+      "grad_norm": 0.6529403924942017,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.7254,
+      "step": 8680
+    },
+    {
+      "epoch": 0.08080330225870785,
+      "grad_norm": 0.6234943270683289,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.7222,
+      "step": 8711
+    },
+    {
+      "epoch": 0.08109085849450397,
+      "grad_norm": 0.6449539661407471,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.7225,
+      "step": 8742
+    },
+    {
+      "epoch": 0.08137841473030008,
+      "grad_norm": 0.6134011745452881,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.7233,
+      "step": 8773
+    },
+    {
+      "epoch": 0.0816659709660962,
+      "grad_norm": 0.6429490447044373,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.7301,
+      "step": 8804
+    },
+    {
+      "epoch": 0.0819535272018923,
+      "grad_norm": 0.689408004283905,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.7145,
+      "step": 8835
+    },
+    {
+      "epoch": 0.08224108343768842,
+      "grad_norm": 0.6384241580963135,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.7163,
+      "step": 8866
+    },
+    {
+      "epoch": 0.08252863967348453,
+      "grad_norm": 0.6733195185661316,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.7336,
+      "step": 8897
+    },
+    {
+      "epoch": 0.08281619590928065,
+      "grad_norm": 0.5776221752166748,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.723,
+      "step": 8928
+    },
+    {
+      "epoch": 0.08310375214507676,
+      "grad_norm": 0.6372654438018799,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.7213,
+      "step": 8959
+    },
+    {
+      "epoch": 0.08339130838087287,
+      "grad_norm": 0.6379313468933105,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.7236,
+      "step": 8990
+    },
+    {
+      "epoch": 0.08367886461666899,
+      "grad_norm": 0.6363175511360168,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.7273,
+      "step": 9021
+    },
+    {
+      "epoch": 0.0839664208524651,
+      "grad_norm": 0.5839366316795349,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.7345,
+      "step": 9052
+    },
+    {
+      "epoch": 0.08425397708826121,
+      "grad_norm": 0.6896429061889648,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.7256,
+      "step": 9083
+    },
+    {
+      "epoch": 0.08454153332405732,
+      "grad_norm": 0.6036957502365112,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.7125,
+      "step": 9114
+    },
+    {
+      "epoch": 0.08482908955985344,
+      "grad_norm": 0.5292845964431763,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.7068,
+      "step": 9145
+    },
+    {
+      "epoch": 0.08511664579564955,
+      "grad_norm": 0.7312672138214111,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.7159,
+      "step": 9176
+    },
+    {
+      "epoch": 0.08540420203144566,
+      "grad_norm": 0.6188672780990601,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.715,
+      "step": 9207
+    },
+    {
+      "epoch": 0.08569175826724178,
+      "grad_norm": 0.6074671745300293,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.7053,
+      "step": 9238
+    },
+    {
+      "epoch": 0.08597931450303789,
+      "grad_norm": 0.6689853072166443,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.7234,
+      "step": 9269
+    },
+    {
+      "epoch": 0.086266870738834,
+      "grad_norm": 0.5816609859466553,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.7169,
+      "step": 9300
+    },
+    {
+      "epoch": 0.08655442697463012,
+      "grad_norm": 0.6053051352500916,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.7251,
+      "step": 9331
+    },
+    {
+      "epoch": 0.08684198321042623,
+      "grad_norm": 0.568250298500061,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.7241,
+      "step": 9362
+    },
+    {
+      "epoch": 0.08712953944622234,
+      "grad_norm": 0.516308069229126,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.7113,
+      "step": 9393
+    },
+    {
+      "epoch": 0.08741709568201846,
+      "grad_norm": 0.5996320247650146,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.7212,
+      "step": 9424
+    },
+    {
+      "epoch": 0.08770465191781457,
+      "grad_norm": 0.9900774955749512,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.7143,
+      "step": 9455
+    },
+    {
+      "epoch": 0.08799220815361068,
+      "grad_norm": 0.6253843903541565,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.7134,
+      "step": 9486
+    },
+    {
+      "epoch": 0.0882797643894068,
+      "grad_norm": 0.6412758231163025,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.7102,
+      "step": 9517
+    },
+    {
+      "epoch": 0.08856732062520291,
+      "grad_norm": 0.5213416218757629,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.717,
+      "step": 9548
+    },
+    {
+      "epoch": 0.08885487686099902,
+      "grad_norm": 0.7382434010505676,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.7157,
+      "step": 9579
+    },
+    {
+      "epoch": 0.08914243309679513,
+      "grad_norm": 0.6071272492408752,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.709,
+      "step": 9610
+    },
+    {
+      "epoch": 0.08942998933259125,
+      "grad_norm": 0.5866951942443848,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.7131,
+      "step": 9641
+    },
+    {
+      "epoch": 0.08971754556838736,
+      "grad_norm": 0.6112024784088135,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.7063,
+      "step": 9672
+    },
+    {
+      "epoch": 0.09000510180418347,
+      "grad_norm": 0.5468956232070923,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.7083,
+      "step": 9703
+    },
+    {
+      "epoch": 0.09029265803997959,
+      "grad_norm": 0.6030653119087219,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.7134,
+      "step": 9734
+    },
+    {
+      "epoch": 0.0905802142757757,
+      "grad_norm": 0.7345271706581116,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.7211,
+      "step": 9765
+    },
+    {
+      "epoch": 0.09086777051157181,
+      "grad_norm": 0.6731435656547546,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.7032,
+      "step": 9796
+    },
+    {
+      "epoch": 0.09115532674736793,
+      "grad_norm": 0.5787028670310974,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.7217,
+      "step": 9827
+    },
+    {
+      "epoch": 0.09144288298316404,
+      "grad_norm": 0.7460885047912598,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.7162,
+      "step": 9858
+    },
+    {
+      "epoch": 0.09173043921896017,
+      "grad_norm": 0.5730577111244202,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.7137,
+      "step": 9889
+    },
+    {
+      "epoch": 0.09201799545475628,
+      "grad_norm": 0.7368761897087097,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.7101,
+      "step": 9920
+    },
+    {
+      "epoch": 0.09230555169055239,
+      "grad_norm": 0.6312885880470276,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.7107,
+      "step": 9951
+    },
+    {
+      "epoch": 0.0925931079263485,
+      "grad_norm": 0.5750525593757629,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.7097,
+      "step": 9982
+    },
+    {
+      "epoch": 0.09288066416214462,
+      "grad_norm": 0.7677292823791504,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.7363,
+      "step": 10013
+    },
+    {
+      "epoch": 0.09316822039794073,
+      "grad_norm": 0.7287603616714478,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.7093,
+      "step": 10044
+    },
+    {
+      "epoch": 0.09345577663373685,
+      "grad_norm": 0.7049741744995117,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.7093,
+      "step": 10075
+    },
+    {
+      "epoch": 0.09374333286953296,
+      "grad_norm": 0.6399069428443909,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.7171,
+      "step": 10106
+    },
+    {
+      "epoch": 0.09403088910532907,
+      "grad_norm": 0.6106202006340027,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.7222,
+      "step": 10137
+    },
+    {
+      "epoch": 0.09431844534112518,
+      "grad_norm": 0.5872201919555664,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.699,
+      "step": 10168
+    },
+    {
+      "epoch": 0.0946060015769213,
+      "grad_norm": 0.5277218818664551,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.7216,
+      "step": 10199
+    },
+    {
+      "epoch": 0.09489355781271741,
+      "grad_norm": 0.6080947518348694,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.7084,
+      "step": 10230
+    },
+    {
+      "epoch": 0.09518111404851352,
+      "grad_norm": 0.6509852409362793,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.7073,
+      "step": 10261
+    },
+    {
+      "epoch": 0.09546867028430964,
+      "grad_norm": 0.5382758378982544,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.7155,
+      "step": 10292
+    },
+    {
+      "epoch": 0.09575622652010575,
+      "grad_norm": 0.5467644929885864,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.7057,
+      "step": 10323
+    },
+    {
+      "epoch": 0.09604378275590186,
+      "grad_norm": 0.7037911415100098,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.7059,
+      "step": 10354
+    },
+    {
+      "epoch": 0.09633133899169798,
+      "grad_norm": 0.643120527267456,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.6991,
+      "step": 10385
+    },
+    {
+      "epoch": 0.09661889522749409,
+      "grad_norm": 0.7134397029876709,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.7235,
+      "step": 10416
+    },
+    {
+      "epoch": 0.0969064514632902,
+      "grad_norm": 0.6029829382896423,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.7112,
+      "step": 10447
+    },
+    {
+      "epoch": 0.09719400769908632,
+      "grad_norm": 0.5507195591926575,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.7126,
+      "step": 10478
+    },
+    {
+      "epoch": 0.09748156393488243,
+      "grad_norm": 0.5905954241752625,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.7066,
+      "step": 10509
+    },
+    {
+      "epoch": 0.09776912017067854,
+      "grad_norm": 0.655809760093689,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.7117,
+      "step": 10540
+    },
+    {
+      "epoch": 0.09805667640647465,
+      "grad_norm": 0.6456587910652161,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.7153,
+      "step": 10571
+    },
+    {
+      "epoch": 0.09834423264227077,
+      "grad_norm": 0.5832169651985168,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.7154,
+      "step": 10602
+    },
+    {
+      "epoch": 0.09863178887806688,
+      "grad_norm": 0.6231696009635925,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.7035,
+      "step": 10633
+    },
+    {
+      "epoch": 0.098919345113863,
+      "grad_norm": 0.5719037055969238,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.7114,
+      "step": 10664
+    },
+    {
+      "epoch": 0.09920690134965911,
+      "grad_norm": 0.5518574714660645,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.7022,
+      "step": 10695
+    },
+    {
+      "epoch": 0.09949445758545522,
+      "grad_norm": 0.610763669013977,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.7103,
+      "step": 10726
+    },
+    {
+      "epoch": 0.09978201382125133,
+      "grad_norm": 0.595777153968811,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.7041,
+      "step": 10757
+    },
+    {
+      "epoch": 0.10006957005704745,
+      "grad_norm": 0.554775595664978,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.7161,
+      "step": 10788
+    },
+    {
+      "epoch": 0.10035712629284356,
+      "grad_norm": 0.5296738743782043,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.7101,
+      "step": 10819
+    },
+    {
+      "epoch": 0.10064468252863967,
+      "grad_norm": 0.5633993148803711,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.7028,
+      "step": 10850
+    },
+    {
+      "epoch": 0.10093223876443579,
+      "grad_norm": 0.619892954826355,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.73,
+      "step": 10881
+    },
+    {
+      "epoch": 0.1012197950002319,
+      "grad_norm": 0.5270977020263672,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.6967,
+      "step": 10912
+    },
+    {
+      "epoch": 0.10150735123602801,
+      "grad_norm": 0.597468912601471,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.7073,
+      "step": 10943
+    },
+    {
+      "epoch": 0.10179490747182413,
+      "grad_norm": 0.6410956382751465,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.7273,
+      "step": 10974
+    },
+    {
+      "epoch": 0.10208246370762024,
+      "grad_norm": 0.5290685296058655,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.7054,
+      "step": 11005
+    },
+    {
+      "epoch": 0.10237001994341635,
+      "grad_norm": 0.625141978263855,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.7015,
+      "step": 11036
+    },
+    {
+      "epoch": 0.10265757617921246,
+      "grad_norm": 0.6491115689277649,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.7103,
+      "step": 11067
+    },
+    {
+      "epoch": 0.10294513241500858,
+      "grad_norm": 0.6526436805725098,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.7062,
+      "step": 11098
+    },
+    {
+      "epoch": 0.10323268865080469,
+      "grad_norm": 0.619213342666626,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.703,
+      "step": 11129
+    },
+    {
+      "epoch": 0.1035202448866008,
+      "grad_norm": 0.6151726245880127,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.7208,
+      "step": 11160
+    },
+    {
+      "epoch": 0.10380780112239692,
+      "grad_norm": 0.7930813431739807,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.7094,
+      "step": 11191
+    },
+    {
+      "epoch": 0.10409535735819303,
+      "grad_norm": 0.5755916237831116,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.7016,
+      "step": 11222
+    },
+    {
+      "epoch": 0.10438291359398914,
+      "grad_norm": 0.6342223286628723,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.7049,
+      "step": 11253
+    },
+    {
+      "epoch": 0.10467046982978526,
+      "grad_norm": 0.6157016754150391,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.7044,
+      "step": 11284
+    },
+    {
+      "epoch": 0.10495802606558137,
+      "grad_norm": 0.55302894115448,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.7027,
+      "step": 11315
+    },
+    {
+      "epoch": 0.10524558230137748,
+      "grad_norm": 0.5279561877250671,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.7039,
+      "step": 11346
+    },
+    {
+      "epoch": 0.1055331385371736,
+      "grad_norm": 0.47922828793525696,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.695,
+      "step": 11377
+    },
+    {
+      "epoch": 0.10582069477296971,
+      "grad_norm": 0.7774313688278198,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.6911,
+      "step": 11408
+    },
+    {
+      "epoch": 0.10610825100876582,
+      "grad_norm": 0.6279293298721313,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.7028,
+      "step": 11439
+    },
+    {
+      "epoch": 0.10639580724456194,
+      "grad_norm": 0.5655359625816345,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.6885,
+      "step": 11470
+    },
+    {
+      "epoch": 0.10668336348035805,
+      "grad_norm": 0.5349294543266296,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.6984,
+      "step": 11501
+    },
+    {
+      "epoch": 0.10697091971615416,
+      "grad_norm": 0.5396154522895813,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.7012,
+      "step": 11532
+    },
+    {
+      "epoch": 0.10725847595195027,
+      "grad_norm": 0.5853836536407471,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.7125,
+      "step": 11563
+    },
+    {
+      "epoch": 0.10754603218774639,
+      "grad_norm": 0.5341833233833313,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.7085,
+      "step": 11594
+    },
+    {
+      "epoch": 0.1078335884235425,
+      "grad_norm": 0.5626436471939087,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.6921,
+      "step": 11625
+    },
+    {
+      "epoch": 0.10812114465933861,
+      "grad_norm": 0.5850298404693604,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.6929,
+      "step": 11656
+    },
+    {
+      "epoch": 0.10840870089513474,
+      "grad_norm": 0.691791296005249,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.7059,
+      "step": 11687
+    },
+    {
+      "epoch": 0.10869625713093085,
+      "grad_norm": 0.5825905799865723,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.7109,
+      "step": 11718
+    },
+    {
+      "epoch": 0.10898381336672697,
+      "grad_norm": 0.5547176003456116,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.7001,
+      "step": 11749
+    },
+    {
+      "epoch": 0.10927136960252308,
+      "grad_norm": 0.5340707302093506,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.7001,
+      "step": 11780
+    },
+    {
+      "epoch": 0.1095589258383192,
+      "grad_norm": 0.6140413284301758,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.7052,
+      "step": 11811
+    },
+    {
+      "epoch": 0.1098464820741153,
+      "grad_norm": 0.6150991320610046,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.7007,
+      "step": 11842
+    },
+    {
+      "epoch": 0.11013403830991142,
+      "grad_norm": 0.6035052537918091,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.6951,
+      "step": 11873
+    },
+    {
+      "epoch": 0.11042159454570753,
+      "grad_norm": 0.5953954458236694,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.6904,
+      "step": 11904
+    },
+    {
+      "epoch": 0.11070915078150365,
+      "grad_norm": 0.5533605217933655,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.6942,
+      "step": 11935
+    },
+    {
+      "epoch": 0.11099670701729976,
+      "grad_norm": 0.603411078453064,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.6899,
+      "step": 11966
+    },
+    {
+      "epoch": 0.11128426325309587,
+      "grad_norm": 0.6111969947814941,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.6937,
+      "step": 11997
+    },
+    {
+      "epoch": 0.11157181948889199,
+      "grad_norm": 0.6074976325035095,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.703,
+      "step": 12028
+    },
+    {
+      "epoch": 0.1118593757246881,
+      "grad_norm": 0.5913040041923523,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.6959,
+      "step": 12059
+    },
+    {
+      "epoch": 0.11214693196048421,
+      "grad_norm": 0.6213125586509705,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.7111,
+      "step": 12090
+    },
+    {
+      "epoch": 0.11243448819628032,
+      "grad_norm": 0.5172368884086609,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.7089,
+      "step": 12121
+    },
+    {
+      "epoch": 0.11272204443207644,
+      "grad_norm": 0.5970536470413208,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.6987,
+      "step": 12152
+    },
+    {
+      "epoch": 0.11300960066787255,
+      "grad_norm": 0.5105701088905334,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.7077,
+      "step": 12183
+    },
+    {
+      "epoch": 0.11329715690366866,
+      "grad_norm": 0.5650436878204346,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 0.704,
+      "step": 12214
+    },
+    {
+      "epoch": 0.11358471313946478,
+      "grad_norm": 0.562443733215332,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 0.6953,
+      "step": 12245
+    },
+    {
+      "epoch": 0.11387226937526089,
+      "grad_norm": 3.179368734359741,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 0.6982,
+      "step": 12276
+    },
+    {
+      "epoch": 0.114159825611057,
+      "grad_norm": 0.5393089056015015,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 0.6847,
+      "step": 12307
+    },
+    {
+      "epoch": 0.11444738184685312,
+      "grad_norm": 0.6538736820220947,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 0.693,
+      "step": 12338
+    },
+    {
+      "epoch": 0.11473493808264923,
+      "grad_norm": 0.6349672675132751,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 0.709,
+      "step": 12369
+    },
+    {
+      "epoch": 0.11502249431844534,
+      "grad_norm": 0.5471822619438171,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 0.6978,
+      "step": 12400
+    },
+    {
+      "epoch": 0.11531005055424146,
+      "grad_norm": 0.5674034357070923,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 0.6905,
+      "step": 12431
+    },
+    {
+      "epoch": 0.11559760679003757,
+      "grad_norm": 0.5688623785972595,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 0.691,
+      "step": 12462
+    },
+    {
+      "epoch": 0.11588516302583368,
+      "grad_norm": 0.6054248809814453,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 0.6767,
+      "step": 12493
+    },
+    {
+      "epoch": 0.1161727192616298,
+      "grad_norm": 0.507800817489624,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 0.6945,
+      "step": 12524
+    },
+    {
+      "epoch": 0.11646027549742591,
+      "grad_norm": 0.515336811542511,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 0.6949,
+      "step": 12555
+    },
+    {
+      "epoch": 0.11674783173322202,
+      "grad_norm": 0.6008026599884033,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 0.6887,
+      "step": 12586
+    },
+    {
+      "epoch": 0.11703538796901813,
+      "grad_norm": 0.6126205325126648,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 0.6982,
+      "step": 12617
+    },
+    {
+      "epoch": 0.11732294420481425,
+      "grad_norm": 0.5590875744819641,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 0.694,
+      "step": 12648
+    },
+    {
+      "epoch": 0.11761050044061036,
+      "grad_norm": 0.53928542137146,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 0.6825,
+      "step": 12679
+    },
+    {
+      "epoch": 0.11789805667640647,
+      "grad_norm": 0.6018074750900269,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 0.7038,
+      "step": 12710
+    },
+    {
+      "epoch": 0.11818561291220259,
+      "grad_norm": 0.5353229641914368,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 0.689,
+      "step": 12741
+    },
+    {
+      "epoch": 0.1184731691479987,
+      "grad_norm": 0.5861886143684387,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 0.6936,
+      "step": 12772
+    },
+    {
+      "epoch": 0.11876072538379481,
+      "grad_norm": 0.5276220440864563,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 0.6961,
+      "step": 12803
+    },
+    {
+      "epoch": 0.11904828161959093,
+      "grad_norm": 0.643604576587677,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 0.6995,
+      "step": 12834
+    },
+    {
+      "epoch": 0.11933583785538704,
+      "grad_norm": 0.5255733728408813,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 0.6879,
+      "step": 12865
+    },
+    {
+      "epoch": 0.11962339409118315,
+      "grad_norm": 0.8856157064437866,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 0.6864,
+      "step": 12896
+    },
+    {
+      "epoch": 0.11991095032697927,
+      "grad_norm": 0.6918179988861084,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 0.7054,
+      "step": 12927
+    },
+    {
+      "epoch": 0.12019850656277538,
+      "grad_norm": 0.5902060866355896,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 0.7035,
+      "step": 12958
+    },
+    {
+      "epoch": 0.12048606279857149,
+      "grad_norm": 0.5346528887748718,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 0.68,
+      "step": 12989
+    },
+    {
+      "epoch": 0.1207736190343676,
+      "grad_norm": 0.5875746607780457,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 0.7023,
+      "step": 13020
+    },
+    {
+      "epoch": 0.12106117527016372,
+      "grad_norm": 0.5587065815925598,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 0.6892,
+      "step": 13051
+    },
+    {
+      "epoch": 0.12134873150595983,
+      "grad_norm": 0.6295893788337708,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 0.6798,
+      "step": 13082
+    },
+    {
+      "epoch": 0.12163628774175594,
+      "grad_norm": 0.6536754369735718,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 0.7022,
+      "step": 13113
+    },
+    {
+      "epoch": 0.12192384397755206,
+      "grad_norm": 0.5231682062149048,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 0.6828,
+      "step": 13144
+    },
+    {
+      "epoch": 0.12221140021334817,
+      "grad_norm": 0.5961389541625977,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 0.6938,
+      "step": 13175
+    },
+    {
+      "epoch": 0.12249895644914428,
+      "grad_norm": 0.587988018989563,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 0.6974,
+      "step": 13206
+    },
+    {
+      "epoch": 0.1227865126849404,
+      "grad_norm": 0.5592740774154663,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 0.6907,
+      "step": 13237
+    },
+    {
+      "epoch": 0.12307406892073651,
+      "grad_norm": 0.5331279635429382,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 0.6899,
+      "step": 13268
+    },
+    {
+      "epoch": 0.12336162515653262,
+      "grad_norm": 0.5590211153030396,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 0.6797,
+      "step": 13299
+    },
+    {
+      "epoch": 0.12364918139232874,
+      "grad_norm": 0.7163476347923279,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 0.7031,
+      "step": 13330
+    },
+    {
+      "epoch": 0.12393673762812485,
+      "grad_norm": 0.5383007526397705,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 0.6984,
+      "step": 13361
+    },
+    {
+      "epoch": 0.12422429386392096,
+      "grad_norm": 0.5943237543106079,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 0.6975,
+      "step": 13392
+    },
+    {
+      "epoch": 0.12451185009971708,
+      "grad_norm": 0.5462716817855835,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 0.6907,
+      "step": 13423
+    },
+    {
+      "epoch": 0.12479940633551319,
+      "grad_norm": 0.5856647491455078,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 0.6864,
+      "step": 13454
+    },
+    {
+      "epoch": 0.1250869625713093,
+      "grad_norm": 0.616330623626709,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 0.7025,
+      "step": 13485
+    },
+    {
+      "epoch": 0.12537451880710543,
+      "grad_norm": 0.5825441479682922,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 0.6972,
+      "step": 13516
+    },
+    {
+      "epoch": 0.12566207504290153,
+      "grad_norm": 2.123152732849121,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 0.6878,
+      "step": 13547
+    },
+    {
+      "epoch": 0.12594963127869765,
+      "grad_norm": 0.5779552459716797,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 0.6858,
+      "step": 13578
+    },
+    {
+      "epoch": 0.12623718751449375,
+      "grad_norm": 0.5518434047698975,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 0.6773,
+      "step": 13609
+    },
+    {
+      "epoch": 0.12652474375028988,
+      "grad_norm": 0.4813186526298523,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 0.6948,
+      "step": 13640
+    },
+    {
+      "epoch": 0.12681229998608598,
+      "grad_norm": 0.5231770873069763,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 0.6807,
+      "step": 13671
+    },
+    {
+      "epoch": 0.1270998562218821,
+      "grad_norm": 0.6137570142745972,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 0.6888,
+      "step": 13702
+    },
+    {
+      "epoch": 0.1273874124576782,
+      "grad_norm": 0.5769107937812805,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 0.683,
+      "step": 13733
+    },
+    {
+      "epoch": 0.12767496869347433,
+      "grad_norm": 0.5705944299697876,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 0.7081,
+      "step": 13764
+    },
+    {
+      "epoch": 0.12796252492927043,
+      "grad_norm": 0.579873263835907,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 0.6883,
+      "step": 13795
+    },
+    {
+      "epoch": 0.12825008116506656,
+      "grad_norm": 0.6501721739768982,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 0.6886,
+      "step": 13826
+    },
+    {
+      "epoch": 0.12853763740086266,
+      "grad_norm": 0.6716403365135193,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 0.6933,
+      "step": 13857
+    },
+    {
+      "epoch": 0.12882519363665879,
+      "grad_norm": 0.5967142581939697,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 0.6902,
+      "step": 13888
+    },
+    {
+      "epoch": 0.12911274987245488,
+      "grad_norm": 0.6142268180847168,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 0.69,
+      "step": 13919
+    },
+    {
+      "epoch": 0.129400306108251,
+      "grad_norm": 0.5498846769332886,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 0.6873,
+      "step": 13950
+    },
+    {
+      "epoch": 0.1296878623440471,
+      "grad_norm": 0.5367789268493652,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 0.7038,
+      "step": 13981
+    },
+    {
+      "epoch": 0.12997541857984324,
+      "grad_norm": 0.5484664440155029,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 0.6881,
+      "step": 14012
+    },
+    {
+      "epoch": 0.13026297481563934,
+      "grad_norm": 0.5144880414009094,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 0.6932,
+      "step": 14043
+    },
+    {
+      "epoch": 0.13055053105143546,
+      "grad_norm": 0.6005863547325134,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 0.6959,
+      "step": 14074
+    },
+    {
+      "epoch": 0.13083808728723156,
+      "grad_norm": 0.5766619443893433,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 0.6926,
+      "step": 14105
+    },
+    {
+      "epoch": 0.1311256435230277,
+      "grad_norm": 0.6153157949447632,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 0.6882,
+      "step": 14136
+    },
+    {
+      "epoch": 0.1314131997588238,
+      "grad_norm": 0.5288106203079224,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 0.6954,
+      "step": 14167
+    },
+    {
+      "epoch": 0.13170075599461992,
+      "grad_norm": 0.5486290454864502,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 0.6833,
+      "step": 14198
+    },
+    {
+      "epoch": 0.13198831223041602,
+      "grad_norm": 0.6377080678939819,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 0.6807,
+      "step": 14229
+    },
+    {
+      "epoch": 0.13227586846621214,
+      "grad_norm": 0.7021725177764893,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 0.6939,
+      "step": 14260
+    },
+    {
+      "epoch": 0.13256342470200824,
+      "grad_norm": 0.5936801433563232,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 0.6877,
+      "step": 14291
+    },
+    {
+      "epoch": 0.13285098093780437,
+      "grad_norm": 0.5426299571990967,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 0.697,
+      "step": 14322
+    },
+    {
+      "epoch": 0.13313853717360047,
+      "grad_norm": 0.5674059987068176,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 0.6985,
+      "step": 14353
+    },
+    {
+      "epoch": 0.1334260934093966,
+      "grad_norm": 3.5487141609191895,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 0.6906,
+      "step": 14384
+    },
+    {
+      "epoch": 0.13371364964519272,
+      "grad_norm": 0.5367308855056763,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 0.6776,
+      "step": 14415
+    },
+    {
+      "epoch": 0.13400120588098882,
+      "grad_norm": 0.4844568073749542,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 0.703,
+      "step": 14446
+    },
+    {
+      "epoch": 0.13428876211678495,
+      "grad_norm": 0.5673976540565491,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 0.6864,
+      "step": 14477
+    },
+    {
+      "epoch": 0.13457631835258105,
+      "grad_norm": 0.57732754945755,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 0.6847,
+      "step": 14508
+    },
+    {
+      "epoch": 0.13486387458837718,
+      "grad_norm": 0.5443653464317322,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 0.7077,
+      "step": 14539
+    },
+    {
+      "epoch": 0.13515143082417327,
+      "grad_norm": 0.6283824443817139,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 0.6909,
+      "step": 14570
+    },
+    {
+      "epoch": 0.1354389870599694,
+      "grad_norm": 0.5682728886604309,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 0.6801,
+      "step": 14601
+    },
+    {
+      "epoch": 0.1357265432957655,
+      "grad_norm": 0.5784809589385986,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 0.6954,
+      "step": 14632
+    },
+    {
+      "epoch": 0.13601409953156163,
+      "grad_norm": 0.5511460304260254,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 0.6776,
+      "step": 14663
+    },
+    {
+      "epoch": 0.13630165576735773,
+      "grad_norm": 0.5853559970855713,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 0.6743,
+      "step": 14694
+    },
+    {
+      "epoch": 0.13658921200315385,
+      "grad_norm": 0.577244222164154,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 0.683,
+      "step": 14725
+    },
+    {
+      "epoch": 0.13687676823894995,
+      "grad_norm": 0.5763031840324402,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 0.6957,
+      "step": 14756
+    },
+    {
+      "epoch": 0.13716432447474608,
+      "grad_norm": 0.5836259722709656,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 0.6824,
+      "step": 14787
+    },
+    {
+      "epoch": 0.13745188071054218,
+      "grad_norm": 0.5423312187194824,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 0.6882,
+      "step": 14818
+    },
+    {
+      "epoch": 0.1377394369463383,
+      "grad_norm": 0.5841296911239624,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 0.6901,
+      "step": 14849
+    },
+    {
+      "epoch": 0.1380269931821344,
+      "grad_norm": 0.564987301826477,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 0.684,
+      "step": 14880
+    },
+    {
+      "epoch": 0.13831454941793053,
+      "grad_norm": 0.500950813293457,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 0.6755,
+      "step": 14911
+    },
+    {
+      "epoch": 0.13860210565372663,
+      "grad_norm": 0.6033563017845154,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 0.6729,
+      "step": 14942
+    },
+    {
+      "epoch": 0.13888966188952276,
+      "grad_norm": 0.5506045818328857,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 0.7044,
+      "step": 14973
+    },
+    {
+      "epoch": 0.13917721812531886,
+      "grad_norm": 0.5446169376373291,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 0.6964,
+      "step": 15004
+    },
+    {
+      "epoch": 0.13946477436111498,
+      "grad_norm": 0.5484293103218079,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 0.6948,
+      "step": 15035
+    },
+    {
+      "epoch": 0.13975233059691108,
+      "grad_norm": 0.5502480268478394,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 0.6823,
+      "step": 15066
+    },
+    {
+      "epoch": 0.1400398868327072,
+      "grad_norm": 0.6017868518829346,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 0.6786,
+      "step": 15097
+    },
+    {
+      "epoch": 0.1403274430685033,
+      "grad_norm": 0.5150992274284363,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 0.6764,
+      "step": 15128
+    },
+    {
+      "epoch": 0.14061499930429944,
+      "grad_norm": 0.5524524450302124,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 0.6922,
+      "step": 15159
+    },
+    {
+      "epoch": 0.14090255554009554,
+      "grad_norm": 0.7386986017227173,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 0.6814,
+      "step": 15190
+    },
+    {
+      "epoch": 0.14119011177589166,
+      "grad_norm": 0.5595665574073792,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 0.6789,
+      "step": 15221
+    },
+    {
+      "epoch": 0.14147766801168776,
+      "grad_norm": 0.5879199504852295,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 0.6828,
+      "step": 15252
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 7630,
+  "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 sha256:08815548a100e5acdd0a48cf1bebdaf5ac1f995718a6e734dbfe9db26d9d6730
+size 5240

checkpoint-22890/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-22890/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-22890/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad3640ddf86f598d0d430d5cccbc476f4e0c4e746601f9b10f54eb082f50534
+size 4976687216

checkpoint-22890/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faab92c079dee70573da2aa38bf83c1a2a2858fbee7104c30f77e30eb62ed67f
+size 4778622352

checkpoint-22890/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d579560f2723d4a62b22ef6ec0d935dfbc2ddf0f14fc9efeac83bf5b586bf9d6
+size 4932743960

checkpoint-22890/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089cf99962fd351ceb590220ea351f1d18937b35376077982b276416f768317a
+size 4932743992

checkpoint-22890/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b61bee4a8b5e41f744ec0820def58c39c0c333e6787b7e24146468348f082a0
+size 4998852296

checkpoint-22890/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5e5de74221056e3010dfa6601b67281d4732f5244e925341831eb03c418bd2
+size 3662865184

checkpoint-22890/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dca433a0a24d1afcbdcee7a5305cffb3588214e60671deecbdeeaa51028eeee
+size 2179989632

checkpoint-22890/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-22890/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092040ce5c4149a164d78b939a212647e5891017b2a9f77ad5a5a4f8919e09c7
+size 16177880918

checkpoint-22890/rng_state.pth

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

checkpoint-22890/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cceae98d85860224f83926a9c2d0797a9f4411abc8a933e66f23226e9ba794a
+size 1064

checkpoint-22890/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08815548a100e5acdd0a48cf1bebdaf5ac1f995718a6e734dbfe9db26d9d6730
+size 5240

checkpoint-30517/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-30517/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-30517/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce121f99cd7e21f47b68c85375bd66262edfee840cd50fd2ae651c2fcaff7c7
+size 4976687216

checkpoint-30517/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faab92c079dee70573da2aa38bf83c1a2a2858fbee7104c30f77e30eb62ed67f
+size 4778622352

checkpoint-30517/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d579560f2723d4a62b22ef6ec0d935dfbc2ddf0f14fc9efeac83bf5b586bf9d6
+size 4932743960

checkpoint-30517/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089cf99962fd351ceb590220ea351f1d18937b35376077982b276416f768317a
+size 4932743992

checkpoint-30517/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b61bee4a8b5e41f744ec0820def58c39c0c333e6787b7e24146468348f082a0
+size 4998852296

checkpoint-30517/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b983728a831e5e8fc7246dde01627d51ae73f16407337db6be871437cb8dc148
+size 3662865184

checkpoint-30517/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a135a24e1330761b05537c3889b237d0147ffdfd7144156e78e5436654b260a7
+size 2179989632

checkpoint-30517/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-30517/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aae99f6ec740e78f6ab2cf37c4236ea5458bc876e74ada40913c4540e4ceacb
+size 16177880918

checkpoint-30517/rng_state.pth

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

checkpoint-30517/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d91c597306f26392e8da0d33a09fdcca77cfdeb5ad42248045521772fa3d64e
+size 1064

checkpoint-30517/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08815548a100e5acdd0a48cf1bebdaf5ac1f995718a6e734dbfe9db26d9d6730
+size 5240

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.44.0.dev0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce121f99cd7e21f47b68c85375bd66262edfee840cd50fd2ae651c2fcaff7c7
+size 4976687216