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 sha256:49a72cac8be78ad0d4b18f46d118a0bee47d6d506f408b02b32876b0b2bb4016
+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 sha256:1b4040a7935c0a9f143b1c09509898be7e21c0a0ed8751f625a742e3ba92303c
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5044abfc8a570b655ede73835fbc3a49892c773f0cfbb5bc3b95168a9a68fb
+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 sha256:562e9c723fb5eef491c13a75cd8b419cf4c933a006987c21e90d0463f9af4b61
+size 16177880918

checkpoint-15260/rng_state.pth

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

checkpoint-15260/scheduler.pt

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

checkpoint-15260/trainer_state.json

@@ -0,0 +1,3477 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.40068268347118285,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008139687541026651,
+      "grad_norm": 3.665264844894409,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 2.1812,
+      "step": 31
+    },
+    {
+      "epoch": 0.0016279375082053301,
+      "grad_norm": 2.4676246643066406,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 2.0535,
+      "step": 62
+    },
+    {
+      "epoch": 0.0024419062623079954,
+      "grad_norm": 2.878305196762085,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.9458,
+      "step": 93
+    },
+    {
+      "epoch": 0.0032558750164106602,
+      "grad_norm": 2.694674015045166,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.8719,
+      "step": 124
+    },
+    {
+      "epoch": 0.004069843770513325,
+      "grad_norm": 2.7240898609161377,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.8334,
+      "step": 155
+    },
+    {
+      "epoch": 0.004883812524615991,
+      "grad_norm": 3.3849148750305176,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.7827,
+      "step": 186
+    },
+    {
+      "epoch": 0.005697781278718656,
+      "grad_norm": 3.106435537338257,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.7446,
+      "step": 217
+    },
+    {
+      "epoch": 0.0065117500328213205,
+      "grad_norm": 4.933763027191162,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.7271,
+      "step": 248
+    },
+    {
+      "epoch": 0.007325718786923986,
+      "grad_norm": 3.060612678527832,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.6866,
+      "step": 279
+    },
+    {
+      "epoch": 0.00813968754102665,
+      "grad_norm": 3.417919158935547,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.6634,
+      "step": 310
+    },
+    {
+      "epoch": 0.008953656295129316,
+      "grad_norm": 4.560545444488525,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.6522,
+      "step": 341
+    },
+    {
+      "epoch": 0.009767625049231982,
+      "grad_norm": 2.6599414348602295,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.6286,
+      "step": 372
+    },
+    {
+      "epoch": 0.010581593803334646,
+      "grad_norm": 3.5111501216888428,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.6086,
+      "step": 403
+    },
+    {
+      "epoch": 0.011395562557437311,
+      "grad_norm": 3.8709545135498047,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 1.6005,
+      "step": 434
+    },
+    {
+      "epoch": 0.012209531311539977,
+      "grad_norm": 2.655081272125244,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 1.5753,
+      "step": 465
+    },
+    {
+      "epoch": 0.013023500065642641,
+      "grad_norm": 4.050207614898682,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 1.5758,
+      "step": 496
+    },
+    {
+      "epoch": 0.013837468819745307,
+      "grad_norm": 2.916259527206421,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 1.5491,
+      "step": 527
+    },
+    {
+      "epoch": 0.014651437573847972,
+      "grad_norm": 4.070659160614014,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 1.5347,
+      "step": 558
+    },
+    {
+      "epoch": 0.015465406327950636,
+      "grad_norm": 3.4878790378570557,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 1.5151,
+      "step": 589
+    },
+    {
+      "epoch": 0.0162793750820533,
+      "grad_norm": 2.949390172958374,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 1.5107,
+      "step": 620
+    },
+    {
+      "epoch": 0.017093343836155968,
+      "grad_norm": 3.1922178268432617,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 1.5001,
+      "step": 651
+    },
+    {
+      "epoch": 0.017907312590258632,
+      "grad_norm": 3.8529181480407715,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 1.4884,
+      "step": 682
+    },
+    {
+      "epoch": 0.018721281344361296,
+      "grad_norm": 3.2902474403381348,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 1.482,
+      "step": 713
+    },
+    {
+      "epoch": 0.019535250098463963,
+      "grad_norm": 2.9867563247680664,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 1.4658,
+      "step": 744
+    },
+    {
+      "epoch": 0.020349218852566627,
+      "grad_norm": 3.0621280670166016,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 1.4581,
+      "step": 775
+    },
+    {
+      "epoch": 0.02116318760666929,
+      "grad_norm": 3.839115619659424,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 1.4552,
+      "step": 806
+    },
+    {
+      "epoch": 0.02197715636077196,
+      "grad_norm": 2.9147427082061768,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 1.4368,
+      "step": 837
+    },
+    {
+      "epoch": 0.022791125114874623,
+      "grad_norm": 3.521418333053589,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 1.4435,
+      "step": 868
+    },
+    {
+      "epoch": 0.023605093868977287,
+      "grad_norm": 2.9942727088928223,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 1.4255,
+      "step": 899
+    },
+    {
+      "epoch": 0.024419062623079954,
+      "grad_norm": 5.096376419067383,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 1.4206,
+      "step": 930
+    },
+    {
+      "epoch": 0.025233031377182618,
+      "grad_norm": 2.957164764404297,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 1.4177,
+      "step": 961
+    },
+    {
+      "epoch": 0.026047000131285282,
+      "grad_norm": 2.8639140129089355,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 1.4082,
+      "step": 992
+    },
+    {
+      "epoch": 0.02686096888538795,
+      "grad_norm": 5.731191635131836,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 1.4017,
+      "step": 1023
+    },
+    {
+      "epoch": 0.027674937639490613,
+      "grad_norm": 2.957393169403076,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 1.4075,
+      "step": 1054
+    },
+    {
+      "epoch": 0.028488906393593277,
+      "grad_norm": 2.716973304748535,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 1.392,
+      "step": 1085
+    },
+    {
+      "epoch": 0.029302875147695945,
+      "grad_norm": 2.8386828899383545,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 1.3803,
+      "step": 1116
+    },
+    {
+      "epoch": 0.03011684390179861,
+      "grad_norm": 3.3751955032348633,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 1.3613,
+      "step": 1147
+    },
+    {
+      "epoch": 0.030930812655901273,
+      "grad_norm": 2.9111735820770264,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 1.3638,
+      "step": 1178
+    },
+    {
+      "epoch": 0.03174478141000394,
+      "grad_norm": 2.3721137046813965,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 1.3706,
+      "step": 1209
+    },
+    {
+      "epoch": 0.0325587501641066,
+      "grad_norm": 3.0478310585021973,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 1.3646,
+      "step": 1240
+    },
+    {
+      "epoch": 0.03337271891820927,
+      "grad_norm": 2.796151638031006,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 1.3521,
+      "step": 1271
+    },
+    {
+      "epoch": 0.034186687672311936,
+      "grad_norm": 3.2832095623016357,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 1.3445,
+      "step": 1302
+    },
+    {
+      "epoch": 0.035000656426414596,
+      "grad_norm": 2.7193307876586914,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 1.341,
+      "step": 1333
+    },
+    {
+      "epoch": 0.035814625180517264,
+      "grad_norm": 2.3204262256622314,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 1.3392,
+      "step": 1364
+    },
+    {
+      "epoch": 0.03662859393461993,
+      "grad_norm": 3.0932254791259766,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 1.3473,
+      "step": 1395
+    },
+    {
+      "epoch": 0.03744256268872259,
+      "grad_norm": 2.749105930328369,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 1.3355,
+      "step": 1426
+    },
+    {
+      "epoch": 0.03825653144282526,
+      "grad_norm": 3.433612108230591,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 1.3358,
+      "step": 1457
+    },
+    {
+      "epoch": 0.039070500196927926,
+      "grad_norm": 2.8213951587677,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 1.3274,
+      "step": 1488
+    },
+    {
+      "epoch": 0.03988446895103059,
+      "grad_norm": 55.82658004760742,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.3909,
+      "step": 1519
+    },
+    {
+      "epoch": 0.040698437705133254,
+      "grad_norm": 11.446126937866211,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 1.8256,
+      "step": 1550
+    },
+    {
+      "epoch": 0.04151240645923592,
+      "grad_norm": 2.9234585762023926,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 1.5262,
+      "step": 1581
+    },
+    {
+      "epoch": 0.04232637521333858,
+      "grad_norm": 2.534860372543335,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 1.4296,
+      "step": 1612
+    },
+    {
+      "epoch": 0.04314034396744125,
+      "grad_norm": 3.393228054046631,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 1.367,
+      "step": 1643
+    },
+    {
+      "epoch": 0.04395431272154392,
+      "grad_norm": 5.319057464599609,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 1.4302,
+      "step": 1674
+    },
+    {
+      "epoch": 0.04476828147564658,
+      "grad_norm": 2.2556281089782715,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 1.3762,
+      "step": 1705
+    },
+    {
+      "epoch": 0.045582250229749245,
+      "grad_norm": 11.374442100524902,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 1.4159,
+      "step": 1736
+    },
+    {
+      "epoch": 0.04639621898385191,
+      "grad_norm": 2.643413782119751,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 1.4324,
+      "step": 1767
+    },
+    {
+      "epoch": 0.04721018773795457,
+      "grad_norm": 4.3118109703063965,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 1.399,
+      "step": 1798
+    },
+    {
+      "epoch": 0.04802415649205724,
+      "grad_norm": 2.8440845012664795,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 1.3763,
+      "step": 1829
+    },
+    {
+      "epoch": 0.04883812524615991,
+      "grad_norm": 3.8986079692840576,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 1.3756,
+      "step": 1860
+    },
+    {
+      "epoch": 0.04965209400026257,
+      "grad_norm": 3.168850898742676,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 1.3393,
+      "step": 1891
+    },
+    {
+      "epoch": 0.050466062754365236,
+      "grad_norm": 2.3892204761505127,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 1.3304,
+      "step": 1922
+    },
+    {
+      "epoch": 0.0512800315084679,
+      "grad_norm": 2.0968079566955566,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 1.3187,
+      "step": 1953
+    },
+    {
+      "epoch": 0.052094000262570564,
+      "grad_norm": 7.010090351104736,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 1.3172,
+      "step": 1984
+    },
+    {
+      "epoch": 0.05290796901667323,
+      "grad_norm": 2.074108362197876,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 1.2991,
+      "step": 2015
+    },
+    {
+      "epoch": 0.0537219377707759,
+      "grad_norm": 2.41266131401062,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 1.2839,
+      "step": 2046
+    },
+    {
+      "epoch": 0.05453590652487856,
+      "grad_norm": 2.0564286708831787,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 1.2844,
+      "step": 2077
+    },
+    {
+      "epoch": 0.05534987527898123,
+      "grad_norm": 2.0147621631622314,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 1.2869,
+      "step": 2108
+    },
+    {
+      "epoch": 0.056163844033083894,
+      "grad_norm": 2.451154947280884,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 1.2789,
+      "step": 2139
+    },
+    {
+      "epoch": 0.056977812787186555,
+      "grad_norm": 2.770345449447632,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 1.2736,
+      "step": 2170
+    },
+    {
+      "epoch": 0.05779178154128922,
+      "grad_norm": 2.041412830352783,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.2717,
+      "step": 2201
+    },
+    {
+      "epoch": 0.05860575029539189,
+      "grad_norm": 2.171128511428833,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.2516,
+      "step": 2232
+    },
+    {
+      "epoch": 0.05941971904949455,
+      "grad_norm": 2.7466177940368652,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 1.2617,
+      "step": 2263
+    },
+    {
+      "epoch": 0.06023368780359722,
+      "grad_norm": 2.0188562870025635,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 1.261,
+      "step": 2294
+    },
+    {
+      "epoch": 0.061047656557699885,
+      "grad_norm": 2.229243516921997,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 1.2552,
+      "step": 2325
+    },
+    {
+      "epoch": 0.061861625311802546,
+      "grad_norm": 3.7142019271850586,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 1.2647,
+      "step": 2356
+    },
+    {
+      "epoch": 0.06267559406590521,
+      "grad_norm": 1.8443535566329956,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 1.2545,
+      "step": 2387
+    },
+    {
+      "epoch": 0.06348956282000788,
+      "grad_norm": 2.1792187690734863,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 1.2602,
+      "step": 2418
+    },
+    {
+      "epoch": 0.06430353157411055,
+      "grad_norm": 2.427130937576294,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 1.2599,
+      "step": 2449
+    },
+    {
+      "epoch": 0.0651175003282132,
+      "grad_norm": 2.40641450881958,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.2482,
+      "step": 2480
+    },
+    {
+      "epoch": 0.06593146908231587,
+      "grad_norm": 2.4361321926116943,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 1.2477,
+      "step": 2511
+    },
+    {
+      "epoch": 0.06674543783641854,
+      "grad_norm": 3.251391887664795,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 1.249,
+      "step": 2542
+    },
+    {
+      "epoch": 0.0675594065905212,
+      "grad_norm": 2.3272197246551514,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.2456,
+      "step": 2573
+    },
+    {
+      "epoch": 0.06837337534462387,
+      "grad_norm": 1.765633463859558,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.2275,
+      "step": 2604
+    },
+    {
+      "epoch": 0.06918734409872654,
+      "grad_norm": 2.487745761871338,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.2348,
+      "step": 2635
+    },
+    {
+      "epoch": 0.07000131285282919,
+      "grad_norm": 2.476963520050049,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.222,
+      "step": 2666
+    },
+    {
+      "epoch": 0.07081528160693186,
+      "grad_norm": 2.867267370223999,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.2393,
+      "step": 2697
+    },
+    {
+      "epoch": 0.07162925036103453,
+      "grad_norm": 2.260697841644287,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.2454,
+      "step": 2728
+    },
+    {
+      "epoch": 0.0724432191151372,
+      "grad_norm": 2.2477054595947266,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.2461,
+      "step": 2759
+    },
+    {
+      "epoch": 0.07325718786923986,
+      "grad_norm": 4.51762056350708,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.2167,
+      "step": 2790
+    },
+    {
+      "epoch": 0.07407115662334253,
+      "grad_norm": 1.9302934408187866,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.2335,
+      "step": 2821
+    },
+    {
+      "epoch": 0.07488512537744518,
+      "grad_norm": 2.1645681858062744,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.238,
+      "step": 2852
+    },
+    {
+      "epoch": 0.07569909413154785,
+      "grad_norm": 2.2581164836883545,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.2147,
+      "step": 2883
+    },
+    {
+      "epoch": 0.07651306288565052,
+      "grad_norm": 1.9437881708145142,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.2344,
+      "step": 2914
+    },
+    {
+      "epoch": 0.07732703163975319,
+      "grad_norm": 1.807570219039917,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.2186,
+      "step": 2945
+    },
+    {
+      "epoch": 0.07814100039385585,
+      "grad_norm": 2.321345567703247,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.2151,
+      "step": 2976
+    },
+    {
+      "epoch": 0.07895496914795852,
+      "grad_norm": 2.279082775115967,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.2187,
+      "step": 3007
+    },
+    {
+      "epoch": 0.07976893790206117,
+      "grad_norm": 1.6429636478424072,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.2104,
+      "step": 3038
+    },
+    {
+      "epoch": 0.08058290665616384,
+      "grad_norm": 1.9841675758361816,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.2183,
+      "step": 3069
+    },
+    {
+      "epoch": 0.08139687541026651,
+      "grad_norm": 2.1972384452819824,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.2156,
+      "step": 3100
+    },
+    {
+      "epoch": 0.08221084416436918,
+      "grad_norm": 1.8140931129455566,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.205,
+      "step": 3131
+    },
+    {
+      "epoch": 0.08302481291847184,
+      "grad_norm": 1.7327383756637573,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.2105,
+      "step": 3162
+    },
+    {
+      "epoch": 0.08383878167257451,
+      "grad_norm": 1.5160003900527954,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.2089,
+      "step": 3193
+    },
+    {
+      "epoch": 0.08465275042667716,
+      "grad_norm": 2.113037109375,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.1991,
+      "step": 3224
+    },
+    {
+      "epoch": 0.08546671918077983,
+      "grad_norm": 1.807724118232727,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.2026,
+      "step": 3255
+    },
+    {
+      "epoch": 0.0862806879348825,
+      "grad_norm": 1.8682724237442017,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.193,
+      "step": 3286
+    },
+    {
+      "epoch": 0.08709465668898517,
+      "grad_norm": 2.3081648349761963,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.2019,
+      "step": 3317
+    },
+    {
+      "epoch": 0.08790862544308783,
+      "grad_norm": 1.8127061128616333,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.1934,
+      "step": 3348
+    },
+    {
+      "epoch": 0.08872259419719049,
+      "grad_norm": 1.8878953456878662,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.1923,
+      "step": 3379
+    },
+    {
+      "epoch": 0.08953656295129316,
+      "grad_norm": 1.6906676292419434,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.1993,
+      "step": 3410
+    },
+    {
+      "epoch": 0.09035053170539582,
+      "grad_norm": 2.181830883026123,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.1911,
+      "step": 3441
+    },
+    {
+      "epoch": 0.09116450045949849,
+      "grad_norm": 2.4296047687530518,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.198,
+      "step": 3472
+    },
+    {
+      "epoch": 0.09197846921360116,
+      "grad_norm": 1.9574142694473267,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.1938,
+      "step": 3503
+    },
+    {
+      "epoch": 0.09279243796770383,
+      "grad_norm": 1.6882851123809814,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.1974,
+      "step": 3534
+    },
+    {
+      "epoch": 0.09360640672180648,
+      "grad_norm": 2.3280014991760254,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.194,
+      "step": 3565
+    },
+    {
+      "epoch": 0.09442037547590915,
+      "grad_norm": 2.2544307708740234,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.1814,
+      "step": 3596
+    },
+    {
+      "epoch": 0.09523434423001181,
+      "grad_norm": 2.25360369682312,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.1737,
+      "step": 3627
+    },
+    {
+      "epoch": 0.09604831298411448,
+      "grad_norm": 1.5724776983261108,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.1766,
+      "step": 3658
+    },
+    {
+      "epoch": 0.09686228173821715,
+      "grad_norm": 1.8221943378448486,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.183,
+      "step": 3689
+    },
+    {
+      "epoch": 0.09767625049231982,
+      "grad_norm": 1.722594141960144,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.1681,
+      "step": 3720
+    },
+    {
+      "epoch": 0.09849021924642247,
+      "grad_norm": 1.5307432413101196,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.1737,
+      "step": 3751
+    },
+    {
+      "epoch": 0.09930418800052514,
+      "grad_norm": 2.0803110599517822,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.1698,
+      "step": 3782
+    },
+    {
+      "epoch": 0.1001181567546278,
+      "grad_norm": 1.7529264688491821,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.1752,
+      "step": 3813
+    },
+    {
+      "epoch": 0.10093212550873047,
+      "grad_norm": 1.4459233283996582,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.154,
+      "step": 3844
+    },
+    {
+      "epoch": 0.10174609426283314,
+      "grad_norm": 1.980885624885559,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.1751,
+      "step": 3875
+    },
+    {
+      "epoch": 0.1025600630169358,
+      "grad_norm": 2.3104734420776367,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.1609,
+      "step": 3906
+    },
+    {
+      "epoch": 0.10337403177103846,
+      "grad_norm": 1.7842062711715698,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.1737,
+      "step": 3937
+    },
+    {
+      "epoch": 0.10418800052514113,
+      "grad_norm": 1.6121835708618164,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.1681,
+      "step": 3968
+    },
+    {
+      "epoch": 0.1050019692792438,
+      "grad_norm": 2.3961281776428223,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.1686,
+      "step": 3999
+    },
+    {
+      "epoch": 0.10581593803334646,
+      "grad_norm": 1.7535598278045654,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.169,
+      "step": 4030
+    },
+    {
+      "epoch": 0.10662990678744913,
+      "grad_norm": 1.7736597061157227,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.1627,
+      "step": 4061
+    },
+    {
+      "epoch": 0.1074438755415518,
+      "grad_norm": 1.7297468185424805,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.152,
+      "step": 4092
+    },
+    {
+      "epoch": 0.10825784429565445,
+      "grad_norm": 2.4818034172058105,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.1757,
+      "step": 4123
+    },
+    {
+      "epoch": 0.10907181304975712,
+      "grad_norm": 1.5024869441986084,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.1645,
+      "step": 4154
+    },
+    {
+      "epoch": 0.10988578180385979,
+      "grad_norm": 2.0316147804260254,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.1607,
+      "step": 4185
+    },
+    {
+      "epoch": 0.11069975055796245,
+      "grad_norm": 2.1756372451782227,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.1504,
+      "step": 4216
+    },
+    {
+      "epoch": 0.11151371931206512,
+      "grad_norm": 1.5000461339950562,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.1768,
+      "step": 4247
+    },
+    {
+      "epoch": 0.11232768806616779,
+      "grad_norm": 2.6072757244110107,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.1499,
+      "step": 4278
+    },
+    {
+      "epoch": 0.11314165682027044,
+      "grad_norm": 1.3471242189407349,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.158,
+      "step": 4309
+    },
+    {
+      "epoch": 0.11395562557437311,
+      "grad_norm": 1.6472967863082886,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.1474,
+      "step": 4340
+    },
+    {
+      "epoch": 0.11476959432847578,
+      "grad_norm": 2.29596209526062,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.1526,
+      "step": 4371
+    },
+    {
+      "epoch": 0.11558356308257844,
+      "grad_norm": 1.2598167657852173,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.1563,
+      "step": 4402
+    },
+    {
+      "epoch": 0.11639753183668111,
+      "grad_norm": 1.800126075744629,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.1527,
+      "step": 4433
+    },
+    {
+      "epoch": 0.11721150059078378,
+      "grad_norm": 1.5320085287094116,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.154,
+      "step": 4464
+    },
+    {
+      "epoch": 0.11802546934488643,
+      "grad_norm": 1.6290438175201416,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.1564,
+      "step": 4495
+    },
+    {
+      "epoch": 0.1188394380989891,
+      "grad_norm": 1.6375097036361694,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.1641,
+      "step": 4526
+    },
+    {
+      "epoch": 0.11965340685309177,
+      "grad_norm": 1.5468589067459106,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.1419,
+      "step": 4557
+    },
+    {
+      "epoch": 0.12046737560719444,
+      "grad_norm": 1.6913152933120728,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.1506,
+      "step": 4588
+    },
+    {
+      "epoch": 0.1212813443612971,
+      "grad_norm": 1.8452041149139404,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.1469,
+      "step": 4619
+    },
+    {
+      "epoch": 0.12209531311539977,
+      "grad_norm": 1.7008527517318726,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.1458,
+      "step": 4650
+    },
+    {
+      "epoch": 0.12290928186950242,
+      "grad_norm": 1.6071614027023315,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.155,
+      "step": 4681
+    },
+    {
+      "epoch": 0.12372325062360509,
+      "grad_norm": 1.4235854148864746,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.1359,
+      "step": 4712
+    },
+    {
+      "epoch": 0.12453721937770776,
+      "grad_norm": 1.5262200832366943,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.1487,
+      "step": 4743
+    },
+    {
+      "epoch": 0.12535118813181043,
+      "grad_norm": 1.5988918542861938,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.1409,
+      "step": 4774
+    },
+    {
+      "epoch": 0.1261651568859131,
+      "grad_norm": 1.8762277364730835,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.1415,
+      "step": 4805
+    },
+    {
+      "epoch": 0.12697912564001576,
+      "grad_norm": 1.7586325407028198,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.1468,
+      "step": 4836
+    },
+    {
+      "epoch": 0.12779309439411843,
+      "grad_norm": 1.6530872583389282,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.1426,
+      "step": 4867
+    },
+    {
+      "epoch": 0.1286070631482211,
+      "grad_norm": 1.7553999423980713,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.1337,
+      "step": 4898
+    },
+    {
+      "epoch": 0.12942103190232376,
+      "grad_norm": 1.7332961559295654,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.1507,
+      "step": 4929
+    },
+    {
+      "epoch": 0.1302350006564264,
+      "grad_norm": 1.756203532218933,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.1451,
+      "step": 4960
+    },
+    {
+      "epoch": 0.13104896941052907,
+      "grad_norm": 1.4433952569961548,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.1481,
+      "step": 4991
+    },
+    {
+      "epoch": 0.13186293816463174,
+      "grad_norm": 1.4313442707061768,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.1465,
+      "step": 5022
+    },
+    {
+      "epoch": 0.1326769069187344,
+      "grad_norm": 1.5878046751022339,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.1327,
+      "step": 5053
+    },
+    {
+      "epoch": 0.13349087567283707,
+      "grad_norm": 1.4836533069610596,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.1336,
+      "step": 5084
+    },
+    {
+      "epoch": 0.13430484442693974,
+      "grad_norm": 1.5261276960372925,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.141,
+      "step": 5115
+    },
+    {
+      "epoch": 0.1351188131810424,
+      "grad_norm": 1.4848837852478027,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.137,
+      "step": 5146
+    },
+    {
+      "epoch": 0.13593278193514508,
+      "grad_norm": 2.077648401260376,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.1502,
+      "step": 5177
+    },
+    {
+      "epoch": 0.13674675068924774,
+      "grad_norm": 2.374537944793701,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.148,
+      "step": 5208
+    },
+    {
+      "epoch": 0.1375607194433504,
+      "grad_norm": 1.7867786884307861,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.1312,
+      "step": 5239
+    },
+    {
+      "epoch": 0.13837468819745308,
+      "grad_norm": 1.8930435180664062,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.1349,
+      "step": 5270
+    },
+    {
+      "epoch": 0.13918865695155572,
+      "grad_norm": 1.636661410331726,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.122,
+      "step": 5301
+    },
+    {
+      "epoch": 0.14000262570565838,
+      "grad_norm": 2.0743846893310547,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.1411,
+      "step": 5332
+    },
+    {
+      "epoch": 0.14081659445976105,
+      "grad_norm": 1.5637271404266357,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.1269,
+      "step": 5363
+    },
+    {
+      "epoch": 0.14163056321386372,
+      "grad_norm": 1.3702319860458374,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.132,
+      "step": 5394
+    },
+    {
+      "epoch": 0.1424445319679664,
+      "grad_norm": 1.3957338333129883,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.1343,
+      "step": 5425
+    },
+    {
+      "epoch": 0.14325850072206905,
+      "grad_norm": 1.6967320442199707,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.1344,
+      "step": 5456
+    },
+    {
+      "epoch": 0.14407246947617172,
+      "grad_norm": 1.5744746923446655,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.1339,
+      "step": 5487
+    },
+    {
+      "epoch": 0.1448864382302744,
+      "grad_norm": 1.5498865842819214,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.1398,
+      "step": 5518
+    },
+    {
+      "epoch": 0.14570040698437706,
+      "grad_norm": 1.3732212781906128,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.1273,
+      "step": 5549
+    },
+    {
+      "epoch": 0.14651437573847972,
+      "grad_norm": 1.3601373434066772,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.116,
+      "step": 5580
+    },
+    {
+      "epoch": 0.1473283444925824,
+      "grad_norm": 1.3350623846054077,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.1228,
+      "step": 5611
+    },
+    {
+      "epoch": 0.14814231324668506,
+      "grad_norm": 1.319671392440796,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.1156,
+      "step": 5642
+    },
+    {
+      "epoch": 0.1489562820007877,
+      "grad_norm": 1.8750630617141724,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.1269,
+      "step": 5673
+    },
+    {
+      "epoch": 0.14977025075489037,
+      "grad_norm": 2.0026299953460693,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.1278,
+      "step": 5704
+    },
+    {
+      "epoch": 0.15058421950899303,
+      "grad_norm": 1.418369174003601,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.1104,
+      "step": 5735
+    },
+    {
+      "epoch": 0.1513981882630957,
+      "grad_norm": 1.5593863725662231,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.1229,
+      "step": 5766
+    },
+    {
+      "epoch": 0.15221215701719837,
+      "grad_norm": 1.6161731481552124,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.1314,
+      "step": 5797
+    },
+    {
+      "epoch": 0.15302612577130104,
+      "grad_norm": 1.509048342704773,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.1192,
+      "step": 5828
+    },
+    {
+      "epoch": 0.1538400945254037,
+      "grad_norm": 1.9641119241714478,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.1221,
+      "step": 5859
+    },
+    {
+      "epoch": 0.15465406327950637,
+      "grad_norm": 1.7621874809265137,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.1223,
+      "step": 5890
+    },
+    {
+      "epoch": 0.15546803203360904,
+      "grad_norm": 2.2426326274871826,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.1266,
+      "step": 5921
+    },
+    {
+      "epoch": 0.1562820007877117,
+      "grad_norm": 1.9674558639526367,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.1243,
+      "step": 5952
+    },
+    {
+      "epoch": 0.15709596954181437,
+      "grad_norm": 1.4433611631393433,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.129,
+      "step": 5983
+    },
+    {
+      "epoch": 0.15790993829591704,
+      "grad_norm": 1.7753652334213257,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.12,
+      "step": 6014
+    },
+    {
+      "epoch": 0.15872390705001968,
+      "grad_norm": 1.9805961847305298,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.1068,
+      "step": 6045
+    },
+    {
+      "epoch": 0.15953787580412235,
+      "grad_norm": 1.1892720460891724,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.1216,
+      "step": 6076
+    },
+    {
+      "epoch": 0.16035184455822502,
+      "grad_norm": 1.7206059694290161,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.1148,
+      "step": 6107
+    },
+    {
+      "epoch": 0.16116581331232768,
+      "grad_norm": 1.7299422025680542,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.0974,
+      "step": 6138
+    },
+    {
+      "epoch": 0.16197978206643035,
+      "grad_norm": 1.5966317653656006,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.106,
+      "step": 6169
+    },
+    {
+      "epoch": 0.16279375082053302,
+      "grad_norm": 1.6218801736831665,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.1103,
+      "step": 6200
+    },
+    {
+      "epoch": 0.16360771957463568,
+      "grad_norm": 1.208667278289795,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.0979,
+      "step": 6231
+    },
+    {
+      "epoch": 0.16442168832873835,
+      "grad_norm": 1.98179030418396,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.1163,
+      "step": 6262
+    },
+    {
+      "epoch": 0.16523565708284102,
+      "grad_norm": 2.215501070022583,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.1213,
+      "step": 6293
+    },
+    {
+      "epoch": 0.1660496258369437,
+      "grad_norm": 1.575427770614624,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.1133,
+      "step": 6324
+    },
+    {
+      "epoch": 0.16686359459104635,
+      "grad_norm": 1.6315374374389648,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.1064,
+      "step": 6355
+    },
+    {
+      "epoch": 0.16767756334514902,
+      "grad_norm": 1.4703013896942139,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.121,
+      "step": 6386
+    },
+    {
+      "epoch": 0.16849153209925166,
+      "grad_norm": 1.553431749343872,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.1099,
+      "step": 6417
+    },
+    {
+      "epoch": 0.16930550085335433,
+      "grad_norm": 1.4701799154281616,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.1002,
+      "step": 6448
+    },
+    {
+      "epoch": 0.170119469607457,
+      "grad_norm": 1.7020679712295532,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.1033,
+      "step": 6479
+    },
+    {
+      "epoch": 0.17093343836155966,
+      "grad_norm": 1.8985180854797363,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.0935,
+      "step": 6510
+    },
+    {
+      "epoch": 0.17174740711566233,
+      "grad_norm": 1.4587364196777344,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.1169,
+      "step": 6541
+    },
+    {
+      "epoch": 0.172561375869765,
+      "grad_norm": 1.525999903678894,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.1205,
+      "step": 6572
+    },
+    {
+      "epoch": 0.17337534462386767,
+      "grad_norm": 1.961179494857788,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.1053,
+      "step": 6603
+    },
+    {
+      "epoch": 0.17418931337797033,
+      "grad_norm": 1.9014114141464233,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.1067,
+      "step": 6634
+    },
+    {
+      "epoch": 0.175003282132073,
+      "grad_norm": 1.3822484016418457,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.1145,
+      "step": 6665
+    },
+    {
+      "epoch": 0.17581725088617567,
+      "grad_norm": 1.573196530342102,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.0908,
+      "step": 6696
+    },
+    {
+      "epoch": 0.17663121964027834,
+      "grad_norm": 1.0946050882339478,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.1068,
+      "step": 6727
+    },
+    {
+      "epoch": 0.17744518839438098,
+      "grad_norm": 1.260721206665039,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.1089,
+      "step": 6758
+    },
+    {
+      "epoch": 0.17825915714848364,
+      "grad_norm": 1.9283548593521118,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.1133,
+      "step": 6789
+    },
+    {
+      "epoch": 0.1790731259025863,
+      "grad_norm": 1.4549671411514282,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.1,
+      "step": 6820
+    },
+    {
+      "epoch": 0.17988709465668898,
+      "grad_norm": 2.1779208183288574,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.1033,
+      "step": 6851
+    },
+    {
+      "epoch": 0.18070106341079165,
+      "grad_norm": 3.1343655586242676,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.104,
+      "step": 6882
+    },
+    {
+      "epoch": 0.1815150321648943,
+      "grad_norm": 1.5330688953399658,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.1068,
+      "step": 6913
+    },
+    {
+      "epoch": 0.18232900091899698,
+      "grad_norm": 1.4057691097259521,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.0965,
+      "step": 6944
+    },
+    {
+      "epoch": 0.18314296967309965,
+      "grad_norm": 1.360346794128418,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.0899,
+      "step": 6975
+    },
+    {
+      "epoch": 0.18395693842720232,
+      "grad_norm": 1.762463092803955,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.0973,
+      "step": 7006
+    },
+    {
+      "epoch": 0.18477090718130498,
+      "grad_norm": 1.6311441659927368,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.0991,
+      "step": 7037
+    },
+    {
+      "epoch": 0.18558487593540765,
+      "grad_norm": 2.032707929611206,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.1026,
+      "step": 7068
+    },
+    {
+      "epoch": 0.18639884468951032,
+      "grad_norm": 1.519220232963562,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.0988,
+      "step": 7099
+    },
+    {
+      "epoch": 0.18721281344361296,
+      "grad_norm": 1.2609440088272095,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.103,
+      "step": 7130
+    },
+    {
+      "epoch": 0.18802678219771563,
+      "grad_norm": 1.3468326330184937,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.0937,
+      "step": 7161
+    },
+    {
+      "epoch": 0.1888407509518183,
+      "grad_norm": 1.8098242282867432,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.0952,
+      "step": 7192
+    },
+    {
+      "epoch": 0.18965471970592096,
+      "grad_norm": 1.881813883781433,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.1013,
+      "step": 7223
+    },
+    {
+      "epoch": 0.19046868846002363,
+      "grad_norm": 1.517236351966858,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.1013,
+      "step": 7254
+    },
+    {
+      "epoch": 0.1912826572141263,
+      "grad_norm": 1.1923933029174805,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.0925,
+      "step": 7285
+    },
+    {
+      "epoch": 0.19209662596822896,
+      "grad_norm": 1.4103548526763916,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.0967,
+      "step": 7316
+    },
+    {
+      "epoch": 0.19291059472233163,
+      "grad_norm": 1.344855546951294,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.0959,
+      "step": 7347
+    },
+    {
+      "epoch": 0.1937245634764343,
+      "grad_norm": 1.6658297777175903,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.1007,
+      "step": 7378
+    },
+    {
+      "epoch": 0.19453853223053696,
+      "grad_norm": 1.3121784925460815,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.1026,
+      "step": 7409
+    },
+    {
+      "epoch": 0.19535250098463963,
+      "grad_norm": 1.4923721551895142,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.1003,
+      "step": 7440
+    },
+    {
+      "epoch": 0.1961664697387423,
+      "grad_norm": 1.6884660720825195,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.0965,
+      "step": 7471
+    },
+    {
+      "epoch": 0.19698043849284494,
+      "grad_norm": 1.6829025745391846,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.0976,
+      "step": 7502
+    },
+    {
+      "epoch": 0.1977944072469476,
+      "grad_norm": 1.8072466850280762,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.086,
+      "step": 7533
+    },
+    {
+      "epoch": 0.19860837600105027,
+      "grad_norm": 1.9585840702056885,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.091,
+      "step": 7564
+    },
+    {
+      "epoch": 0.19942234475515294,
+      "grad_norm": 1.1095181703567505,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.1001,
+      "step": 7595
+    },
+    {
+      "epoch": 0.2002363135092556,
+      "grad_norm": 1.4648469686508179,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.1025,
+      "step": 7626
+    },
+    {
+      "epoch": 0.20105028226335828,
+      "grad_norm": 1.5900369882583618,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.0972,
+      "step": 7657
+    },
+    {
+      "epoch": 0.20186425101746094,
+      "grad_norm": 1.6693593263626099,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.0974,
+      "step": 7688
+    },
+    {
+      "epoch": 0.2026782197715636,
+      "grad_norm": 1.8450345993041992,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.0855,
+      "step": 7719
+    },
+    {
+      "epoch": 0.20349218852566628,
+      "grad_norm": 1.5518052577972412,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.099,
+      "step": 7750
+    },
+    {
+      "epoch": 0.20430615727976895,
+      "grad_norm": 1.4895716905593872,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.088,
+      "step": 7781
+    },
+    {
+      "epoch": 0.2051201260338716,
+      "grad_norm": 1.6725503206253052,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.0804,
+      "step": 7812
+    },
+    {
+      "epoch": 0.20593409478797428,
+      "grad_norm": 1.7620623111724854,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.0866,
+      "step": 7843
+    },
+    {
+      "epoch": 0.20674806354207692,
+      "grad_norm": 1.954484224319458,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.0917,
+      "step": 7874
+    },
+    {
+      "epoch": 0.2075620322961796,
+      "grad_norm": 1.295616626739502,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.091,
+      "step": 7905
+    },
+    {
+      "epoch": 0.20837600105028226,
+      "grad_norm": 1.3337727785110474,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.1014,
+      "step": 7936
+    },
+    {
+      "epoch": 0.20918996980438492,
+      "grad_norm": 1.6083234548568726,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.0802,
+      "step": 7967
+    },
+    {
+      "epoch": 0.2100039385584876,
+      "grad_norm": 1.483178973197937,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.0756,
+      "step": 7998
+    },
+    {
+      "epoch": 0.21081790731259026,
+      "grad_norm": 4.383185863494873,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.0841,
+      "step": 8029
+    },
+    {
+      "epoch": 0.21163187606669293,
+      "grad_norm": 1.6037579774856567,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.0835,
+      "step": 8060
+    },
+    {
+      "epoch": 0.2124458448207956,
+      "grad_norm": 1.8999346494674683,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.095,
+      "step": 8091
+    },
+    {
+      "epoch": 0.21325981357489826,
+      "grad_norm": 1.852630376815796,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.0767,
+      "step": 8122
+    },
+    {
+      "epoch": 0.21407378232900093,
+      "grad_norm": 1.5361006259918213,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.0888,
+      "step": 8153
+    },
+    {
+      "epoch": 0.2148877510831036,
+      "grad_norm": 2.0351686477661133,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.0747,
+      "step": 8184
+    },
+    {
+      "epoch": 0.21570171983720626,
+      "grad_norm": 1.3601598739624023,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.0983,
+      "step": 8215
+    },
+    {
+      "epoch": 0.2165156885913089,
+      "grad_norm": 1.7752212285995483,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.0896,
+      "step": 8246
+    },
+    {
+      "epoch": 0.21732965734541157,
+      "grad_norm": 1.6295273303985596,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.0944,
+      "step": 8277
+    },
+    {
+      "epoch": 0.21814362609951424,
+      "grad_norm": 1.82109797000885,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.0843,
+      "step": 8308
+    },
+    {
+      "epoch": 0.2189575948536169,
+      "grad_norm": 1.879706621170044,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.0776,
+      "step": 8339
+    },
+    {
+      "epoch": 0.21977156360771957,
+      "grad_norm": 1.4658154249191284,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.0838,
+      "step": 8370
+    },
+    {
+      "epoch": 0.22058553236182224,
+      "grad_norm": 1.4365441799163818,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.0819,
+      "step": 8401
+    },
+    {
+      "epoch": 0.2213995011159249,
+      "grad_norm": 1.6058299541473389,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.0642,
+      "step": 8432
+    },
+    {
+      "epoch": 0.22221346987002757,
+      "grad_norm": 1.1539628505706787,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.0857,
+      "step": 8463
+    },
+    {
+      "epoch": 0.22302743862413024,
+      "grad_norm": 1.3252378702163696,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.09,
+      "step": 8494
+    },
+    {
+      "epoch": 0.2238414073782329,
+      "grad_norm": 1.3166979551315308,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.0935,
+      "step": 8525
+    },
+    {
+      "epoch": 0.22465537613233558,
+      "grad_norm": 1.9119739532470703,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.0861,
+      "step": 8556
+    },
+    {
+      "epoch": 0.22546934488643822,
+      "grad_norm": 1.606436014175415,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.0869,
+      "step": 8587
+    },
+    {
+      "epoch": 0.22628331364054088,
+      "grad_norm": 1.651023268699646,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.0771,
+      "step": 8618
+    },
+    {
+      "epoch": 0.22709728239464355,
+      "grad_norm": 1.8768386840820312,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.0722,
+      "step": 8649
+    },
+    {
+      "epoch": 0.22791125114874622,
+      "grad_norm": 1.5180752277374268,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.0792,
+      "step": 8680
+    },
+    {
+      "epoch": 0.2287252199028489,
+      "grad_norm": 1.5237736701965332,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.0825,
+      "step": 8711
+    },
+    {
+      "epoch": 0.22953918865695155,
+      "grad_norm": 1.2274247407913208,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.0755,
+      "step": 8742
+    },
+    {
+      "epoch": 0.23035315741105422,
+      "grad_norm": 1.512094259262085,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.0929,
+      "step": 8773
+    },
+    {
+      "epoch": 0.2311671261651569,
+      "grad_norm": 1.6443533897399902,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.0723,
+      "step": 8804
+    },
+    {
+      "epoch": 0.23198109491925956,
+      "grad_norm": 1.2440882921218872,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.0725,
+      "step": 8835
+    },
+    {
+      "epoch": 0.23279506367336222,
+      "grad_norm": 1.1516292095184326,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.0782,
+      "step": 8866
+    },
+    {
+      "epoch": 0.2336090324274649,
+      "grad_norm": 1.4926685094833374,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.0698,
+      "step": 8897
+    },
+    {
+      "epoch": 0.23442300118156756,
+      "grad_norm": 1.4249902963638306,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.0799,
+      "step": 8928
+    },
+    {
+      "epoch": 0.2352369699356702,
+      "grad_norm": 1.3714172840118408,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.0678,
+      "step": 8959
+    },
+    {
+      "epoch": 0.23605093868977287,
+      "grad_norm": 1.3237582445144653,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.0595,
+      "step": 8990
+    },
+    {
+      "epoch": 0.23686490744387553,
+      "grad_norm": 1.2463147640228271,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.087,
+      "step": 9021
+    },
+    {
+      "epoch": 0.2376788761979782,
+      "grad_norm": 1.2657625675201416,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.0715,
+      "step": 9052
+    },
+    {
+      "epoch": 0.23849284495208087,
+      "grad_norm": 1.2939493656158447,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.0673,
+      "step": 9083
+    },
+    {
+      "epoch": 0.23930681370618354,
+      "grad_norm": 1.121070146560669,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.0828,
+      "step": 9114
+    },
+    {
+      "epoch": 0.2401207824602862,
+      "grad_norm": 1.490594506263733,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.065,
+      "step": 9145
+    },
+    {
+      "epoch": 0.24093475121438887,
+      "grad_norm": 1.6066402196884155,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.0752,
+      "step": 9176
+    },
+    {
+      "epoch": 0.24174871996849154,
+      "grad_norm": 1.6252498626708984,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.0607,
+      "step": 9207
+    },
+    {
+      "epoch": 0.2425626887225942,
+      "grad_norm": 1.2539441585540771,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.0752,
+      "step": 9238
+    },
+    {
+      "epoch": 0.24337665747669687,
+      "grad_norm": 1.35456120967865,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.0788,
+      "step": 9269
+    },
+    {
+      "epoch": 0.24419062623079954,
+      "grad_norm": 1.6083767414093018,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.0695,
+      "step": 9300
+    },
+    {
+      "epoch": 0.24500459498490218,
+      "grad_norm": 1.2094999551773071,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.0664,
+      "step": 9331
+    },
+    {
+      "epoch": 0.24581856373900485,
+      "grad_norm": 1.3909991979599,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.0692,
+      "step": 9362
+    },
+    {
+      "epoch": 0.24663253249310751,
+      "grad_norm": 1.311097264289856,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.0742,
+      "step": 9393
+    },
+    {
+      "epoch": 0.24744650124721018,
+      "grad_norm": 1.1820203065872192,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.0619,
+      "step": 9424
+    },
+    {
+      "epoch": 0.24826047000131285,
+      "grad_norm": 1.2960182428359985,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.0796,
+      "step": 9455
+    },
+    {
+      "epoch": 0.24907443875541552,
+      "grad_norm": 1.4245221614837646,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.0675,
+      "step": 9486
+    },
+    {
+      "epoch": 0.24988840750951818,
+      "grad_norm": 1.1937918663024902,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.0694,
+      "step": 9517
+    },
+    {
+      "epoch": 0.25070237626362085,
+      "grad_norm": 1.3787723779678345,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.0687,
+      "step": 9548
+    },
+    {
+      "epoch": 0.2515163450177235,
+      "grad_norm": 1.3951730728149414,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.0702,
+      "step": 9579
+    },
+    {
+      "epoch": 0.2523303137718262,
+      "grad_norm": 1.42860746383667,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.072,
+      "step": 9610
+    },
+    {
+      "epoch": 0.25314428252592885,
+      "grad_norm": 0.981826901435852,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.0599,
+      "step": 9641
+    },
+    {
+      "epoch": 0.2539582512800315,
+      "grad_norm": 1.6953272819519043,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.0586,
+      "step": 9672
+    },
+    {
+      "epoch": 0.2547722200341342,
+      "grad_norm": 1.3150633573532104,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.0697,
+      "step": 9703
+    },
+    {
+      "epoch": 0.25558618878823686,
+      "grad_norm": 1.3116921186447144,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.0611,
+      "step": 9734
+    },
+    {
+      "epoch": 0.2564001575423395,
+      "grad_norm": 1.2162045240402222,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.0797,
+      "step": 9765
+    },
+    {
+      "epoch": 0.2572141262964422,
+      "grad_norm": 1.1685280799865723,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.0766,
+      "step": 9796
+    },
+    {
+      "epoch": 0.25802809505054486,
+      "grad_norm": 1.170324683189392,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.0643,
+      "step": 9827
+    },
+    {
+      "epoch": 0.2588420638046475,
+      "grad_norm": 1.8417725563049316,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.0745,
+      "step": 9858
+    },
+    {
+      "epoch": 0.25965603255875014,
+      "grad_norm": 1.4726077318191528,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.0758,
+      "step": 9889
+    },
+    {
+      "epoch": 0.2604700013128528,
+      "grad_norm": 1.2865711450576782,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.0759,
+      "step": 9920
+    },
+    {
+      "epoch": 0.2612839700669555,
+      "grad_norm": 1.6937872171401978,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.0679,
+      "step": 9951
+    },
+    {
+      "epoch": 0.26209793882105814,
+      "grad_norm": 1.95823335647583,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.0532,
+      "step": 9982
+    },
+    {
+      "epoch": 0.2629119075751608,
+      "grad_norm": 1.7639048099517822,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.0575,
+      "step": 10013
+    },
+    {
+      "epoch": 0.2637258763292635,
+      "grad_norm": 1.4266012907028198,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.0599,
+      "step": 10044
+    },
+    {
+      "epoch": 0.26453984508336614,
+      "grad_norm": 1.554216980934143,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.0612,
+      "step": 10075
+    },
+    {
+      "epoch": 0.2653538138374688,
+      "grad_norm": 1.4160051345825195,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.0614,
+      "step": 10106
+    },
+    {
+      "epoch": 0.2661677825915715,
+      "grad_norm": 1.1997915506362915,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.056,
+      "step": 10137
+    },
+    {
+      "epoch": 0.26698175134567415,
+      "grad_norm": 1.2743796110153198,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.0514,
+      "step": 10168
+    },
+    {
+      "epoch": 0.2677957200997768,
+      "grad_norm": 1.260058879852295,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.0605,
+      "step": 10199
+    },
+    {
+      "epoch": 0.2686096888538795,
+      "grad_norm": 1.3755710124969482,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.0617,
+      "step": 10230
+    },
+    {
+      "epoch": 0.26942365760798215,
+      "grad_norm": 1.3561739921569824,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.0579,
+      "step": 10261
+    },
+    {
+      "epoch": 0.2702376263620848,
+      "grad_norm": 1.7726401090621948,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.0589,
+      "step": 10292
+    },
+    {
+      "epoch": 0.2710515951161875,
+      "grad_norm": 1.0805139541625977,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.0594,
+      "step": 10323
+    },
+    {
+      "epoch": 0.27186556387029015,
+      "grad_norm": 1.5827058553695679,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.0539,
+      "step": 10354
+    },
+    {
+      "epoch": 0.2726795326243928,
+      "grad_norm": 1.3298451900482178,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.0564,
+      "step": 10385
+    },
+    {
+      "epoch": 0.2734935013784955,
+      "grad_norm": 1.3214092254638672,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.0641,
+      "step": 10416
+    },
+    {
+      "epoch": 0.27430747013259815,
+      "grad_norm": 1.2646441459655762,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.0481,
+      "step": 10447
+    },
+    {
+      "epoch": 0.2751214388867008,
+      "grad_norm": 1.3135007619857788,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.0726,
+      "step": 10478
+    },
+    {
+      "epoch": 0.2759354076408035,
+      "grad_norm": 1.1592553853988647,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.0543,
+      "step": 10509
+    },
+    {
+      "epoch": 0.27674937639490615,
+      "grad_norm": 1.314353346824646,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.0626,
+      "step": 10540
+    },
+    {
+      "epoch": 0.2775633451490088,
+      "grad_norm": 1.4998137950897217,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.0542,
+      "step": 10571
+    },
+    {
+      "epoch": 0.27837731390311143,
+      "grad_norm": 1.2354265451431274,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.0646,
+      "step": 10602
+    },
+    {
+      "epoch": 0.2791912826572141,
+      "grad_norm": 1.2907658815383911,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.0694,
+      "step": 10633
+    },
+    {
+      "epoch": 0.28000525141131677,
+      "grad_norm": 1.4032567739486694,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.0673,
+      "step": 10664
+    },
+    {
+      "epoch": 0.28081922016541944,
+      "grad_norm": 1.397120475769043,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.0692,
+      "step": 10695
+    },
+    {
+      "epoch": 0.2816331889195221,
+      "grad_norm": 1.2310523986816406,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.054,
+      "step": 10726
+    },
+    {
+      "epoch": 0.28244715767362477,
+      "grad_norm": 1.566300868988037,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.0548,
+      "step": 10757
+    },
+    {
+      "epoch": 0.28326112642772744,
+      "grad_norm": 1.5181574821472168,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.0544,
+      "step": 10788
+    },
+    {
+      "epoch": 0.2840750951818301,
+      "grad_norm": 1.1848573684692383,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.0489,
+      "step": 10819
+    },
+    {
+      "epoch": 0.2848890639359328,
+      "grad_norm": 1.7483903169631958,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.0506,
+      "step": 10850
+    },
+    {
+      "epoch": 0.28570303269003544,
+      "grad_norm": 1.3677858114242554,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.0543,
+      "step": 10881
+    },
+    {
+      "epoch": 0.2865170014441381,
+      "grad_norm": 1.388460636138916,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.0607,
+      "step": 10912
+    },
+    {
+      "epoch": 0.2873309701982408,
+      "grad_norm": 1.380135178565979,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.0657,
+      "step": 10943
+    },
+    {
+      "epoch": 0.28814493895234344,
+      "grad_norm": 2.1109235286712646,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.0539,
+      "step": 10974
+    },
+    {
+      "epoch": 0.2889589077064461,
+      "grad_norm": 1.5365031957626343,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.0585,
+      "step": 11005
+    },
+    {
+      "epoch": 0.2897728764605488,
+      "grad_norm": 1.4971513748168945,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.049,
+      "step": 11036
+    },
+    {
+      "epoch": 0.29058684521465145,
+      "grad_norm": 1.3715277910232544,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.0697,
+      "step": 11067
+    },
+    {
+      "epoch": 0.2914008139687541,
+      "grad_norm": 1.5066416263580322,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.0517,
+      "step": 11098
+    },
+    {
+      "epoch": 0.2922147827228568,
+      "grad_norm": 1.2851423025131226,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.0571,
+      "step": 11129
+    },
+    {
+      "epoch": 0.29302875147695945,
+      "grad_norm": 1.29548978805542,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.0523,
+      "step": 11160
+    },
+    {
+      "epoch": 0.2938427202310621,
+      "grad_norm": 1.4747354984283447,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.0439,
+      "step": 11191
+    },
+    {
+      "epoch": 0.2946566889851648,
+      "grad_norm": 1.2662986516952515,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.0572,
+      "step": 11222
+    },
+    {
+      "epoch": 0.29547065773926745,
+      "grad_norm": 1.2613598108291626,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.0629,
+      "step": 11253
+    },
+    {
+      "epoch": 0.2962846264933701,
+      "grad_norm": 1.5084261894226074,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.0582,
+      "step": 11284
+    },
+    {
+      "epoch": 0.2970985952474728,
+      "grad_norm": 1.4516050815582275,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.0509,
+      "step": 11315
+    },
+    {
+      "epoch": 0.2979125640015754,
+      "grad_norm": 1.2777527570724487,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.0578,
+      "step": 11346
+    },
+    {
+      "epoch": 0.29872653275567806,
+      "grad_norm": 1.7656491994857788,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.0522,
+      "step": 11377
+    },
+    {
+      "epoch": 0.29954050150978073,
+      "grad_norm": 1.2943507432937622,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.0426,
+      "step": 11408
+    },
+    {
+      "epoch": 0.3003544702638834,
+      "grad_norm": 1.2916288375854492,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.0553,
+      "step": 11439
+    },
+    {
+      "epoch": 0.30116843901798607,
+      "grad_norm": 1.422892451286316,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.0432,
+      "step": 11470
+    },
+    {
+      "epoch": 0.30198240777208873,
+      "grad_norm": 1.1640053987503052,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.0619,
+      "step": 11501
+    },
+    {
+      "epoch": 0.3027963765261914,
+      "grad_norm": 1.1214442253112793,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.0503,
+      "step": 11532
+    },
+    {
+      "epoch": 0.30361034528029407,
+      "grad_norm": 1.2379281520843506,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.041,
+      "step": 11563
+    },
+    {
+      "epoch": 0.30442431403439674,
+      "grad_norm": 1.4117130041122437,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.0594,
+      "step": 11594
+    },
+    {
+      "epoch": 0.3052382827884994,
+      "grad_norm": 1.2534124851226807,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.0419,
+      "step": 11625
+    },
+    {
+      "epoch": 0.30605225154260207,
+      "grad_norm": 1.1628893613815308,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.0487,
+      "step": 11656
+    },
+    {
+      "epoch": 0.30686622029670474,
+      "grad_norm": 1.0175715684890747,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.052,
+      "step": 11687
+    },
+    {
+      "epoch": 0.3076801890508074,
+      "grad_norm": 1.3455405235290527,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.0549,
+      "step": 11718
+    },
+    {
+      "epoch": 0.3084941578049101,
+      "grad_norm": 1.4206137657165527,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.043,
+      "step": 11749
+    },
+    {
+      "epoch": 0.30930812655901274,
+      "grad_norm": 2.0476608276367188,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.051,
+      "step": 11780
+    },
+    {
+      "epoch": 0.3101220953131154,
+      "grad_norm": 1.2169727087020874,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.0465,
+      "step": 11811
+    },
+    {
+      "epoch": 0.3109360640672181,
+      "grad_norm": 1.4038310050964355,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.0535,
+      "step": 11842
+    },
+    {
+      "epoch": 0.31175003282132074,
+      "grad_norm": 1.5230700969696045,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.0596,
+      "step": 11873
+    },
+    {
+      "epoch": 0.3125640015754234,
+      "grad_norm": 1.2232719659805298,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.0554,
+      "step": 11904
+    },
+    {
+      "epoch": 0.3133779703295261,
+      "grad_norm": 1.1676846742630005,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.042,
+      "step": 11935
+    },
+    {
+      "epoch": 0.31419193908362875,
+      "grad_norm": 1.7241026163101196,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.0432,
+      "step": 11966
+    },
+    {
+      "epoch": 0.3150059078377314,
+      "grad_norm": 1.5652648210525513,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.0476,
+      "step": 11997
+    },
+    {
+      "epoch": 0.3158198765918341,
+      "grad_norm": 1.4380812644958496,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.0383,
+      "step": 12028
+    },
+    {
+      "epoch": 0.3166338453459367,
+      "grad_norm": 1.1632492542266846,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.0459,
+      "step": 12059
+    },
+    {
+      "epoch": 0.31744781410003936,
+      "grad_norm": 1.5992326736450195,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.0421,
+      "step": 12090
+    },
+    {
+      "epoch": 0.31826178285414203,
+      "grad_norm": 1.1701931953430176,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.0456,
+      "step": 12121
+    },
+    {
+      "epoch": 0.3190757516082447,
+      "grad_norm": 1.482156753540039,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.0386,
+      "step": 12152
+    },
+    {
+      "epoch": 0.31988972036234736,
+      "grad_norm": 1.1279046535491943,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.0355,
+      "step": 12183
+    },
+    {
+      "epoch": 0.32070368911645003,
+      "grad_norm": 1.1521446704864502,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 1.0329,
+      "step": 12214
+    },
+    {
+      "epoch": 0.3215176578705527,
+      "grad_norm": 1.2494932413101196,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 1.0547,
+      "step": 12245
+    },
+    {
+      "epoch": 0.32233162662465537,
+      "grad_norm": 1.1259201765060425,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 1.0519,
+      "step": 12276
+    },
+    {
+      "epoch": 0.32314559537875803,
+      "grad_norm": 1.2630201578140259,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 1.0447,
+      "step": 12307
+    },
+    {
+      "epoch": 0.3239595641328607,
+      "grad_norm": 1.52993905544281,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 1.0404,
+      "step": 12338
+    },
+    {
+      "epoch": 0.32477353288696337,
+      "grad_norm": 1.3933169841766357,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 1.0403,
+      "step": 12369
+    },
+    {
+      "epoch": 0.32558750164106603,
+      "grad_norm": 1.6856379508972168,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 1.0447,
+      "step": 12400
+    },
+    {
+      "epoch": 0.3264014703951687,
+      "grad_norm": 1.3028291463851929,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 1.0432,
+      "step": 12431
+    },
+    {
+      "epoch": 0.32721543914927137,
+      "grad_norm": 1.123894214630127,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 1.0415,
+      "step": 12462
+    },
+    {
+      "epoch": 0.32802940790337404,
+      "grad_norm": 1.4955415725708008,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 1.0354,
+      "step": 12493
+    },
+    {
+      "epoch": 0.3288433766574767,
+      "grad_norm": 1.099989652633667,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 1.0365,
+      "step": 12524
+    },
+    {
+      "epoch": 0.32965734541157937,
+      "grad_norm": 1.2428457736968994,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 1.0466,
+      "step": 12555
+    },
+    {
+      "epoch": 0.33047131416568204,
+      "grad_norm": 1.1839311122894287,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 1.0453,
+      "step": 12586
+    },
+    {
+      "epoch": 0.3312852829197847,
+      "grad_norm": 1.36717689037323,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 1.0473,
+      "step": 12617
+    },
+    {
+      "epoch": 0.3320992516738874,
+      "grad_norm": 1.432884931564331,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 1.0462,
+      "step": 12648
+    },
+    {
+      "epoch": 0.33291322042799004,
+      "grad_norm": 1.045279622077942,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 1.0429,
+      "step": 12679
+    },
+    {
+      "epoch": 0.3337271891820927,
+      "grad_norm": 1.05605149269104,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 1.0292,
+      "step": 12710
+    },
+    {
+      "epoch": 0.3345411579361954,
+      "grad_norm": 1.1445974111557007,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 1.0492,
+      "step": 12741
+    },
+    {
+      "epoch": 0.33535512669029804,
+      "grad_norm": 1.4154634475708008,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 1.0404,
+      "step": 12772
+    },
+    {
+      "epoch": 0.33616909544440066,
+      "grad_norm": 1.3315508365631104,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 1.0283,
+      "step": 12803
+    },
+    {
+      "epoch": 0.3369830641985033,
+      "grad_norm": 1.9535698890686035,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 1.055,
+      "step": 12834
+    },
+    {
+      "epoch": 0.337797032952606,
+      "grad_norm": 1.262664556503296,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 1.0362,
+      "step": 12865
+    },
+    {
+      "epoch": 0.33861100170670866,
+      "grad_norm": 1.2608447074890137,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 1.041,
+      "step": 12896
+    },
+    {
+      "epoch": 0.3394249704608113,
+      "grad_norm": 1.138190507888794,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 1.0421,
+      "step": 12927
+    },
+    {
+      "epoch": 0.340238939214914,
+      "grad_norm": 1.372586965560913,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 1.0323,
+      "step": 12958
+    },
+    {
+      "epoch": 0.34105290796901666,
+      "grad_norm": 1.2018133401870728,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 1.0507,
+      "step": 12989
+    },
+    {
+      "epoch": 0.34186687672311933,
+      "grad_norm": 1.1174499988555908,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 1.0411,
+      "step": 13020
+    },
+    {
+      "epoch": 0.342680845477222,
+      "grad_norm": 1.7044398784637451,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 1.0493,
+      "step": 13051
+    },
+    {
+      "epoch": 0.34349481423132466,
+      "grad_norm": 1.284325122833252,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 1.0473,
+      "step": 13082
+    },
+    {
+      "epoch": 0.34430878298542733,
+      "grad_norm": 1.0263391733169556,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 1.0449,
+      "step": 13113
+    },
+    {
+      "epoch": 0.34512275173953,
+      "grad_norm": 1.4493783712387085,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 1.024,
+      "step": 13144
+    },
+    {
+      "epoch": 0.34593672049363267,
+      "grad_norm": 1.5828895568847656,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 1.0358,
+      "step": 13175
+    },
+    {
+      "epoch": 0.34675068924773533,
+      "grad_norm": 1.3441163301467896,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 1.0429,
+      "step": 13206
+    },
+    {
+      "epoch": 0.347564658001838,
+      "grad_norm": 1.3031971454620361,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 1.0377,
+      "step": 13237
+    },
+    {
+      "epoch": 0.34837862675594067,
+      "grad_norm": 1.195386528968811,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 1.0411,
+      "step": 13268
+    },
+    {
+      "epoch": 0.34919259551004334,
+      "grad_norm": 1.592167615890503,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 1.0421,
+      "step": 13299
+    },
+    {
+      "epoch": 0.350006564264146,
+      "grad_norm": 0.9788748621940613,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 1.035,
+      "step": 13330
+    },
+    {
+      "epoch": 0.35082053301824867,
+      "grad_norm": 1.288126826286316,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 1.0405,
+      "step": 13361
+    },
+    {
+      "epoch": 0.35163450177235134,
+      "grad_norm": 1.0866012573242188,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 1.0381,
+      "step": 13392
+    },
+    {
+      "epoch": 0.352448470526454,
+      "grad_norm": 1.6304558515548706,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 1.04,
+      "step": 13423
+    },
+    {
+      "epoch": 0.3532624392805567,
+      "grad_norm": 1.4997541904449463,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 1.0197,
+      "step": 13454
+    },
+    {
+      "epoch": 0.35407640803465934,
+      "grad_norm": 1.4830362796783447,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 1.0306,
+      "step": 13485
+    },
+    {
+      "epoch": 0.35489037678876195,
+      "grad_norm": 1.382399320602417,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 1.0364,
+      "step": 13516
+    },
+    {
+      "epoch": 0.3557043455428646,
+      "grad_norm": 1.0394059419631958,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 1.0213,
+      "step": 13547
+    },
+    {
+      "epoch": 0.3565183142969673,
+      "grad_norm": 1.048570990562439,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 1.0295,
+      "step": 13578
+    },
+    {
+      "epoch": 0.35733228305106995,
+      "grad_norm": 1.4423623085021973,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 1.0218,
+      "step": 13609
+    },
+    {
+      "epoch": 0.3581462518051726,
+      "grad_norm": 1.2871686220169067,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 1.0434,
+      "step": 13640
+    },
+    {
+      "epoch": 0.3589602205592753,
+      "grad_norm": 1.1277636289596558,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 1.025,
+      "step": 13671
+    },
+    {
+      "epoch": 0.35977418931337796,
+      "grad_norm": 1.4157992601394653,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 1.0335,
+      "step": 13702
+    },
+    {
+      "epoch": 0.3605881580674806,
+      "grad_norm": 1.350058913230896,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 1.0425,
+      "step": 13733
+    },
+    {
+      "epoch": 0.3614021268215833,
+      "grad_norm": 1.3346654176712036,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 1.03,
+      "step": 13764
+    },
+    {
+      "epoch": 0.36221609557568596,
+      "grad_norm": 1.2549309730529785,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 1.0297,
+      "step": 13795
+    },
+    {
+      "epoch": 0.3630300643297886,
+      "grad_norm": 1.4838144779205322,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 1.0259,
+      "step": 13826
+    },
+    {
+      "epoch": 0.3638440330838913,
+      "grad_norm": 1.1665525436401367,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 1.0299,
+      "step": 13857
+    },
+    {
+      "epoch": 0.36465800183799396,
+      "grad_norm": 1.2306339740753174,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 1.0384,
+      "step": 13888
+    },
+    {
+      "epoch": 0.36547197059209663,
+      "grad_norm": 1.2738476991653442,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 1.0354,
+      "step": 13919
+    },
+    {
+      "epoch": 0.3662859393461993,
+      "grad_norm": 1.1638579368591309,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 1.0399,
+      "step": 13950
+    },
+    {
+      "epoch": 0.36709990810030196,
+      "grad_norm": 1.0074785947799683,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 1.0263,
+      "step": 13981
+    },
+    {
+      "epoch": 0.36791387685440463,
+      "grad_norm": 1.3604648113250732,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 1.0199,
+      "step": 14012
+    },
+    {
+      "epoch": 0.3687278456085073,
+      "grad_norm": 1.7506765127182007,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 1.0392,
+      "step": 14043
+    },
+    {
+      "epoch": 0.36954181436260997,
+      "grad_norm": 1.3466100692749023,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 1.045,
+      "step": 14074
+    },
+    {
+      "epoch": 0.37035578311671263,
+      "grad_norm": 1.6784629821777344,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 1.0232,
+      "step": 14105
+    },
+    {
+      "epoch": 0.3711697518708153,
+      "grad_norm": 1.0676754713058472,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 1.0222,
+      "step": 14136
+    },
+    {
+      "epoch": 0.37198372062491797,
+      "grad_norm": 1.604209065437317,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 1.0338,
+      "step": 14167
+    },
+    {
+      "epoch": 0.37279768937902064,
+      "grad_norm": 1.588007926940918,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 1.0252,
+      "step": 14198
+    },
+    {
+      "epoch": 0.3736116581331233,
+      "grad_norm": 1.1464117765426636,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 1.0269,
+      "step": 14229
+    },
+    {
+      "epoch": 0.3744256268872259,
+      "grad_norm": 1.2006999254226685,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 1.0143,
+      "step": 14260
+    },
+    {
+      "epoch": 0.3752395956413286,
+      "grad_norm": 1.1799211502075195,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 1.0291,
+      "step": 14291
+    },
+    {
+      "epoch": 0.37605356439543125,
+      "grad_norm": 1.6088860034942627,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 1.0334,
+      "step": 14322
+    },
+    {
+      "epoch": 0.3768675331495339,
+      "grad_norm": 1.2822155952453613,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 1.0279,
+      "step": 14353
+    },
+    {
+      "epoch": 0.3776815019036366,
+      "grad_norm": 1.3717602491378784,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 1.0138,
+      "step": 14384
+    },
+    {
+      "epoch": 0.37849547065773925,
+      "grad_norm": 1.3948458433151245,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 1.0334,
+      "step": 14415
+    },
+    {
+      "epoch": 0.3793094394118419,
+      "grad_norm": 1.2528660297393799,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 1.0224,
+      "step": 14446
+    },
+    {
+      "epoch": 0.3801234081659446,
+      "grad_norm": 1.354975938796997,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 1.024,
+      "step": 14477
+    },
+    {
+      "epoch": 0.38093737692004725,
+      "grad_norm": 1.2346854209899902,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 1.0239,
+      "step": 14508
+    },
+    {
+      "epoch": 0.3817513456741499,
+      "grad_norm": 1.1305748224258423,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 1.0328,
+      "step": 14539
+    },
+    {
+      "epoch": 0.3825653144282526,
+      "grad_norm": 0.9909107089042664,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 1.0262,
+      "step": 14570
+    },
+    {
+      "epoch": 0.38337928318235526,
+      "grad_norm": 1.260072946548462,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 1.0276,
+      "step": 14601
+    },
+    {
+      "epoch": 0.3841932519364579,
+      "grad_norm": 1.230176568031311,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 1.0205,
+      "step": 14632
+    },
+    {
+      "epoch": 0.3850072206905606,
+      "grad_norm": 1.3262946605682373,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 1.0297,
+      "step": 14663
+    },
+    {
+      "epoch": 0.38582118944466326,
+      "grad_norm": 1.3962515592575073,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 1.0227,
+      "step": 14694
+    },
+    {
+      "epoch": 0.3866351581987659,
+      "grad_norm": 1.2761191129684448,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 1.018,
+      "step": 14725
+    },
+    {
+      "epoch": 0.3874491269528686,
+      "grad_norm": 1.160860538482666,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 1.0193,
+      "step": 14756
+    },
+    {
+      "epoch": 0.38826309570697126,
+      "grad_norm": 1.3368817567825317,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 1.0338,
+      "step": 14787
+    },
+    {
+      "epoch": 0.38907706446107393,
+      "grad_norm": 1.1442415714263916,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 1.0179,
+      "step": 14818
+    },
+    {
+      "epoch": 0.3898910332151766,
+      "grad_norm": 0.9936277270317078,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 1.0179,
+      "step": 14849
+    },
+    {
+      "epoch": 0.39070500196927926,
+      "grad_norm": 1.4644626379013062,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 1.023,
+      "step": 14880
+    },
+    {
+      "epoch": 0.39151897072338193,
+      "grad_norm": 1.3222097158432007,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 1.0186,
+      "step": 14911
+    },
+    {
+      "epoch": 0.3923329394774846,
+      "grad_norm": 1.384956955909729,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 1.0279,
+      "step": 14942
+    },
+    {
+      "epoch": 0.39314690823158727,
+      "grad_norm": 1.3031655550003052,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 1.0062,
+      "step": 14973
+    },
+    {
+      "epoch": 0.3939608769856899,
+      "grad_norm": 1.319303274154663,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 1.0243,
+      "step": 15004
+    },
+    {
+      "epoch": 0.39477484573979255,
+      "grad_norm": 1.139217495918274,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 1.0228,
+      "step": 15035
+    },
+    {
+      "epoch": 0.3955888144938952,
+      "grad_norm": 1.494051456451416,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 1.0209,
+      "step": 15066
+    },
+    {
+      "epoch": 0.3964027832479979,
+      "grad_norm": 1.402320146560669,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 1.0072,
+      "step": 15097
+    },
+    {
+      "epoch": 0.39721675200210055,
+      "grad_norm": 1.411827564239502,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 1.021,
+      "step": 15128
+    },
+    {
+      "epoch": 0.3980307207562032,
+      "grad_norm": 1.1419063806533813,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 1.0277,
+      "step": 15159
+    },
+    {
+      "epoch": 0.3988446895103059,
+      "grad_norm": 1.2265127897262573,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 1.032,
+      "step": 15190
+    },
+    {
+      "epoch": 0.39965865826440855,
+      "grad_norm": 1.2999345064163208,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 1.0171,
+      "step": 15221
+    },
+    {
+      "epoch": 0.4004726270185112,
+      "grad_norm": 1.0721927881240845,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 1.0299,
+      "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:bab9caa19bbcbaea1127e8615eb39fda6d96afa462c878d00c2364fcb7e8f8ea
+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 sha256:4db4e864dd5dfa7e8b556b7ded29e2b7569f15078d54bafa3146d9bb2a223f42
+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:c249a0d75ff1689d1359a13d7effb0aa6b1db5c59082c4e3ac46fd2c798623a5
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5441f6f49adabe45cf92c9ebae0233f119c87b9c163503111829997fa87ede6
+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:cec0beff9a46ef2055bdcad47b4e7ff06129a1d9d4219864dcb754474f70a1fa
+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:bab9caa19bbcbaea1127e8615eb39fda6d96afa462c878d00c2364fcb7e8f8ea
+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:f316942a1fb01e691e18be89b5ba5286871225125c44b6f15c118326a1b53f33
+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:fb357f40d89a2c6b16533a892feece954f1aac621a9b35c576b316296e1c7c74
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e54cd0cd820d76b4a797fcaa858d9e09ea533608e1064728266e3dad74bed1
+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 sha256:8d53e1c0d7c2fd8c3ba214422adcb85b7e353ccec0325dbf26d7afcb0665f7b5
+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:bab9caa19bbcbaea1127e8615eb39fda6d96afa462c878d00c2364fcb7e8f8ea
+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:f316942a1fb01e691e18be89b5ba5286871225125c44b6f15c118326a1b53f33
+size 4976687216