Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/gruntdata/event_graph/llm_models/Qwen2.5-14B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1bea0a8dd5abc45a6d6416ddfe8505b7ebce20922290af3eabb944404b91a53
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16bc0ef76a15c4627fd83b65bdd7cc2880777c85dbb989727b5975c608c10bb
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e9968fd644c321708cd356434802fb6628b2ed19bf16fb83fc52e6d54bd171
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336519e8c47c270ff484b609645f3601247875f06305349937c343bbe0191d61
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5021fcf19b9e19366c0d66c5c80676445f1cca7c37b9e8c18bffc90eea7b9c
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a974f5c76a49c183710b4b4f3dc2d1d12f8a85d48c8e3ac10637855bc9d8975
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1881 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9745042492917846,
+  "eval_steps": 500,
+  "global_step": 264,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0113314447592068,
+      "grad_norm": 23.53424926746809,
+      "learning_rate": 3.7037037037037036e-07,
+      "loss": 1.4032,
+      "step": 1
+    },
+    {
+      "epoch": 0.0226628895184136,
+      "grad_norm": 23.298712049647957,
+      "learning_rate": 7.407407407407407e-07,
+      "loss": 1.4235,
+      "step": 2
+    },
+    {
+      "epoch": 0.0339943342776204,
+      "grad_norm": 25.15418991437702,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.3918,
+      "step": 3
+    },
+    {
+      "epoch": 0.0453257790368272,
+      "grad_norm": 23.513705846381587,
+      "learning_rate": 1.4814814814814815e-06,
+      "loss": 1.3583,
+      "step": 4
+    },
+    {
+      "epoch": 0.056657223796033995,
+      "grad_norm": 18.732779423937743,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 1.2546,
+      "step": 5
+    },
+    {
+      "epoch": 0.0679886685552408,
+      "grad_norm": 19.557080948103327,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.2998,
+      "step": 6
+    },
+    {
+      "epoch": 0.07932011331444759,
+      "grad_norm": 10.724009151468064,
+      "learning_rate": 2.5925925925925925e-06,
+      "loss": 1.2226,
+      "step": 7
+    },
+    {
+      "epoch": 0.0906515580736544,
+      "grad_norm": 4.775800267490731,
+      "learning_rate": 2.962962962962963e-06,
+      "loss": 1.0559,
+      "step": 8
+    },
+    {
+      "epoch": 0.10198300283286119,
+      "grad_norm": 3.94648433253879,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0475,
+      "step": 9
+    },
+    {
+      "epoch": 0.11331444759206799,
+      "grad_norm": 3.2410802138408448,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.9999,
+      "step": 10
+    },
+    {
+      "epoch": 0.12464589235127478,
+      "grad_norm": 3.409262196892178,
+      "learning_rate": 4.074074074074074e-06,
+      "loss": 0.9393,
+      "step": 11
+    },
+    {
+      "epoch": 0.1359773371104816,
+      "grad_norm": 2.7175044653926625,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.9487,
+      "step": 12
+    },
+    {
+      "epoch": 0.14730878186968838,
+      "grad_norm": 2.3048951821321078,
+      "learning_rate": 4.814814814814815e-06,
+      "loss": 0.9302,
+      "step": 13
+    },
+    {
+      "epoch": 0.15864022662889518,
+      "grad_norm": 2.172665075682734,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 0.9152,
+      "step": 14
+    },
+    {
+      "epoch": 0.16997167138810199,
+      "grad_norm": 2.1574147876066445,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.828,
+      "step": 15
+    },
+    {
+      "epoch": 0.1813031161473088,
+      "grad_norm": 2.097885575557383,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 0.8426,
+      "step": 16
+    },
+    {
+      "epoch": 0.19263456090651557,
+      "grad_norm": 1.7637510926108797,
+      "learning_rate": 6.296296296296297e-06,
+      "loss": 0.8096,
+      "step": 17
+    },
+    {
+      "epoch": 0.20396600566572237,
+      "grad_norm": 1.6562239272452715,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.838,
+      "step": 18
+    },
+    {
+      "epoch": 0.21529745042492918,
+      "grad_norm": 1.4205229302221682,
+      "learning_rate": 7.0370370370370375e-06,
+      "loss": 0.7763,
+      "step": 19
+    },
+    {
+      "epoch": 0.22662889518413598,
+      "grad_norm": 1.4262379616902559,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.7698,
+      "step": 20
+    },
+    {
+      "epoch": 0.23796033994334279,
+      "grad_norm": 1.6494892959766825,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.7665,
+      "step": 21
+    },
+    {
+      "epoch": 0.24929178470254956,
+      "grad_norm": 1.4334685604983732,
+      "learning_rate": 8.148148148148148e-06,
+      "loss": 0.7822,
+      "step": 22
+    },
+    {
+      "epoch": 0.26062322946175637,
+      "grad_norm": 1.3849818905239097,
+      "learning_rate": 8.518518518518519e-06,
+      "loss": 0.7283,
+      "step": 23
+    },
+    {
+      "epoch": 0.2719546742209632,
+      "grad_norm": 1.341658865495544,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.6999,
+      "step": 24
+    },
+    {
+      "epoch": 0.28328611898017,
+      "grad_norm": 1.30493584130229,
+      "learning_rate": 9.25925925925926e-06,
+      "loss": 0.7367,
+      "step": 25
+    },
+    {
+      "epoch": 0.29461756373937675,
+      "grad_norm": 1.400982166207809,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 0.7212,
+      "step": 26
+    },
+    {
+      "epoch": 0.3059490084985836,
+      "grad_norm": 1.2376220091039114,
+      "learning_rate": 1e-05,
+      "loss": 0.7211,
+      "step": 27
+    },
+    {
+      "epoch": 0.31728045325779036,
+      "grad_norm": 1.3155466485701666,
+      "learning_rate": 9.999560724782173e-06,
+      "loss": 0.7194,
+      "step": 28
+    },
+    {
+      "epoch": 0.3286118980169972,
+      "grad_norm": 1.1452371029975463,
+      "learning_rate": 9.998242976313777e-06,
+      "loss": 0.7205,
+      "step": 29
+    },
+    {
+      "epoch": 0.33994334277620397,
+      "grad_norm": 1.166971440865611,
+      "learning_rate": 9.99604698613651e-06,
+      "loss": 0.7097,
+      "step": 30
+    },
+    {
+      "epoch": 0.35127478753541075,
+      "grad_norm": 1.3261901880488491,
+      "learning_rate": 9.992973140107998e-06,
+      "loss": 0.6974,
+      "step": 31
+    },
+    {
+      "epoch": 0.3626062322946176,
+      "grad_norm": 1.2464894375774034,
+      "learning_rate": 9.989021978333996e-06,
+      "loss": 0.7082,
+      "step": 32
+    },
+    {
+      "epoch": 0.37393767705382436,
+      "grad_norm": 1.1355726846388239,
+      "learning_rate": 9.98419419507348e-06,
+      "loss": 0.6734,
+      "step": 33
+    },
+    {
+      "epoch": 0.38526912181303113,
+      "grad_norm": 1.0490944265922426,
+      "learning_rate": 9.978490638616671e-06,
+      "loss": 0.6853,
+      "step": 34
+    },
+    {
+      "epoch": 0.39660056657223797,
+      "grad_norm": 1.2600398341735712,
+      "learning_rate": 9.971912311135967e-06,
+      "loss": 0.6703,
+      "step": 35
+    },
+    {
+      "epoch": 0.40793201133144474,
+      "grad_norm": 1.1344614916090783,
+      "learning_rate": 9.964460368509868e-06,
+      "loss": 0.6841,
+      "step": 36
+    },
+    {
+      "epoch": 0.4192634560906516,
+      "grad_norm": 1.1274773706270436,
+      "learning_rate": 9.956136120119858e-06,
+      "loss": 0.6817,
+      "step": 37
+    },
+    {
+      "epoch": 0.43059490084985835,
+      "grad_norm": 1.2113014190849545,
+      "learning_rate": 9.946941028620349e-06,
+      "loss": 0.6837,
+      "step": 38
+    },
+    {
+      "epoch": 0.44192634560906513,
+      "grad_norm": 1.172097274900492,
+      "learning_rate": 9.936876709681668e-06,
+      "loss": 0.6678,
+      "step": 39
+    },
+    {
+      "epoch": 0.45325779036827196,
+      "grad_norm": 1.2490078546533159,
+      "learning_rate": 9.925944931706174e-06,
+      "loss": 0.7413,
+      "step": 40
+    },
+    {
+      "epoch": 0.46458923512747874,
+      "grad_norm": 1.140086857717275,
+      "learning_rate": 9.914147615517527e-06,
+      "loss": 0.6778,
+      "step": 41
+    },
+    {
+      "epoch": 0.47592067988668557,
+      "grad_norm": 1.2223423143241732,
+      "learning_rate": 9.901486834023182e-06,
+      "loss": 0.7388,
+      "step": 42
+    },
+    {
+      "epoch": 0.48725212464589235,
+      "grad_norm": 1.2452223599483243,
+      "learning_rate": 9.887964811850159e-06,
+      "loss": 0.691,
+      "step": 43
+    },
+    {
+      "epoch": 0.4985835694050991,
+      "grad_norm": 1.1350515055455908,
+      "learning_rate": 9.873583924954152e-06,
+      "loss": 0.6593,
+      "step": 44
+    },
+    {
+      "epoch": 0.509915014164306,
+      "grad_norm": 1.0405719380983063,
+      "learning_rate": 9.85834670020205e-06,
+      "loss": 0.6351,
+      "step": 45
+    },
+    {
+      "epoch": 0.5212464589235127,
+      "grad_norm": 1.3303109757890985,
+      "learning_rate": 9.842255814927945e-06,
+      "loss": 0.6404,
+      "step": 46
+    },
+    {
+      "epoch": 0.5325779036827195,
+      "grad_norm": 1.1787017310861478,
+      "learning_rate": 9.825314096462686e-06,
+      "loss": 0.6858,
+      "step": 47
+    },
+    {
+      "epoch": 0.5439093484419264,
+      "grad_norm": 1.1028621034116284,
+      "learning_rate": 9.807524521637103e-06,
+      "loss": 0.6554,
+      "step": 48
+    },
+    {
+      "epoch": 0.5552407932011332,
+      "grad_norm": 1.0192876247663198,
+      "learning_rate": 9.78889021625894e-06,
+      "loss": 0.6581,
+      "step": 49
+    },
+    {
+      "epoch": 0.56657223796034,
+      "grad_norm": 1.0981773991994468,
+      "learning_rate": 9.769414454563614e-06,
+      "loss": 0.6873,
+      "step": 50
+    },
+    {
+      "epoch": 0.5779036827195467,
+      "grad_norm": 1.080964680948062,
+      "learning_rate": 9.749100658638914e-06,
+      "loss": 0.6313,
+      "step": 51
+    },
+    {
+      "epoch": 0.5892351274787535,
+      "grad_norm": 1.060635241593271,
+      "learning_rate": 9.72795239782369e-06,
+      "loss": 0.657,
+      "step": 52
+    },
+    {
+      "epoch": 0.6005665722379604,
+      "grad_norm": 1.1436681010237095,
+      "learning_rate": 9.705973388080694e-06,
+      "loss": 0.6521,
+      "step": 53
+    },
+    {
+      "epoch": 0.6118980169971672,
+      "grad_norm": 1.0838029458150678,
+      "learning_rate": 9.68316749134364e-06,
+      "loss": 0.6712,
+      "step": 54
+    },
+    {
+      "epoch": 0.623229461756374,
+      "grad_norm": 1.0579456798759823,
+      "learning_rate": 9.659538714838635e-06,
+      "loss": 0.6439,
+      "step": 55
+    },
+    {
+      "epoch": 0.6345609065155807,
+      "grad_norm": 1.000408593357701,
+      "learning_rate": 9.635091210380052e-06,
+      "loss": 0.6164,
+      "step": 56
+    },
+    {
+      "epoch": 0.6458923512747875,
+      "grad_norm": 1.0871122101771147,
+      "learning_rate": 9.609829273641034e-06,
+      "loss": 0.6561,
+      "step": 57
+    },
+    {
+      "epoch": 0.6572237960339944,
+      "grad_norm": 1.0392258903623652,
+      "learning_rate": 9.583757343398685e-06,
+      "loss": 0.6353,
+      "step": 58
+    },
+    {
+      "epoch": 0.6685552407932012,
+      "grad_norm": 1.0694855168162771,
+      "learning_rate": 9.55688000075414e-06,
+      "loss": 0.672,
+      "step": 59
+    },
+    {
+      "epoch": 0.6798866855524079,
+      "grad_norm": 1.0818048041242603,
+      "learning_rate": 9.529201968327618e-06,
+      "loss": 0.6649,
+      "step": 60
+    },
+    {
+      "epoch": 0.6912181303116147,
+      "grad_norm": 1.122154267801109,
+      "learning_rate": 9.500728109428603e-06,
+      "loss": 0.6338,
+      "step": 61
+    },
+    {
+      "epoch": 0.7025495750708215,
+      "grad_norm": 1.0115716268572774,
+      "learning_rate": 9.47146342720133e-06,
+      "loss": 0.6404,
+      "step": 62
+    },
+    {
+      "epoch": 0.7138810198300283,
+      "grad_norm": 1.060628179091387,
+      "learning_rate": 9.44141306374566e-06,
+      "loss": 0.6491,
+      "step": 63
+    },
+    {
+      "epoch": 0.7252124645892352,
+      "grad_norm": 1.0433876035374046,
+      "learning_rate": 9.410582299213574e-06,
+      "loss": 0.6131,
+      "step": 64
+    },
+    {
+      "epoch": 0.7365439093484419,
+      "grad_norm": 1.0724446453489962,
+      "learning_rate": 9.378976550881393e-06,
+      "loss": 0.645,
+      "step": 65
+    },
+    {
+      "epoch": 0.7478753541076487,
+      "grad_norm": 16.698318216158572,
+      "learning_rate": 9.346601372197914e-06,
+      "loss": 0.628,
+      "step": 66
+    },
+    {
+      "epoch": 0.7592067988668555,
+      "grad_norm": 1.088611623094774,
+      "learning_rate": 9.3134624518086e-06,
+      "loss": 0.651,
+      "step": 67
+    },
+    {
+      "epoch": 0.7705382436260623,
+      "grad_norm": 1.08573159288467,
+      "learning_rate": 9.279565612556043e-06,
+      "loss": 0.6913,
+      "step": 68
+    },
+    {
+      "epoch": 0.7818696883852692,
+      "grad_norm": 1.287771998076043,
+      "learning_rate": 9.244916810456822e-06,
+      "loss": 0.6167,
+      "step": 69
+    },
+    {
+      "epoch": 0.7932011331444759,
+      "grad_norm": 1.0734450115631073,
+      "learning_rate": 9.20952213365497e-06,
+      "loss": 0.6048,
+      "step": 70
+    },
+    {
+      "epoch": 0.8045325779036827,
+      "grad_norm": 1.041169203868327,
+      "learning_rate": 9.173387801352232e-06,
+      "loss": 0.622,
+      "step": 71
+    },
+    {
+      "epoch": 0.8158640226628895,
+      "grad_norm": 1.0441941562582049,
+      "learning_rate": 9.136520162715288e-06,
+      "loss": 0.636,
+      "step": 72
+    },
+    {
+      "epoch": 0.8271954674220963,
+      "grad_norm": 1.0266494367822185,
+      "learning_rate": 9.098925695760132e-06,
+      "loss": 0.641,
+      "step": 73
+    },
+    {
+      "epoch": 0.8385269121813032,
+      "grad_norm": 1.0525228370033899,
+      "learning_rate": 9.060611006213833e-06,
+      "loss": 0.605,
+      "step": 74
+    },
+    {
+      "epoch": 0.8498583569405099,
+      "grad_norm": 1.0169561500024211,
+      "learning_rate": 9.021582826353825e-06,
+      "loss": 0.6691,
+      "step": 75
+    },
+    {
+      "epoch": 0.8611898016997167,
+      "grad_norm": 1.0482739302531685,
+      "learning_rate": 8.981848013824995e-06,
+      "loss": 0.6658,
+      "step": 76
+    },
+    {
+      "epoch": 0.8725212464589235,
+      "grad_norm": 1.0794377750181379,
+      "learning_rate": 8.94141355043471e-06,
+      "loss": 0.6578,
+      "step": 77
+    },
+    {
+      "epoch": 0.8838526912181303,
+      "grad_norm": 1.0439742131558416,
+      "learning_rate": 8.900286540926062e-06,
+      "loss": 0.6138,
+      "step": 78
+    },
+    {
+      "epoch": 0.8951841359773371,
+      "grad_norm": 1.072198566934302,
+      "learning_rate": 8.85847421172947e-06,
+      "loss": 0.6313,
+      "step": 79
+    },
+    {
+      "epoch": 0.9065155807365439,
+      "grad_norm": 1.0570789500714661,
+      "learning_rate": 8.815983909692941e-06,
+      "loss": 0.611,
+      "step": 80
+    },
+    {
+      "epoch": 0.9178470254957507,
+      "grad_norm": 0.9747424186741095,
+      "learning_rate": 8.772823100791152e-06,
+      "loss": 0.6235,
+      "step": 81
+    },
+    {
+      "epoch": 0.9291784702549575,
+      "grad_norm": 0.9650403389286071,
+      "learning_rate": 8.728999368813591e-06,
+      "loss": 0.6289,
+      "step": 82
+    },
+    {
+      "epoch": 0.9405099150141643,
+      "grad_norm": 1.0608225953186365,
+      "learning_rate": 8.684520414032023e-06,
+      "loss": 0.6534,
+      "step": 83
+    },
+    {
+      "epoch": 0.9518413597733711,
+      "grad_norm": 1.0400599060401146,
+      "learning_rate": 8.639394051847472e-06,
+      "loss": 0.6351,
+      "step": 84
+    },
+    {
+      "epoch": 0.9631728045325779,
+      "grad_norm": 1.029029843151287,
+      "learning_rate": 8.593628211416964e-06,
+      "loss": 0.637,
+      "step": 85
+    },
+    {
+      "epoch": 0.9745042492917847,
+      "grad_norm": 0.9884213872615792,
+      "learning_rate": 8.547230934260313e-06,
+      "loss": 0.6414,
+      "step": 86
+    },
+    {
+      "epoch": 0.9858356940509915,
+      "grad_norm": 1.0448881569178157,
+      "learning_rate": 8.500210372847128e-06,
+      "loss": 0.6234,
+      "step": 87
+    },
+    {
+      "epoch": 0.9971671388101983,
+      "grad_norm": 1.0141851489732272,
+      "learning_rate": 8.452574789164352e-06,
+      "loss": 0.636,
+      "step": 88
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0141851489732272,
+      "learning_rate": 8.404332553264548e-06,
+      "loss": 0.6351,
+      "step": 89
+    },
+    {
+      "epoch": 1.0113314447592068,
+      "grad_norm": 2.0125074643954024,
+      "learning_rate": 8.355492141795185e-06,
+      "loss": 0.5146,
+      "step": 90
+    },
+    {
+      "epoch": 1.0226628895184136,
+      "grad_norm": 1.1306298266109818,
+      "learning_rate": 8.30606213650922e-06,
+      "loss": 0.497,
+      "step": 91
+    },
+    {
+      "epoch": 1.0339943342776203,
+      "grad_norm": 1.0714951468489908,
+      "learning_rate": 8.256051222757188e-06,
+      "loss": 0.4921,
+      "step": 92
+    },
+    {
+      "epoch": 1.045325779036827,
+      "grad_norm": 0.9830972246185706,
+      "learning_rate": 8.2054681879611e-06,
+      "loss": 0.4906,
+      "step": 93
+    },
+    {
+      "epoch": 1.056657223796034,
+      "grad_norm": 0.9632332800113752,
+      "learning_rate": 8.154321920070415e-06,
+      "loss": 0.4657,
+      "step": 94
+    },
+    {
+      "epoch": 1.0679886685552409,
+      "grad_norm": 1.193395200214797,
+      "learning_rate": 8.10262140600031e-06,
+      "loss": 0.4861,
+      "step": 95
+    },
+    {
+      "epoch": 1.0793201133144477,
+      "grad_norm": 1.28865060369019,
+      "learning_rate": 8.050375730052622e-06,
+      "loss": 0.5093,
+      "step": 96
+    },
+    {
+      "epoch": 1.0906515580736544,
+      "grad_norm": 1.247161113611643,
+      "learning_rate": 7.997594072319625e-06,
+      "loss": 0.504,
+      "step": 97
+    },
+    {
+      "epoch": 1.1019830028328612,
+      "grad_norm": 1.1321908951225559,
+      "learning_rate": 7.944285707070999e-06,
+      "loss": 0.514,
+      "step": 98
+    },
+    {
+      "epoch": 1.113314447592068,
+      "grad_norm": 1.097294675331813,
+      "learning_rate": 7.890460001124242e-06,
+      "loss": 0.5074,
+      "step": 99
+    },
+    {
+      "epoch": 1.1246458923512748,
+      "grad_norm": 1.1106766243842143,
+      "learning_rate": 7.836126412198842e-06,
+      "loss": 0.495,
+      "step": 100
+    },
+    {
+      "epoch": 1.1359773371104815,
+      "grad_norm": 1.0781028414115594,
+      "learning_rate": 7.781294487254436e-06,
+      "loss": 0.4917,
+      "step": 101
+    },
+    {
+      "epoch": 1.1473087818696883,
+      "grad_norm": 1.0597834799331805,
+      "learning_rate": 7.725973860813338e-06,
+      "loss": 0.4953,
+      "step": 102
+    },
+    {
+      "epoch": 1.158640226628895,
+      "grad_norm": 1.075317244066298,
+      "learning_rate": 7.67017425326764e-06,
+      "loss": 0.4985,
+      "step": 103
+    },
+    {
+      "epoch": 1.1699716713881019,
+      "grad_norm": 1.126814415152867,
+      "learning_rate": 7.613905469171247e-06,
+      "loss": 0.4869,
+      "step": 104
+    },
+    {
+      "epoch": 1.1813031161473089,
+      "grad_norm": 1.0228965180222989,
+      "learning_rate": 7.5571773955171124e-06,
+      "loss": 0.4956,
+      "step": 105
+    },
+    {
+      "epoch": 1.1926345609065157,
+      "grad_norm": 1.0496260656765666,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.4804,
+      "step": 106
+    },
+    {
+      "epoch": 1.2039660056657224,
+      "grad_norm": 1.057021462285616,
+      "learning_rate": 7.442383329265063e-06,
+      "loss": 0.4802,
+      "step": 107
+    },
+    {
+      "epoch": 1.2152974504249292,
+      "grad_norm": 1.0586760394529304,
+      "learning_rate": 7.3843375071425315e-06,
+      "loss": 0.4755,
+      "step": 108
+    },
+    {
+      "epoch": 1.226628895184136,
+      "grad_norm": 1.098164645835599,
+      "learning_rate": 7.32587273286887e-06,
+      "loss": 0.4806,
+      "step": 109
+    },
+    {
+      "epoch": 1.2379603399433428,
+      "grad_norm": 1.0425540537419706,
+      "learning_rate": 7.2669992792946595e-06,
+      "loss": 0.4976,
+      "step": 110
+    },
+    {
+      "epoch": 1.2492917847025495,
+      "grad_norm": 1.0081778159600596,
+      "learning_rate": 7.2077274910795605e-06,
+      "loss": 0.4775,
+      "step": 111
+    },
+    {
+      "epoch": 1.2606232294617563,
+      "grad_norm": 1.0426051895523285,
+      "learning_rate": 7.14806778287464e-06,
+      "loss": 0.4948,
+      "step": 112
+    },
+    {
+      "epoch": 1.271954674220963,
+      "grad_norm": 1.0491543765702032,
+      "learning_rate": 7.088030637492429e-06,
+      "loss": 0.5198,
+      "step": 113
+    },
+    {
+      "epoch": 1.28328611898017,
+      "grad_norm": 1.0120042186636362,
+      "learning_rate": 7.02762660406497e-06,
+      "loss": 0.5032,
+      "step": 114
+    },
+    {
+      "epoch": 1.2946175637393766,
+      "grad_norm": 1.0538656654185354,
+      "learning_rate": 6.966866296190243e-06,
+      "loss": 0.4835,
+      "step": 115
+    },
+    {
+      "epoch": 1.3059490084985836,
+      "grad_norm": 0.983675200448248,
+      "learning_rate": 6.9057603900672355e-06,
+      "loss": 0.4469,
+      "step": 116
+    },
+    {
+      "epoch": 1.3172804532577904,
+      "grad_norm": 1.1103412550285476,
+      "learning_rate": 6.844319622620039e-06,
+      "loss": 0.5124,
+      "step": 117
+    },
+    {
+      "epoch": 1.3286118980169972,
+      "grad_norm": 1.064307096238654,
+      "learning_rate": 6.782554789611256e-06,
+      "loss": 0.4943,
+      "step": 118
+    },
+    {
+      "epoch": 1.339943342776204,
+      "grad_norm": 1.0325281954877101,
+      "learning_rate": 6.7204767437450725e-06,
+      "loss": 0.4703,
+      "step": 119
+    },
+    {
+      "epoch": 1.3512747875354107,
+      "grad_norm": 1.0365628583864628,
+      "learning_rate": 6.65809639276034e-06,
+      "loss": 0.494,
+      "step": 120
+    },
+    {
+      "epoch": 1.3626062322946175,
+      "grad_norm": 1.0482388627399757,
+      "learning_rate": 6.595424697513963e-06,
+      "loss": 0.4502,
+      "step": 121
+    },
+    {
+      "epoch": 1.3739376770538243,
+      "grad_norm": 1.0272064142818405,
+      "learning_rate": 6.532472670054975e-06,
+      "loss": 0.492,
+      "step": 122
+    },
+    {
+      "epoch": 1.385269121813031,
+      "grad_norm": 1.0810272879082132,
+      "learning_rate": 6.469251371689606e-06,
+      "loss": 0.4847,
+      "step": 123
+    },
+    {
+      "epoch": 1.3966005665722379,
+      "grad_norm": 1.0366197600921454,
+      "learning_rate": 6.405771911037698e-06,
+      "loss": 0.4999,
+      "step": 124
+    },
+    {
+      "epoch": 1.4079320113314449,
+      "grad_norm": 1.0295069364200777,
+      "learning_rate": 6.342045442080818e-06,
+      "loss": 0.4783,
+      "step": 125
+    },
+    {
+      "epoch": 1.4192634560906516,
+      "grad_norm": 1.0528763013327969,
+      "learning_rate": 6.278083162202374e-06,
+      "loss": 0.4846,
+      "step": 126
+    },
+    {
+      "epoch": 1.4305949008498584,
+      "grad_norm": 1.0734593139015471,
+      "learning_rate": 6.21389631022014e-06,
+      "loss": 0.5134,
+      "step": 127
+    },
+    {
+      "epoch": 1.4419263456090652,
+      "grad_norm": 1.0207282551843653,
+      "learning_rate": 6.1494961644114685e-06,
+      "loss": 0.4855,
+      "step": 128
+    },
+    {
+      "epoch": 1.453257790368272,
+      "grad_norm": 0.9713494112903828,
+      "learning_rate": 6.084894040531591e-06,
+      "loss": 0.4667,
+      "step": 129
+    },
+    {
+      "epoch": 1.4645892351274787,
+      "grad_norm": 1.1036048289558185,
+      "learning_rate": 6.0201012898253244e-06,
+      "loss": 0.4905,
+      "step": 130
+    },
+    {
+      "epoch": 1.4759206798866855,
+      "grad_norm": 0.996202225854195,
+      "learning_rate": 5.9551292970325394e-06,
+      "loss": 0.4746,
+      "step": 131
+    },
+    {
+      "epoch": 1.4872521246458923,
+      "grad_norm": 1.0919133151119662,
+      "learning_rate": 5.8899894783877536e-06,
+      "loss": 0.5201,
+      "step": 132
+    },
+    {
+      "epoch": 1.498583569405099,
+      "grad_norm": 1.11280141387768,
+      "learning_rate": 5.824693279614171e-06,
+      "loss": 0.4953,
+      "step": 133
+    },
+    {
+      "epoch": 1.509915014164306,
+      "grad_norm": 1.1163217052046956,
+      "learning_rate": 5.759252173912573e-06,
+      "loss": 0.481,
+      "step": 134
+    },
+    {
+      "epoch": 1.5212464589235126,
+      "grad_norm": 1.0688323988028812,
+      "learning_rate": 5.693677659945343e-06,
+      "loss": 0.4711,
+      "step": 135
+    },
+    {
+      "epoch": 1.5325779036827196,
+      "grad_norm": 0.9512892167994508,
+      "learning_rate": 5.627981259816041e-06,
+      "loss": 0.4697,
+      "step": 136
+    },
+    {
+      "epoch": 1.5439093484419264,
+      "grad_norm": 1.0157798339830766,
+      "learning_rate": 5.562174517044862e-06,
+      "loss": 0.4728,
+      "step": 137
+    },
+    {
+      "epoch": 1.5552407932011332,
+      "grad_norm": 0.9982778169224142,
+      "learning_rate": 5.496268994540309e-06,
+      "loss": 0.453,
+      "step": 138
+    },
+    {
+      "epoch": 1.56657223796034,
+      "grad_norm": 1.1297738773397445,
+      "learning_rate": 5.430276272567485e-06,
+      "loss": 0.495,
+      "step": 139
+    },
+    {
+      "epoch": 1.5779036827195467,
+      "grad_norm": 1.0139903899310507,
+      "learning_rate": 5.364207946713318e-06,
+      "loss": 0.4844,
+      "step": 140
+    },
+    {
+      "epoch": 1.5892351274787535,
+      "grad_norm": 0.9490126458491319,
+      "learning_rate": 5.2980756258491e-06,
+      "loss": 0.4632,
+      "step": 141
+    },
+    {
+      "epoch": 1.6005665722379603,
+      "grad_norm": 0.9789924111916612,
+      "learning_rate": 5.231890930090692e-06,
+      "loss": 0.4641,
+      "step": 142
+    },
+    {
+      "epoch": 1.6118980169971673,
+      "grad_norm": 1.0001930502458516,
+      "learning_rate": 5.165665488756755e-06,
+      "loss": 0.4511,
+      "step": 143
+    },
+    {
+      "epoch": 1.6232294617563738,
+      "grad_norm": 1.0412278168604834,
+      "learning_rate": 5.099410938325351e-06,
+      "loss": 0.4813,
+      "step": 144
+    },
+    {
+      "epoch": 1.6345609065155808,
+      "grad_norm": 2.990945647537025,
+      "learning_rate": 5.033138920389313e-06,
+      "loss": 0.4949,
+      "step": 145
+    },
+    {
+      "epoch": 1.6458923512747874,
+      "grad_norm": 0.9622418163601026,
+      "learning_rate": 4.966861079610688e-06,
+      "loss": 0.4855,
+      "step": 146
+    },
+    {
+      "epoch": 1.6572237960339944,
+      "grad_norm": 1.0030167678640822,
+      "learning_rate": 4.900589061674649e-06,
+      "loss": 0.4589,
+      "step": 147
+    },
+    {
+      "epoch": 1.6685552407932012,
+      "grad_norm": 1.0109166766299091,
+      "learning_rate": 4.8343345112432475e-06,
+      "loss": 0.4778,
+      "step": 148
+    },
+    {
+      "epoch": 1.679886685552408,
+      "grad_norm": 1.0402771028968805,
+      "learning_rate": 4.7681090699093076e-06,
+      "loss": 0.4874,
+      "step": 149
+    },
+    {
+      "epoch": 1.6912181303116147,
+      "grad_norm": 1.0333160217244122,
+      "learning_rate": 4.701924374150901e-06,
+      "loss": 0.469,
+      "step": 150
+    },
+    {
+      "epoch": 1.7025495750708215,
+      "grad_norm": 1.0264878278726923,
+      "learning_rate": 4.635792053286682e-06,
+      "loss": 0.477,
+      "step": 151
+    },
+    {
+      "epoch": 1.7138810198300283,
+      "grad_norm": 0.9806277129349131,
+      "learning_rate": 4.569723727432517e-06,
+      "loss": 0.4609,
+      "step": 152
+    },
+    {
+      "epoch": 1.725212464589235,
+      "grad_norm": 1.0430109649067774,
+      "learning_rate": 4.5037310054596936e-06,
+      "loss": 0.4852,
+      "step": 153
+    },
+    {
+      "epoch": 1.736543909348442,
+      "grad_norm": 1.0177412955604808,
+      "learning_rate": 4.43782548295514e-06,
+      "loss": 0.4538,
+      "step": 154
+    },
+    {
+      "epoch": 1.7478753541076486,
+      "grad_norm": 1.0742221754801993,
+      "learning_rate": 4.372018740183961e-06,
+      "loss": 0.502,
+      "step": 155
+    },
+    {
+      "epoch": 1.7592067988668556,
+      "grad_norm": 1.2114594760413002,
+      "learning_rate": 4.30632234005466e-06,
+      "loss": 0.4626,
+      "step": 156
+    },
+    {
+      "epoch": 1.7705382436260622,
+      "grad_norm": 1.0105219104936058,
+      "learning_rate": 4.2407478260874294e-06,
+      "loss": 0.4443,
+      "step": 157
+    },
+    {
+      "epoch": 1.7818696883852692,
+      "grad_norm": 1.0676939421912321,
+      "learning_rate": 4.175306720385831e-06,
+      "loss": 0.461,
+      "step": 158
+    },
+    {
+      "epoch": 1.793201133144476,
+      "grad_norm": 1.0843360976121068,
+      "learning_rate": 4.11001052161225e-06,
+      "loss": 0.4562,
+      "step": 159
+    },
+    {
+      "epoch": 1.8045325779036827,
+      "grad_norm": 1.0182445190909426,
+      "learning_rate": 4.044870702967461e-06,
+      "loss": 0.4597,
+      "step": 160
+    },
+    {
+      "epoch": 1.8158640226628895,
+      "grad_norm": 1.0266398146802735,
+      "learning_rate": 3.979898710174678e-06,
+      "loss": 0.4737,
+      "step": 161
+    },
+    {
+      "epoch": 1.8271954674220963,
+      "grad_norm": 1.0375307407230006,
+      "learning_rate": 3.91510595946841e-06,
+      "loss": 0.476,
+      "step": 162
+    },
+    {
+      "epoch": 1.8385269121813033,
+      "grad_norm": 1.0510195116895713,
+      "learning_rate": 3.850503835588533e-06,
+      "loss": 0.4572,
+      "step": 163
+    },
+    {
+      "epoch": 1.8498583569405098,
+      "grad_norm": 1.0707576258473916,
+      "learning_rate": 3.786103689779861e-06,
+      "loss": 0.4855,
+      "step": 164
+    },
+    {
+      "epoch": 1.8611898016997168,
+      "grad_norm": 1.109879197789788,
+      "learning_rate": 3.721916837797627e-06,
+      "loss": 0.4744,
+      "step": 165
+    },
+    {
+      "epoch": 1.8725212464589234,
+      "grad_norm": 0.9430434127126872,
+      "learning_rate": 3.6579545579191834e-06,
+      "loss": 0.5036,
+      "step": 166
+    },
+    {
+      "epoch": 1.8838526912181304,
+      "grad_norm": 1.0454617136926816,
+      "learning_rate": 3.5942280889623028e-06,
+      "loss": 0.4757,
+      "step": 167
+    },
+    {
+      "epoch": 1.8951841359773371,
+      "grad_norm": 0.9669993221473043,
+      "learning_rate": 3.5307486283103966e-06,
+      "loss": 0.4939,
+      "step": 168
+    },
+    {
+      "epoch": 1.906515580736544,
+      "grad_norm": 1.1489596332179548,
+      "learning_rate": 3.4675273299450264e-06,
+      "loss": 0.4875,
+      "step": 169
+    },
+    {
+      "epoch": 1.9178470254957507,
+      "grad_norm": 1.236638321882873,
+      "learning_rate": 3.4045753024860393e-06,
+      "loss": 0.4899,
+      "step": 170
+    },
+    {
+      "epoch": 1.9291784702549575,
+      "grad_norm": 1.0015067232304347,
+      "learning_rate": 3.3419036072396614e-06,
+      "loss": 0.4367,
+      "step": 171
+    },
+    {
+      "epoch": 1.9405099150141643,
+      "grad_norm": 0.991139662986458,
+      "learning_rate": 3.2795232562549296e-06,
+      "loss": 0.4593,
+      "step": 172
+    },
+    {
+      "epoch": 1.951841359773371,
+      "grad_norm": 1.0171228373147831,
+      "learning_rate": 3.2174452103887455e-06,
+      "loss": 0.4864,
+      "step": 173
+    },
+    {
+      "epoch": 1.963172804532578,
+      "grad_norm": 1.0183503025841374,
+      "learning_rate": 3.1556803773799616e-06,
+      "loss": 0.4775,
+      "step": 174
+    },
+    {
+      "epoch": 1.9745042492917846,
+      "grad_norm": 0.9658158834425475,
+      "learning_rate": 3.0942396099327645e-06,
+      "loss": 0.4628,
+      "step": 175
+    },
+    {
+      "epoch": 1.9858356940509916,
+      "grad_norm": 1.0046391704473616,
+      "learning_rate": 3.03313370380976e-06,
+      "loss": 0.4945,
+      "step": 176
+    },
+    {
+      "epoch": 1.9971671388101981,
+      "grad_norm": 0.9746868290860945,
+      "learning_rate": 2.972373395935031e-06,
+      "loss": 0.4384,
+      "step": 177
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9746868290860945,
+      "learning_rate": 2.911969362507574e-06,
+      "loss": 0.4562,
+      "step": 178
+    },
+    {
+      "epoch": 2.011331444759207,
+      "grad_norm": 2.1634786845934584,
+      "learning_rate": 2.8519322171253605e-06,
+      "loss": 0.3576,
+      "step": 179
+    },
+    {
+      "epoch": 2.0226628895184136,
+      "grad_norm": 1.259167809122465,
+      "learning_rate": 2.792272508920443e-06,
+      "loss": 0.3306,
+      "step": 180
+    },
+    {
+      "epoch": 2.0339943342776206,
+      "grad_norm": 1.3388873888110011,
+      "learning_rate": 2.7330007207053413e-06,
+      "loss": 0.353,
+      "step": 181
+    },
+    {
+      "epoch": 2.045325779036827,
+      "grad_norm": 1.1581849151502048,
+      "learning_rate": 2.674127267131131e-06,
+      "loss": 0.3317,
+      "step": 182
+    },
+    {
+      "epoch": 2.056657223796034,
+      "grad_norm": 1.0160032268336192,
+      "learning_rate": 2.615662492857471e-06,
+      "loss": 0.3581,
+      "step": 183
+    },
+    {
+      "epoch": 2.0679886685552407,
+      "grad_norm": 1.0233678646861728,
+      "learning_rate": 2.5576166707349387e-06,
+      "loss": 0.3359,
+      "step": 184
+    },
+    {
+      "epoch": 2.0793201133144477,
+      "grad_norm": 1.0874679159300038,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.3219,
+      "step": 185
+    },
+    {
+      "epoch": 2.090651558073654,
+      "grad_norm": 1.2469998353736902,
+      "learning_rate": 2.4428226044828896e-06,
+      "loss": 0.3271,
+      "step": 186
+    },
+    {
+      "epoch": 2.101983002832861,
+      "grad_norm": 1.1847806975199535,
+      "learning_rate": 2.3860945308287554e-06,
+      "loss": 0.3429,
+      "step": 187
+    },
+    {
+      "epoch": 2.113314447592068,
+      "grad_norm": 1.3829661881977866,
+      "learning_rate": 2.3298257467323605e-06,
+      "loss": 0.3492,
+      "step": 188
+    },
+    {
+      "epoch": 2.1246458923512748,
+      "grad_norm": 1.1118666347289263,
+      "learning_rate": 2.2740261391866634e-06,
+      "loss": 0.3343,
+      "step": 189
+    },
+    {
+      "epoch": 2.1359773371104818,
+      "grad_norm": 1.1295786044065697,
+      "learning_rate": 2.2187055127455653e-06,
+      "loss": 0.3306,
+      "step": 190
+    },
+    {
+      "epoch": 2.1473087818696883,
+      "grad_norm": 1.3950194361496737,
+      "learning_rate": 2.1638735878011603e-06,
+      "loss": 0.3515,
+      "step": 191
+    },
+    {
+      "epoch": 2.1586402266288953,
+      "grad_norm": 1.1337210762125438,
+      "learning_rate": 2.1095399988757574e-06,
+      "loss": 0.3201,
+      "step": 192
+    },
+    {
+      "epoch": 2.169971671388102,
+      "grad_norm": 1.059433716116878,
+      "learning_rate": 2.0557142929290027e-06,
+      "loss": 0.3526,
+      "step": 193
+    },
+    {
+      "epoch": 2.181303116147309,
+      "grad_norm": 1.0876920114742847,
+      "learning_rate": 2.0024059276803742e-06,
+      "loss": 0.3275,
+      "step": 194
+    },
+    {
+      "epoch": 2.1926345609065154,
+      "grad_norm": 1.136528776323311,
+      "learning_rate": 1.949624269947378e-06,
+      "loss": 0.3499,
+      "step": 195
+    },
+    {
+      "epoch": 2.2039660056657224,
+      "grad_norm": 1.1195654060494844,
+      "learning_rate": 1.897378593999693e-06,
+      "loss": 0.3105,
+      "step": 196
+    },
+    {
+      "epoch": 2.215297450424929,
+      "grad_norm": 1.0686107201673802,
+      "learning_rate": 1.8456780799295888e-06,
+      "loss": 0.3409,
+      "step": 197
+    },
+    {
+      "epoch": 2.226628895184136,
+      "grad_norm": 1.1176135978118285,
+      "learning_rate": 1.794531812038901e-06,
+      "loss": 0.3242,
+      "step": 198
+    },
+    {
+      "epoch": 2.237960339943343,
+      "grad_norm": 1.1225522593354427,
+      "learning_rate": 1.7439487772428142e-06,
+      "loss": 0.3331,
+      "step": 199
+    },
+    {
+      "epoch": 2.2492917847025495,
+      "grad_norm": 1.0504526826797216,
+      "learning_rate": 1.6939378634907815e-06,
+      "loss": 0.3223,
+      "step": 200
+    },
+    {
+      "epoch": 2.2606232294617565,
+      "grad_norm": 1.0112717450368687,
+      "learning_rate": 1.6445078582048158e-06,
+      "loss": 0.3328,
+      "step": 201
+    },
+    {
+      "epoch": 2.271954674220963,
+      "grad_norm": 1.0056815807805697,
+      "learning_rate": 1.5956674467354538e-06,
+      "loss": 0.3349,
+      "step": 202
+    },
+    {
+      "epoch": 2.28328611898017,
+      "grad_norm": 1.0324761445382153,
+      "learning_rate": 1.5474252108356475e-06,
+      "loss": 0.3147,
+      "step": 203
+    },
+    {
+      "epoch": 2.2946175637393766,
+      "grad_norm": 3.0756191856725437,
+      "learning_rate": 1.499789627152874e-06,
+      "loss": 0.3148,
+      "step": 204
+    },
+    {
+      "epoch": 2.3059490084985836,
+      "grad_norm": 1.14933836933374,
+      "learning_rate": 1.452769065739688e-06,
+      "loss": 0.3487,
+      "step": 205
+    },
+    {
+      "epoch": 2.31728045325779,
+      "grad_norm": 0.9691075451255097,
+      "learning_rate": 1.4063717885830375e-06,
+      "loss": 0.3216,
+      "step": 206
+    },
+    {
+      "epoch": 2.328611898016997,
+      "grad_norm": 1.2745727227347767,
+      "learning_rate": 1.3606059481525296e-06,
+      "loss": 0.3585,
+      "step": 207
+    },
+    {
+      "epoch": 2.3399433427762037,
+      "grad_norm": 0.9868916262509804,
+      "learning_rate": 1.3154795859679781e-06,
+      "loss": 0.3416,
+      "step": 208
+    },
+    {
+      "epoch": 2.3512747875354107,
+      "grad_norm": 1.029329657926381,
+      "learning_rate": 1.2710006311864104e-06,
+      "loss": 0.3438,
+      "step": 209
+    },
+    {
+      "epoch": 2.3626062322946177,
+      "grad_norm": 1.2301937202365874,
+      "learning_rate": 1.227176899208849e-06,
+      "loss": 0.3232,
+      "step": 210
+    },
+    {
+      "epoch": 2.3739376770538243,
+      "grad_norm": 1.1079694734813215,
+      "learning_rate": 1.1840160903070591e-06,
+      "loss": 0.3533,
+      "step": 211
+    },
+    {
+      "epoch": 2.3852691218130313,
+      "grad_norm": 1.0355467829487406,
+      "learning_rate": 1.141525788270531e-06,
+      "loss": 0.3455,
+      "step": 212
+    },
+    {
+      "epoch": 2.396600566572238,
+      "grad_norm": 1.0285862271263877,
+      "learning_rate": 1.09971345907394e-06,
+      "loss": 0.2994,
+      "step": 213
+    },
+    {
+      "epoch": 2.407932011331445,
+      "grad_norm": 1.0633893519411577,
+      "learning_rate": 1.0585864495652899e-06,
+      "loss": 0.3386,
+      "step": 214
+    },
+    {
+      "epoch": 2.4192634560906514,
+      "grad_norm": 0.985097331489618,
+      "learning_rate": 1.0181519861750078e-06,
+      "loss": 0.3181,
+      "step": 215
+    },
+    {
+      "epoch": 2.4305949008498584,
+      "grad_norm": 0.951413780263271,
+      "learning_rate": 9.784171736461762e-07,
+      "loss": 0.3105,
+      "step": 216
+    },
+    {
+      "epoch": 2.441926345609065,
+      "grad_norm": 1.0282273427987358,
+      "learning_rate": 9.393889937861694e-07,
+      "loss": 0.3179,
+      "step": 217
+    },
+    {
+      "epoch": 2.453257790368272,
+      "grad_norm": 1.026529941608791,
+      "learning_rate": 9.010743042398684e-07,
+      "loss": 0.3234,
+      "step": 218
+    },
+    {
+      "epoch": 2.4645892351274785,
+      "grad_norm": 1.0299442438320148,
+      "learning_rate": 8.634798372847148e-07,
+      "loss": 0.335,
+      "step": 219
+    },
+    {
+      "epoch": 2.4759206798866855,
+      "grad_norm": 0.9309231031132973,
+      "learning_rate": 8.266121986477699e-07,
+      "loss": 0.318,
+      "step": 220
+    },
+    {
+      "epoch": 2.4872521246458925,
+      "grad_norm": 1.0062159661580126,
+      "learning_rate": 7.904778663450325e-07,
+      "loss": 0.3292,
+      "step": 221
+    },
+    {
+      "epoch": 2.498583569405099,
+      "grad_norm": 1.0354919361102888,
+      "learning_rate": 7.550831895431799e-07,
+      "loss": 0.3266,
+      "step": 222
+    },
+    {
+      "epoch": 2.509915014164306,
+      "grad_norm": 0.9693415538045153,
+      "learning_rate": 7.204343874439578e-07,
+      "loss": 0.3282,
+      "step": 223
+    },
+    {
+      "epoch": 2.5212464589235126,
+      "grad_norm": 1.0178821797615285,
+      "learning_rate": 6.865375481914017e-07,
+      "loss": 0.3561,
+      "step": 224
+    },
+    {
+      "epoch": 2.5325779036827196,
+      "grad_norm": 1.0271091771586642,
+      "learning_rate": 6.533986278020876e-07,
+      "loss": 0.3064,
+      "step": 225
+    },
+    {
+      "epoch": 2.543909348441926,
+      "grad_norm": 0.9930205073186488,
+      "learning_rate": 6.210234491186079e-07,
+      "loss": 0.318,
+      "step": 226
+    },
+    {
+      "epoch": 2.555240793201133,
+      "grad_norm": 1.015466323155115,
+      "learning_rate": 5.894177007864272e-07,
+      "loss": 0.3408,
+      "step": 227
+    },
+    {
+      "epoch": 2.56657223796034,
+      "grad_norm": 1.065785552873228,
+      "learning_rate": 5.585869362543416e-07,
+      "loss": 0.3414,
+      "step": 228
+    },
+    {
+      "epoch": 2.5779036827195467,
+      "grad_norm": 1.0524927446179813,
+      "learning_rate": 5.285365727986708e-07,
+      "loss": 0.3422,
+      "step": 229
+    },
+    {
+      "epoch": 2.5892351274787533,
+      "grad_norm": 1.0219196548167786,
+      "learning_rate": 4.992718905713967e-07,
+      "loss": 0.3388,
+      "step": 230
+    },
+    {
+      "epoch": 2.6005665722379603,
+      "grad_norm": 0.9679912813387603,
+      "learning_rate": 4.707980316723837e-07,
+      "loss": 0.3165,
+      "step": 231
+    },
+    {
+      "epoch": 2.6118980169971673,
+      "grad_norm": 0.9893500327460035,
+      "learning_rate": 4.431199992458607e-07,
+      "loss": 0.3238,
+      "step": 232
+    },
+    {
+      "epoch": 2.623229461756374,
+      "grad_norm": 0.9876579686339385,
+      "learning_rate": 4.16242656601315e-07,
+      "loss": 0.308,
+      "step": 233
+    },
+    {
+      "epoch": 2.634560906515581,
+      "grad_norm": 1.01213916356771,
+      "learning_rate": 3.9017072635896716e-07,
+      "loss": 0.331,
+      "step": 234
+    },
+    {
+      "epoch": 2.6458923512747874,
+      "grad_norm": 1.0151577294613559,
+      "learning_rate": 3.649087896199488e-07,
+      "loss": 0.3098,
+      "step": 235
+    },
+    {
+      "epoch": 2.6572237960339944,
+      "grad_norm": 0.9854787297770221,
+      "learning_rate": 3.404612851613676e-07,
+      "loss": 0.3202,
+      "step": 236
+    },
+    {
+      "epoch": 2.668555240793201,
+      "grad_norm": 2.5197939583747866,
+      "learning_rate": 3.168325086563612e-07,
+      "loss": 0.3302,
+      "step": 237
+    },
+    {
+      "epoch": 2.679886685552408,
+      "grad_norm": 0.9681009670329549,
+      "learning_rate": 2.9402661191930803e-07,
+      "loss": 0.3221,
+      "step": 238
+    },
+    {
+      "epoch": 2.691218130311615,
+      "grad_norm": 1.0155833734622453,
+      "learning_rate": 2.7204760217631074e-07,
+      "loss": 0.324,
+      "step": 239
+    },
+    {
+      "epoch": 2.7025495750708215,
+      "grad_norm": 1.1931982505904983,
+      "learning_rate": 2.5089934136108665e-07,
+      "loss": 0.3327,
+      "step": 240
+    },
+    {
+      "epoch": 2.713881019830028,
+      "grad_norm": 0.9735860788683143,
+      "learning_rate": 2.30585545436387e-07,
+      "loss": 0.3483,
+      "step": 241
+    },
+    {
+      "epoch": 2.725212464589235,
+      "grad_norm": 0.9628214952166717,
+      "learning_rate": 2.1110978374106195e-07,
+      "loss": 0.3455,
+      "step": 242
+    },
+    {
+      "epoch": 2.736543909348442,
+      "grad_norm": 1.4367674984114238,
+      "learning_rate": 1.9247547836289792e-07,
+      "loss": 0.3565,
+      "step": 243
+    },
+    {
+      "epoch": 2.7478753541076486,
+      "grad_norm": 1.0738794442822241,
+      "learning_rate": 1.7468590353731495e-07,
+      "loss": 0.3577,
+      "step": 244
+    },
+    {
+      "epoch": 2.7592067988668556,
+      "grad_norm": 1.0163993435166494,
+      "learning_rate": 1.577441850720568e-07,
+      "loss": 0.3346,
+      "step": 245
+    },
+    {
+      "epoch": 2.770538243626062,
+      "grad_norm": 1.1268283470669345,
+      "learning_rate": 1.4165329979794972e-07,
+      "loss": 0.3204,
+      "step": 246
+    },
+    {
+      "epoch": 2.781869688385269,
+      "grad_norm": 1.00412302366148,
+      "learning_rate": 1.264160750458493e-07,
+      "loss": 0.3091,
+      "step": 247
+    },
+    {
+      "epoch": 2.7932011331444757,
+      "grad_norm": 1.0878323463224275,
+      "learning_rate": 1.1203518814984216e-07,
+      "loss": 0.3219,
+      "step": 248
+    },
+    {
+      "epoch": 2.8045325779036827,
+      "grad_norm": 1.0326844241286977,
+      "learning_rate": 9.851316597681959e-08,
+      "loss": 0.3407,
+      "step": 249
+    },
+    {
+      "epoch": 2.8158640226628897,
+      "grad_norm": 1.0488660487318535,
+      "learning_rate": 8.585238448247434e-08,
+      "loss": 0.3066,
+      "step": 250
+    },
+    {
+      "epoch": 2.8271954674220963,
+      "grad_norm": 0.9440222402450956,
+      "learning_rate": 7.405506829382736e-08,
+      "loss": 0.3007,
+      "step": 251
+    },
+    {
+      "epoch": 2.8385269121813033,
+      "grad_norm": 0.9992965787158642,
+      "learning_rate": 6.31232903183332e-08,
+      "loss": 0.3211,
+      "step": 252
+    },
+    {
+      "epoch": 2.84985835694051,
+      "grad_norm": 1.0525889142182898,
+      "learning_rate": 5.305897137965199e-08,
+      "loss": 0.3339,
+      "step": 253
+    },
+    {
+      "epoch": 2.861189801699717,
+      "grad_norm": 1.0406232501867803,
+      "learning_rate": 4.3863879880142737e-08,
+      "loss": 0.3188,
+      "step": 254
+    },
+    {
+      "epoch": 2.8725212464589234,
+      "grad_norm": 1.0108504238438418,
+      "learning_rate": 3.553963149013295e-08,
+      "loss": 0.3426,
+      "step": 255
+    },
+    {
+      "epoch": 2.8838526912181304,
+      "grad_norm": 1.040975846702501,
+      "learning_rate": 2.8087688864033014e-08,
+      "loss": 0.3365,
+      "step": 256
+    },
+    {
+      "epoch": 2.8951841359773374,
+      "grad_norm": 1.0279134406587973,
+      "learning_rate": 2.1509361383330597e-08,
+      "loss": 0.3167,
+      "step": 257
+    },
+    {
+      "epoch": 2.906515580736544,
+      "grad_norm": 1.0127896976081647,
+      "learning_rate": 1.580580492652084e-08,
+      "loss": 0.3589,
+      "step": 258
+    },
+    {
+      "epoch": 2.9178470254957505,
+      "grad_norm": 1.002944001928922,
+      "learning_rate": 1.0978021666005479e-08,
+      "loss": 0.3382,
+      "step": 259
+    },
+    {
+      "epoch": 2.9291784702549575,
+      "grad_norm": 0.9936405641782646,
+      "learning_rate": 7.02685989200258e-09,
+      "loss": 0.3373,
+      "step": 260
+    },
+    {
+      "epoch": 2.9405099150141645,
+      "grad_norm": 1.0916598818224916,
+      "learning_rate": 3.953013863490784e-09,
+      "loss": 0.3124,
+      "step": 261
+    },
+    {
+      "epoch": 2.951841359773371,
+      "grad_norm": 0.9881063904383428,
+      "learning_rate": 1.757023686224102e-09,
+      "loss": 0.3401,
+      "step": 262
+    },
+    {
+      "epoch": 2.963172804532578,
+      "grad_norm": 0.9953124861905701,
+      "learning_rate": 4.392752178278281e-10,
+      "loss": 0.3202,
+      "step": 263
+    },
+    {
+      "epoch": 2.9745042492917846,
+      "grad_norm": 0.9957928075882635,
+      "learning_rate": 0.0,
+      "loss": 0.299,
+      "step": 264
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 264,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 72196646453248.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54bdcea5faf903f385e1a2816e3bc831afb44dd0c605e3eef9f94d96b9d385f
+size 7608