Upload folder using huggingface_hub

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "kaizen9/regu25k_atnfrz25k",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1cc906242eb4786df6609e0d420676f03af563d617dd0df3fefec297af06ed
+size 4981252848

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc9b70e2bb7837a834b27a9b363a0159da5c335ea1fde94912aa1a6daffe190
+size 726720104

model.safetensors.index.json

@@ -0,0 +1,345 @@
+{
+  "metadata": {
+    "total_size": 5707934720
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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 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 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": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1218 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001,
+      "grad_norm": 0.4723578691482544,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 15.0023,
+      "loss/crossentropy": 2.8106061220169067,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15208163857460022,
+      "loss/reg": 14.850236892700195,
+      "step": 1
+    },
+    {
+      "epoch": 0.002,
+      "grad_norm": 0.3746773898601532,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 14.8245,
+      "loss/crossentropy": 2.88076388835907,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13159187883138657,
+      "loss/reg": 14.692875862121582,
+      "step": 2
+    },
+    {
+      "epoch": 0.003,
+      "grad_norm": 0.39371100068092346,
+      "learning_rate": 1.5e-06,
+      "loss": 14.6298,
+      "loss/crossentropy": 2.8186020851135254,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13105076551437378,
+      "loss/reg": 14.4987154006958,
+      "step": 3
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 0.4312513470649719,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 14.4644,
+      "loss/crossentropy": 2.561935782432556,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15662836283445358,
+      "loss/reg": 14.307746887207031,
+      "step": 4
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 0.5712147951126099,
+      "learning_rate": 2.5e-06,
+      "loss": 14.2884,
+      "loss/crossentropy": 2.6744261980056763,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16902200877666473,
+      "loss/reg": 14.119378089904785,
+      "step": 5
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 0.4991922080516815,
+      "learning_rate": 3e-06,
+      "loss": 14.0796,
+      "loss/crossentropy": 2.541142702102661,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14546513557434082,
+      "loss/reg": 13.934137344360352,
+      "step": 6
+    },
+    {
+      "epoch": 0.007,
+      "grad_norm": 0.394466370344162,
+      "learning_rate": 3.5000000000000004e-06,
+      "loss": 13.8978,
+      "loss/crossentropy": 2.863157868385315,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14624819159507751,
+      "loss/reg": 13.751592636108398,
+      "step": 7
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.5288362503051758,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 13.7514,
+      "loss/crossentropy": 2.53192400932312,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.17936921864748,
+      "loss/reg": 13.571989059448242,
+      "step": 8
+    },
+    {
+      "epoch": 0.009,
+      "grad_norm": 0.3661612570285797,
+      "learning_rate": 4.5e-06,
+      "loss": 13.5249,
+      "loss/crossentropy": 2.6582940816879272,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13002116978168488,
+      "loss/reg": 13.39488697052002,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.37344738841056824,
+      "learning_rate": 5e-06,
+      "loss": 13.3611,
+      "loss/crossentropy": 2.8080869913101196,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1404452547430992,
+      "loss/reg": 13.220650672912598,
+      "step": 10
+    },
+    {
+      "epoch": 0.011,
+      "grad_norm": 0.47446200251579285,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 13.2185,
+      "loss/crossentropy": 2.7942490577697754,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16937557607889175,
+      "loss/reg": 13.049126625061035,
+      "step": 11
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 0.41823914647102356,
+      "learning_rate": 6e-06,
+      "loss": 13.0431,
+      "loss/crossentropy": 2.7883923053741455,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16317125409841537,
+      "loss/reg": 12.879945755004883,
+      "step": 12
+    },
+    {
+      "epoch": 0.013,
+      "grad_norm": 0.3810077905654907,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 12.8458,
+      "loss/crossentropy": 2.5887070894241333,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13234061002731323,
+      "loss/reg": 12.713478088378906,
+      "step": 13
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 0.861165463924408,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 12.7646,
+      "loss/crossentropy": 3.0489625930786133,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.2151956632733345,
+      "loss/reg": 12.549367904663086,
+      "step": 14
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 0.3999025225639343,
+      "learning_rate": 7.5e-06,
+      "loss": 12.5428,
+      "loss/crossentropy": 2.6218740940093994,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15504448860883713,
+      "loss/reg": 12.38780403137207,
+      "step": 15
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.3485129177570343,
+      "grad_norm_var": 0.015782494207215392,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 12.3624,
+      "loss/crossentropy": 2.704634428024292,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1335841417312622,
+      "loss/reg": 12.228797912597656,
+      "step": 16
+    },
+    {
+      "epoch": 0.017,
+      "grad_norm": 0.394564151763916,
+      "grad_norm_var": 0.015986270113443057,
+      "learning_rate": 8.500000000000002e-06,
+      "loss": 12.2458,
+      "loss/crossentropy": 2.6254637241363525,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.17384596914052963,
+      "loss/reg": 12.071925163269043,
+      "step": 17
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 0.359417200088501,
+      "grad_norm_var": 0.016155457953818328,
+      "learning_rate": 9e-06,
+      "loss": 12.0449,
+      "loss/crossentropy": 2.6955989599227905,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.12739497795701027,
+      "loss/reg": 11.917520523071289,
+      "step": 18
+    },
+    {
+      "epoch": 0.019,
+      "grad_norm": 0.4362143278121948,
+      "grad_norm_var": 0.01595094581098607,
+      "learning_rate": 9.5e-06,
+      "loss": 11.9337,
+      "loss/crossentropy": 2.6590176820755005,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16834121942520142,
+      "loss/reg": 11.765388488769531,
+      "step": 19
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.3776922821998596,
+      "grad_norm_var": 0.01628110467363616,
+      "learning_rate": 1e-05,
+      "loss": 11.7405,
+      "loss/crossentropy": 2.9381775856018066,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.12479494512081146,
+      "loss/reg": 11.615675926208496,
+      "step": 20
+    },
+    {
+      "epoch": 0.021,
+      "grad_norm": 0.3638933598995209,
+      "grad_norm_var": 0.01558998159507059,
+      "learning_rate": 1.05e-05,
+      "loss": 11.5966,
+      "loss/crossentropy": 2.737419009208679,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.12864574417471886,
+      "loss/reg": 11.467905044555664,
+      "step": 21
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 0.3599083125591278,
+      "grad_norm_var": 0.01563029096619477,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 11.4504,
+      "loss/crossentropy": 2.680889368057251,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1280709058046341,
+      "loss/reg": 11.322328567504883,
+      "step": 22
+    },
+    {
+      "epoch": 0.023,
+      "grad_norm": 0.5118765830993652,
+      "grad_norm_var": 0.015976795681526535,
+      "learning_rate": 1.1500000000000002e-05,
+      "loss": 11.3452,
+      "loss/crossentropy": 2.6692968606948853,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16634425520896912,
+      "loss/reg": 11.178874969482422,
+      "step": 23
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 0.3334847688674927,
+      "grad_norm_var": 0.015910143486327633,
+      "learning_rate": 1.2e-05,
+      "loss": 11.1616,
+      "loss/crossentropy": 2.7403935194015503,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.12420090287923813,
+      "loss/reg": 11.037442207336426,
+      "step": 24
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.3828985095024109,
+      "grad_norm_var": 0.015801931574252005,
+      "learning_rate": 1.25e-05,
+      "loss": 11.0467,
+      "loss/crossentropy": 2.796410322189331,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14872785657644272,
+      "loss/reg": 10.897927284240723,
+      "step": 25
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 0.434479683637619,
+      "grad_norm_var": 0.015627081016672508,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 10.9099,
+      "loss/crossentropy": 2.726790428161621,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14949394017457962,
+      "loss/reg": 10.760404586791992,
+      "step": 26
+    },
+    {
+      "epoch": 0.027,
+      "grad_norm": 0.3825664520263672,
+      "grad_norm_var": 0.015577720555919354,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 10.761,
+      "loss/crossentropy": 2.6250252723693848,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13614310324192047,
+      "loss/reg": 10.624829292297363,
+      "step": 27
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 0.3759184777736664,
+      "grad_norm_var": 0.015708703781819332,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 10.6382,
+      "loss/crossentropy": 2.835649013519287,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1468915417790413,
+      "loss/reg": 10.491329193115234,
+      "step": 28
+    },
+    {
+      "epoch": 0.029,
+      "grad_norm": 0.38468286395072937,
+      "grad_norm_var": 0.015690946589658594,
+      "learning_rate": 1.45e-05,
+      "loss": 10.4996,
+      "loss/crossentropy": 2.5807005167007446,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14014270156621933,
+      "loss/reg": 10.359500885009766,
+      "step": 29
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.4535682201385498,
+      "grad_norm_var": 0.002055153692638223,
+      "learning_rate": 1.5e-05,
+      "loss": 10.3735,
+      "loss/crossentropy": 2.547928214073181,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14383359998464584,
+      "loss/reg": 10.229703903198242,
+      "step": 30
+    },
+    {
+      "epoch": 0.031,
+      "grad_norm": 0.38543379306793213,
+      "grad_norm_var": 0.0020563179121854346,
+      "learning_rate": 1.55e-05,
+      "loss": 10.2439,
+      "loss/crossentropy": 2.79032039642334,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1421559825539589,
+      "loss/reg": 10.101773262023926,
+      "step": 31
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.33202216029167175,
+      "grad_norm_var": 0.0021707343468757136,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 10.0965,
+      "loss/crossentropy": 2.7922052145004272,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.12068676576018333,
+      "loss/reg": 9.97581672668457,
+      "step": 32
+    },
+    {
+      "epoch": 0.033,
+      "grad_norm": 0.39245933294296265,
+      "grad_norm_var": 0.0021702323626646702,
+      "learning_rate": 1.65e-05,
+      "loss": 9.9865,
+      "loss/crossentropy": 2.733828544616699,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1354268342256546,
+      "loss/reg": 9.851117134094238,
+      "step": 33
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 0.38694247603416443,
+      "grad_norm_var": 0.0020992626690788385,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 9.8885,
+      "loss/crossentropy": 2.777322292327881,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1599966138601303,
+      "loss/reg": 9.7284574508667,
+      "step": 34
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 0.35561245679855347,
+      "grad_norm_var": 0.0020449413010129036,
+      "learning_rate": 1.75e-05,
+      "loss": 9.7496,
+      "loss/crossentropy": 2.7148683071136475,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14201582968235016,
+      "loss/reg": 9.607542991638184,
+      "step": 35
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 0.4006306231021881,
+      "grad_norm_var": 0.002045261355702799,
+      "learning_rate": 1.8e-05,
+      "loss": 9.635,
+      "loss/crossentropy": 2.637976288795471,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14642605930566788,
+      "loss/reg": 9.488553047180176,
+      "step": 36
+    },
+    {
+      "epoch": 0.037,
+      "grad_norm": 0.41898205876350403,
+      "grad_norm_var": 0.002044839434195215,
+      "learning_rate": 1.85e-05,
+      "loss": 9.5202,
+      "loss/crossentropy": 2.777597665786743,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14908844977617264,
+      "loss/reg": 9.371098518371582,
+      "step": 37
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 0.3961292803287506,
+      "grad_norm_var": 0.001965975366123729,
+      "learning_rate": 1.9e-05,
+      "loss": 9.4067,
+      "loss/crossentropy": 2.9033197164535522,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15159177035093307,
+      "loss/reg": 9.255077362060547,
+      "step": 38
+    },
+    {
+      "epoch": 0.039,
+      "grad_norm": 0.38804033398628235,
+      "grad_norm_var": 0.0010025647229673696,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 9.2802,
+      "loss/crossentropy": 2.889930486679077,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1394604668021202,
+      "loss/reg": 9.14071273803711,
+      "step": 39
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.42919155955314636,
+      "grad_norm_var": 0.0008826965462539841,
+      "learning_rate": 2e-05,
+      "loss": 9.1743,
+      "loss/crossentropy": 2.4006484746932983,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14666535705327988,
+      "loss/reg": 9.027677536010742,
+      "step": 40
+    },
+    {
+      "epoch": 0.041,
+      "grad_norm": 0.37885668873786926,
+      "grad_norm_var": 0.0008895506586849048,
+      "learning_rate": 2.05e-05,
+      "loss": 9.0467,
+      "loss/crossentropy": 2.7493255138397217,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13013121858239174,
+      "loss/reg": 8.916520118713379,
+      "step": 41
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 0.5932357907295227,
+      "grad_norm_var": 0.0033328458836597336,
+      "learning_rate": 2.1e-05,
+      "loss": 8.97,
+      "loss/crossentropy": 2.6117889881134033,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16315819323062897,
+      "loss/reg": 8.80688190460205,
+      "step": 42
+    },
+    {
+      "epoch": 0.043,
+      "grad_norm": 0.3747418224811554,
+      "grad_norm_var": 0.0033583994321603233,
+      "learning_rate": 2.15e-05,
+      "loss": 8.8396,
+      "loss/crossentropy": 2.663694739341736,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14052008837461472,
+      "loss/reg": 8.69911003112793,
+      "step": 43
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 0.4256257116794586,
+      "grad_norm_var": 0.0033339815653853837,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 8.726,
+      "loss/crossentropy": 2.7881768941879272,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13326141238212585,
+      "loss/reg": 8.592697143554688,
+      "step": 44
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 0.4122328460216522,
+      "grad_norm_var": 0.0033030786394142473,
+      "learning_rate": 2.25e-05,
+      "loss": 8.6263,
+      "loss/crossentropy": 2.7951114177703857,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13837838172912598,
+      "loss/reg": 8.487950325012207,
+      "step": 45
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 0.4931789040565491,
+      "grad_norm_var": 0.0036432243285688614,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 8.5405,
+      "loss/crossentropy": 2.80547297000885,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15613804012537003,
+      "loss/reg": 8.384378433227539,
+      "step": 46
+    },
+    {
+      "epoch": 0.047,
+      "grad_norm": 0.4260822832584381,
+      "grad_norm_var": 0.003612225968443994,
+      "learning_rate": 2.35e-05,
+      "loss": 8.4325,
+      "loss/crossentropy": 2.7571998834609985,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15075545758008957,
+      "loss/reg": 8.281789779663086,
+      "step": 47
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.38472291827201843,
+      "grad_norm_var": 0.003218571473485099,
+      "learning_rate": 2.4e-05,
+      "loss": 8.3219,
+      "loss/crossentropy": 2.6643882989883423,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14136053621768951,
+      "loss/reg": 8.180567741394043,
+      "step": 48
+    },
+    {
+      "epoch": 0.049,
+      "grad_norm": 0.36624062061309814,
+      "grad_norm_var": 0.0033439747229166835,
+      "learning_rate": 2.45e-05,
+      "loss": 8.2178,
+      "loss/crossentropy": 2.737678050994873,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13707132637500763,
+      "loss/reg": 8.080729484558105,
+      "step": 49
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3760506212711334,
+      "grad_norm_var": 0.0033912685784647087,
+      "learning_rate": 2.5e-05,
+      "loss": 8.137,
+      "loss/crossentropy": 2.7842084169387817,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15427638590335846,
+      "loss/reg": 7.982727527618408,
+      "step": 50
+    },
+    {
+      "epoch": 0.051,
+      "grad_norm": 0.4842914044857025,
+      "grad_norm_var": 0.0034291612008964874,
+      "learning_rate": 2.5500000000000003e-05,
+      "loss": 8.0328,
+      "loss/crossentropy": 2.4711248874664307,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14703373610973358,
+      "loss/reg": 7.885744094848633,
+      "step": 51
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 0.35167771577835083,
+      "grad_norm_var": 0.0037168779577402794,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 7.9218,
+      "loss/crossentropy": 2.688042402267456,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13181188702583313,
+      "loss/reg": 7.789944648742676,
+      "step": 52
+    },
+    {
+      "epoch": 0.053,
+      "grad_norm": 0.4046782851219177,
+      "grad_norm_var": 0.0037291369976557537,
+      "learning_rate": 2.6500000000000004e-05,
+      "loss": 7.8506,
+      "loss/crossentropy": 2.6470447778701782,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1550150215625763,
+      "loss/reg": 7.695549011230469,
+      "step": 53
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 0.36790555715560913,
+      "grad_norm_var": 0.003860515189158183,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 7.7397,
+      "loss/crossentropy": 2.7709513902664185,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13687237352132797,
+      "loss/reg": 7.6028337478637695,
+      "step": 54
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 0.378646582365036,
+      "grad_norm_var": 0.003901108788218351,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 7.6525,
+      "loss/crossentropy": 2.8750112056732178,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14087973535060883,
+      "loss/reg": 7.511648178100586,
+      "step": 55
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.43194806575775146,
+      "grad_norm_var": 0.0039066305166497416,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 7.5885,
+      "loss/crossentropy": 2.6936086416244507,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16746176779270172,
+      "loss/reg": 7.421041965484619,
+      "step": 56
+    },
+    {
+      "epoch": 0.057,
+      "grad_norm": 0.4012855291366577,
+      "grad_norm_var": 0.0038280935965925374,
+      "learning_rate": 2.8499999999999998e-05,
+      "loss": 7.4798,
+      "loss/crossentropy": 2.8553980588912964,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14783543348312378,
+      "loss/reg": 7.331946849822998,
+      "step": 57
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 0.41179144382476807,
+      "grad_norm_var": 0.0016229469351226081,
+      "learning_rate": 2.9e-05,
+      "loss": 7.3917,
+      "loss/crossentropy": 2.90153706073761,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1475769728422165,
+      "loss/reg": 7.24411153793335,
+      "step": 58
+    },
+    {
+      "epoch": 0.059,
+      "grad_norm": 0.5224902033805847,
+      "grad_norm_var": 0.0023775492652975813,
+      "learning_rate": 2.95e-05,
+      "loss": 7.3131,
+      "loss/crossentropy": 2.922032952308655,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15628121048212051,
+      "loss/reg": 7.156867027282715,
+      "step": 59
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.511249840259552,
+      "grad_norm_var": 0.0029578979489786493,
+      "learning_rate": 3e-05,
+      "loss": 7.2356,
+      "loss/crossentropy": 2.7479801177978516,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1649666205048561,
+      "loss/reg": 7.070590019226074,
+      "step": 60
+    },
+    {
+      "epoch": 0.061,
+      "grad_norm": 0.4054379165172577,
+      "grad_norm_var": 0.0029680738800097915,
+      "learning_rate": 3.05e-05,
+      "loss": 7.138,
+      "loss/crossentropy": 2.8455255031585693,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15279172360897064,
+      "loss/reg": 6.985229015350342,
+      "step": 61
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 0.3967909812927246,
+      "grad_norm_var": 0.002606398157824093,
+      "learning_rate": 3.1e-05,
+      "loss": 7.045,
+      "loss/crossentropy": 2.5253665447235107,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14376042783260345,
+      "loss/reg": 6.901230335235596,
+      "step": 62
+    },
+    {
+      "epoch": 0.063,
+      "grad_norm": 0.5105597376823425,
+      "grad_norm_var": 0.0031904242194133975,
+      "learning_rate": 3.15e-05,
+      "loss": 7.0051,
+      "loss/crossentropy": 2.6825212240219116,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.18690404295921326,
+      "loss/reg": 6.818210124969482,
+      "step": 63
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4659242630004883,
+      "grad_norm_var": 0.0032302192085850684,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 6.9076,
+      "loss/crossentropy": 2.6204874515533447,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.17028357833623886,
+      "loss/reg": 6.737268447875977,
+      "step": 64
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 0.3556163012981415,
+      "grad_norm_var": 0.003319357356775484,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 6.79,
+      "loss/crossentropy": 2.6547772884368896,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.13286586478352547,
+      "loss/reg": 6.657088756561279,
+      "step": 65
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 0.4854835867881775,
+      "grad_norm_var": 0.003375179781292544,
+      "learning_rate": 3.3e-05,
+      "loss": 6.758,
+      "loss/crossentropy": 2.817094564437866,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.18038344383239746,
+      "loss/reg": 6.577615261077881,
+      "step": 66
+    },
+    {
+      "epoch": 0.067,
+      "grad_norm": 0.4216950833797455,
+      "grad_norm_var": 0.0031699615767635542,
+      "learning_rate": 3.35e-05,
+      "loss": 6.6588,
+      "loss/crossentropy": 2.872538924217224,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15885479748249054,
+      "loss/reg": 6.499909400939941,
+      "step": 67
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 0.4400080442428589,
+      "grad_norm_var": 0.0027769945370051136,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 6.5852,
+      "loss/crossentropy": 2.6969038248062134,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16181904822587967,
+      "loss/reg": 6.423398971557617,
+      "step": 68
+    },
+    {
+      "epoch": 0.069,
+      "grad_norm": 0.4272904396057129,
+      "grad_norm_var": 0.0027266697361371774,
+      "learning_rate": 3.45e-05,
+      "loss": 6.5089,
+      "loss/crossentropy": 2.7056760787963867,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16134114563465118,
+      "loss/reg": 6.347527503967285,
+      "step": 69
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.4215809404850006,
+      "grad_norm_var": 0.0024381335593683163,
+      "learning_rate": 3.5e-05,
+      "loss": 6.4248,
+      "loss/crossentropy": 2.822075366973877,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15255100280046463,
+      "loss/reg": 6.2722673416137695,
+      "step": 70
+    },
+    {
+      "epoch": 0.071,
+      "grad_norm": 0.3756145238876343,
+      "grad_norm_var": 0.0024621927937988008,
+      "learning_rate": 3.55e-05,
+      "loss": 6.3343,
+      "loss/crossentropy": 2.7529423236846924,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1365201622247696,
+      "loss/reg": 6.1977925300598145,
+      "step": 71
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.4465688467025757,
+      "grad_norm_var": 0.002466586095849488,
+      "learning_rate": 3.6e-05,
+      "loss": 6.2908,
+      "loss/crossentropy": 2.8122498989105225,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16586530208587646,
+      "loss/reg": 6.124953746795654,
+      "step": 72
+    },
+    {
+      "epoch": 0.073,
+      "grad_norm": 0.5681706070899963,
+      "grad_norm_var": 0.0034022813413523423,
+      "learning_rate": 3.65e-05,
+      "loss": 6.2178,
+      "loss/crossentropy": 2.8980711698532104,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16514715552330017,
+      "loss/reg": 6.052603244781494,
+      "step": 73
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 0.48894357681274414,
+      "grad_norm_var": 0.0034029444248247385,
+      "learning_rate": 3.7e-05,
+      "loss": 6.1569,
+      "loss/crossentropy": 2.7240917682647705,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.17589756846427917,
+      "loss/reg": 5.980965614318848,
+      "step": 74
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.4453263580799103,
+      "grad_norm_var": 0.003057192832421729,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 6.0806,
+      "loss/crossentropy": 2.880316376686096,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.17018750309944153,
+      "loss/reg": 5.910387992858887,
+      "step": 75
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.4072200357913971,
+      "grad_norm_var": 0.002854757019651292,
+      "learning_rate": 3.8e-05,
+      "loss": 5.9831,
+      "loss/crossentropy": 2.8352543115615845,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14264734089374542,
+      "loss/reg": 5.840408802032471,
+      "step": 76
+    },
+    {
+      "epoch": 0.077,
+      "grad_norm": 0.47089695930480957,
+      "grad_norm_var": 0.002808781993245483,
+      "learning_rate": 3.85e-05,
+      "loss": 5.9645,
+      "loss/crossentropy": 2.9140390157699585,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.19280433654785156,
+      "loss/reg": 5.771743297576904,
+      "step": 77
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 0.3908418118953705,
+      "grad_norm_var": 0.0028496157710373726,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 5.8542,
+      "loss/crossentropy": 2.70191752910614,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15121394395828247,
+      "loss/reg": 5.7030134201049805,
+      "step": 78
+    },
+    {
+      "epoch": 0.079,
+      "grad_norm": 0.417324423789978,
+      "grad_norm_var": 0.002579272338799754,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 5.7921,
+      "loss/crossentropy": 2.8772886991500854,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15610723197460175,
+      "loss/reg": 5.6359782218933105,
+      "step": 79
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4123746156692505,
+      "grad_norm_var": 0.002568267863573048,
+      "learning_rate": 4e-05,
+      "loss": 5.7333,
+      "loss/crossentropy": 2.785880208015442,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16348882019519806,
+      "loss/reg": 5.569836616516113,
+      "step": 80
+    },
+    {
+      "epoch": 0.081,
+      "grad_norm": 0.4967520833015442,
+      "grad_norm_var": 0.002301783549342551,
+      "learning_rate": 4.05e-05,
+      "loss": 5.6758,
+      "loss/crossentropy": 2.7999967336654663,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.17136523872613907,
+      "loss/reg": 5.504480361938477,
+      "step": 81
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 0.5052318572998047,
+      "grad_norm_var": 0.002433398774934281,
+      "learning_rate": 4.1e-05,
+      "loss": 5.6235,
+      "loss/crossentropy": 2.745284676551819,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.183761365711689,
+      "loss/reg": 5.439704418182373,
+      "step": 82
+    },
+    {
+      "epoch": 0.083,
+      "grad_norm": 0.42788586020469666,
+      "grad_norm_var": 0.0024157402006901862,
+      "learning_rate": 4.15e-05,
+      "loss": 5.5482,
+      "loss/crossentropy": 2.996077299118042,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1716163083910942,
+      "loss/reg": 5.37656831741333,
+      "step": 83
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.4045878052711487,
+      "grad_norm_var": 0.002524230641886934,
+      "learning_rate": 4.2e-05,
+      "loss": 5.4639,
+      "loss/crossentropy": 2.611970067024231,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.14972157776355743,
+      "loss/reg": 5.314174175262451,
+      "step": 84
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 0.41384124755859375,
+      "grad_norm_var": 0.0025657923048212758,
+      "learning_rate": 4.25e-05,
+      "loss": 5.4087,
+      "loss/crossentropy": 2.7544474601745605,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.15563561022281647,
+      "loss/reg": 5.253114223480225,
+      "step": 85
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 0.4230954945087433,
+      "grad_norm_var": 0.002561545150143992,
+      "learning_rate": 4.3e-05,
+      "loss": 5.3742,
+      "loss/crossentropy": 2.8086984157562256,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.18146374821662903,
+      "loss/reg": 5.192752361297607,
+      "step": 86
+    },
+    {
+      "epoch": 0.087,
+      "grad_norm": 0.45918789505958557,
+      "grad_norm_var": 0.0022425431957913728,
+      "learning_rate": 4.35e-05,
+      "loss": 5.3138,
+      "loss/crossentropy": 2.785672187805176,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1815495491027832,
+      "loss/reg": 5.132205486297607,
+      "step": 87
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4096454083919525,
+      "grad_norm_var": 0.002337951427575909,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 5.2231,
+      "loss/crossentropy": 2.7667384147644043,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1498737782239914,
+      "loss/reg": 5.073270797729492,
+      "step": 88
+    },
+    {
+      "epoch": 0.089,
+      "grad_norm": 0.4818902313709259,
+      "grad_norm_var": 0.001401593034965017,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 5.1976,
+      "loss/crossentropy": 2.722651481628418,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.18228119611740112,
+      "loss/reg": 5.015347480773926,
+      "step": 89
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4635304808616638,
+      "grad_norm_var": 0.0012793023910875926,
+      "learning_rate": 4.5e-05,
+      "loss": 5.1364,
+      "loss/crossentropy": 2.7336219549179077,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1788763403892517,
+      "loss/reg": 4.95751953125,
+      "step": 90
+    },
+    {
+      "epoch": 0.091,
+      "grad_norm": 0.46776527166366577,
+      "grad_norm_var": 0.0013286457514422071,
+      "learning_rate": 4.55e-05,
+      "loss": 5.089,
+      "loss/crossentropy": 2.818411946296692,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.18763671815395355,
+      "loss/reg": 4.901313781738281,
+      "step": 91
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.4979424774646759,
+      "grad_norm_var": 0.0014374124356233827,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 5.033,
+      "loss/crossentropy": 2.780390739440918,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.18797770142555237,
+      "loss/reg": 4.844989776611328,
+      "step": 92
+    },
+    {
+      "epoch": 0.093,
+      "grad_norm": 0.476500004529953,
+      "grad_norm_var": 0.0014576571842103666,
+      "learning_rate": 4.6500000000000005e-05,
+      "loss": 4.9601,
+      "loss/crossentropy": 2.873763084411621,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.16978690773248672,
+      "loss/reg": 4.790344715118408,
+      "step": 93
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 0.4781922996044159,
+      "grad_norm_var": 0.0012831022874166228,
+      "learning_rate": 4.7e-05,
+      "loss": 4.9191,
+      "loss/crossentropy": 2.7947566509246826,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1818721517920494,
+      "loss/reg": 4.737210273742676,
+      "step": 94
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 0.4668790102005005,
+      "grad_norm_var": 0.0012059221432147993,
+      "learning_rate": 4.75e-05,
+      "loss": 4.8722,
+      "loss/crossentropy": 2.975098729133606,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.18810376524925232,
+      "loss/reg": 4.684102535247803,
+      "step": 95
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6337518095970154,
+      "grad_norm_var": 0.003000960526301677,
+      "learning_rate": 4.8e-05,
+      "loss": 4.8243,
+      "loss/crossentropy": 2.8563435077667236,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.19358298182487488,
+      "loss/reg": 4.630751132965088,
+      "step": 96
+    },
+    {
+      "epoch": 0.097,
+      "grad_norm": 0.5349352955818176,
+      "grad_norm_var": 0.003232518858686584,
+      "learning_rate": 4.85e-05,
+      "loss": 4.7556,
+      "loss/crossentropy": 2.8064088821411133,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1775345504283905,
+      "loss/reg": 4.578096866607666,
+      "step": 97
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 0.4641897976398468,
+      "grad_norm_var": 0.003153502010794122,
+      "learning_rate": 4.9e-05,
+      "loss": 4.7093,
+      "loss/crossentropy": 2.737215995788574,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.18364109843969345,
+      "loss/reg": 4.525658130645752,
+      "step": 98
+    },
+    {
+      "epoch": 0.099,
+      "grad_norm": 0.4986944794654846,
+      "grad_norm_var": 0.003078809549519083,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 4.6582,
+      "loss/crossentropy": 2.7446107864379883,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.1834591180086136,
+      "loss/reg": 4.474703311920166,
+      "step": 99
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.5496240854263306,
+      "grad_norm_var": 0.0030625509543914593,
+      "learning_rate": 5e-05,
+      "loss": 4.6055,
+      "loss/crossentropy": 2.8407260179519653,
+      "loss/hidden": 0.0,
+      "loss/logits": 0.18116910755634308,
+      "loss/reg": 4.424361228942871,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": true,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.57623446257664e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abcacac90c350d0fcbabe8a3adba957fdf2b43efa21564513baa6401f18187ee
+size 5304