Training in progress, epoch 1

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f17107c64cb34ece715f5bf72399b4ac9b6455544e84a67265ccf9ab71af0fd
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1610d3c6acf3d51367640b1bb36bf901c89ecf183262fbc2c276b633721f161e
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813b9cdeddf49d07511c612f2d5f0671f5596a8be6558a2e4e2afb634d085b7e
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:450f8cb2054a6c0cfe1f362df8a835824aa34661ce62a61448a234ce08fb8221
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_log.jsonl

@@ -0,0 +1,159 @@
+{"current_steps": 10, "total_steps": 4665, "loss": 0.8965, "learning_rate": 5e-06, "epoch": 0.006430868167202572, "percentage": 0.21, "elapsed_time": "0:01:03", "remaining_time": "8:08:47"}
+{"current_steps": 20, "total_steps": 4665, "loss": 0.8501, "learning_rate": 5e-06, "epoch": 0.012861736334405145, "percentage": 0.43, "elapsed_time": "0:02:05", "remaining_time": "8:04:09"}
+{"current_steps": 30, "total_steps": 4665, "loss": 0.8318, "learning_rate": 5e-06, "epoch": 0.01929260450160772, "percentage": 0.64, "elapsed_time": "0:03:07", "remaining_time": "8:02:49"}
+{"current_steps": 40, "total_steps": 4665, "loss": 0.8193, "learning_rate": 5e-06, "epoch": 0.02572347266881029, "percentage": 0.86, "elapsed_time": "0:04:09", "remaining_time": "8:01:00"}
+{"current_steps": 50, "total_steps": 4665, "loss": 0.8094, "learning_rate": 5e-06, "epoch": 0.03215434083601286, "percentage": 1.07, "elapsed_time": "0:05:11", "remaining_time": "7:59:31"}
+{"current_steps": 60, "total_steps": 4665, "loss": 0.8042, "learning_rate": 5e-06, "epoch": 0.03858520900321544, "percentage": 1.29, "elapsed_time": "0:06:13", "remaining_time": "7:58:10"}
+{"current_steps": 70, "total_steps": 4665, "loss": 0.7912, "learning_rate": 5e-06, "epoch": 0.04501607717041801, "percentage": 1.5, "elapsed_time": "0:07:15", "remaining_time": "7:56:54"}
+{"current_steps": 80, "total_steps": 4665, "loss": 0.7894, "learning_rate": 5e-06, "epoch": 0.05144694533762058, "percentage": 1.71, "elapsed_time": "0:08:18", "remaining_time": "7:55:42"}
+{"current_steps": 90, "total_steps": 4665, "loss": 0.7799, "learning_rate": 5e-06, "epoch": 0.05787781350482315, "percentage": 1.93, "elapsed_time": "0:09:20", "remaining_time": "7:54:33"}
+{"current_steps": 100, "total_steps": 4665, "loss": 0.7832, "learning_rate": 5e-06, "epoch": 0.06430868167202572, "percentage": 2.14, "elapsed_time": "0:10:22", "remaining_time": "7:53:26"}
+{"current_steps": 110, "total_steps": 4665, "loss": 0.7791, "learning_rate": 5e-06, "epoch": 0.0707395498392283, "percentage": 2.36, "elapsed_time": "0:11:24", "remaining_time": "7:52:18"}
+{"current_steps": 120, "total_steps": 4665, "loss": 0.7784, "learning_rate": 5e-06, "epoch": 0.07717041800643087, "percentage": 2.57, "elapsed_time": "0:12:26", "remaining_time": "7:51:12"}
+{"current_steps": 130, "total_steps": 4665, "loss": 0.7665, "learning_rate": 5e-06, "epoch": 0.08360128617363344, "percentage": 2.79, "elapsed_time": "0:13:28", "remaining_time": "7:50:06"}
+{"current_steps": 140, "total_steps": 4665, "loss": 0.7643, "learning_rate": 5e-06, "epoch": 0.09003215434083602, "percentage": 3.0, "elapsed_time": "0:14:30", "remaining_time": "7:49:01"}
+{"current_steps": 150, "total_steps": 4665, "loss": 0.7772, "learning_rate": 5e-06, "epoch": 0.09646302250803858, "percentage": 3.22, "elapsed_time": "0:15:32", "remaining_time": "7:47:56"}
+{"current_steps": 160, "total_steps": 4665, "loss": 0.7679, "learning_rate": 5e-06, "epoch": 0.10289389067524116, "percentage": 3.43, "elapsed_time": "0:16:34", "remaining_time": "7:46:51"}
+{"current_steps": 170, "total_steps": 4665, "loss": 0.7724, "learning_rate": 5e-06, "epoch": 0.10932475884244373, "percentage": 3.64, "elapsed_time": "0:17:36", "remaining_time": "7:45:48"}
+{"current_steps": 180, "total_steps": 4665, "loss": 0.7615, "learning_rate": 5e-06, "epoch": 0.1157556270096463, "percentage": 3.86, "elapsed_time": "0:18:39", "remaining_time": "7:44:43"}
+{"current_steps": 190, "total_steps": 4665, "loss": 0.767, "learning_rate": 5e-06, "epoch": 0.12218649517684887, "percentage": 4.07, "elapsed_time": "0:19:41", "remaining_time": "7:43:39"}
+{"current_steps": 200, "total_steps": 4665, "loss": 0.7666, "learning_rate": 5e-06, "epoch": 0.12861736334405144, "percentage": 4.29, "elapsed_time": "0:20:43", "remaining_time": "7:42:36"}
+{"current_steps": 210, "total_steps": 4665, "loss": 0.7564, "learning_rate": 5e-06, "epoch": 0.13504823151125403, "percentage": 4.5, "elapsed_time": "0:21:45", "remaining_time": "7:41:33"}
+{"current_steps": 220, "total_steps": 4665, "loss": 0.7546, "learning_rate": 5e-06, "epoch": 0.1414790996784566, "percentage": 4.72, "elapsed_time": "0:22:47", "remaining_time": "7:40:29"}
+{"current_steps": 230, "total_steps": 4665, "loss": 0.7597, "learning_rate": 5e-06, "epoch": 0.14790996784565916, "percentage": 4.93, "elapsed_time": "0:23:49", "remaining_time": "7:39:26"}
+{"current_steps": 240, "total_steps": 4665, "loss": 0.7637, "learning_rate": 5e-06, "epoch": 0.15434083601286175, "percentage": 5.14, "elapsed_time": "0:24:51", "remaining_time": "7:38:23"}
+{"current_steps": 250, "total_steps": 4665, "loss": 0.7663, "learning_rate": 5e-06, "epoch": 0.1607717041800643, "percentage": 5.36, "elapsed_time": "0:25:53", "remaining_time": "7:37:20"}
+{"current_steps": 260, "total_steps": 4665, "loss": 0.7567, "learning_rate": 5e-06, "epoch": 0.16720257234726688, "percentage": 5.57, "elapsed_time": "0:26:55", "remaining_time": "7:36:18"}
+{"current_steps": 270, "total_steps": 4665, "loss": 0.7581, "learning_rate": 5e-06, "epoch": 0.17363344051446947, "percentage": 5.79, "elapsed_time": "0:27:58", "remaining_time": "7:35:15"}
+{"current_steps": 280, "total_steps": 4665, "loss": 0.7591, "learning_rate": 5e-06, "epoch": 0.18006430868167203, "percentage": 6.0, "elapsed_time": "0:29:00", "remaining_time": "7:34:13"}
+{"current_steps": 290, "total_steps": 4665, "loss": 0.754, "learning_rate": 5e-06, "epoch": 0.1864951768488746, "percentage": 6.22, "elapsed_time": "0:30:02", "remaining_time": "7:33:11"}
+{"current_steps": 300, "total_steps": 4665, "loss": 0.7601, "learning_rate": 5e-06, "epoch": 0.19292604501607716, "percentage": 6.43, "elapsed_time": "0:31:04", "remaining_time": "7:32:08"}
+{"current_steps": 310, "total_steps": 4665, "loss": 0.7534, "learning_rate": 5e-06, "epoch": 0.19935691318327975, "percentage": 6.65, "elapsed_time": "0:32:06", "remaining_time": "7:31:06"}
+{"current_steps": 320, "total_steps": 4665, "loss": 0.7567, "learning_rate": 5e-06, "epoch": 0.2057877813504823, "percentage": 6.86, "elapsed_time": "0:33:08", "remaining_time": "7:30:03"}
+{"current_steps": 330, "total_steps": 4665, "loss": 0.7701, "learning_rate": 5e-06, "epoch": 0.21221864951768488, "percentage": 7.07, "elapsed_time": "0:34:10", "remaining_time": "7:29:00"}
+{"current_steps": 340, "total_steps": 4665, "loss": 0.7565, "learning_rate": 5e-06, "epoch": 0.21864951768488747, "percentage": 7.29, "elapsed_time": "0:35:12", "remaining_time": "7:27:57"}
+{"current_steps": 350, "total_steps": 4665, "loss": 0.7423, "learning_rate": 5e-06, "epoch": 0.22508038585209003, "percentage": 7.5, "elapsed_time": "0:36:15", "remaining_time": "7:26:55"}
+{"current_steps": 360, "total_steps": 4665, "loss": 0.7569, "learning_rate": 5e-06, "epoch": 0.2315112540192926, "percentage": 7.72, "elapsed_time": "0:37:17", "remaining_time": "7:25:53"}
+{"current_steps": 370, "total_steps": 4665, "loss": 0.7557, "learning_rate": 5e-06, "epoch": 0.2379421221864952, "percentage": 7.93, "elapsed_time": "0:38:19", "remaining_time": "7:24:50"}
+{"current_steps": 380, "total_steps": 4665, "loss": 0.7569, "learning_rate": 5e-06, "epoch": 0.24437299035369775, "percentage": 8.15, "elapsed_time": "0:39:21", "remaining_time": "7:23:48"}
+{"current_steps": 390, "total_steps": 4665, "loss": 0.7496, "learning_rate": 5e-06, "epoch": 0.2508038585209003, "percentage": 8.36, "elapsed_time": "0:40:23", "remaining_time": "7:22:45"}
+{"current_steps": 400, "total_steps": 4665, "loss": 0.7528, "learning_rate": 5e-06, "epoch": 0.2572347266881029, "percentage": 8.57, "elapsed_time": "0:41:25", "remaining_time": "7:21:42"}
+{"current_steps": 410, "total_steps": 4665, "loss": 0.7612, "learning_rate": 5e-06, "epoch": 0.26366559485530544, "percentage": 8.79, "elapsed_time": "0:42:27", "remaining_time": "7:20:40"}
+{"current_steps": 420, "total_steps": 4665, "loss": 0.749, "learning_rate": 5e-06, "epoch": 0.27009646302250806, "percentage": 9.0, "elapsed_time": "0:43:29", "remaining_time": "7:19:38"}
+{"current_steps": 430, "total_steps": 4665, "loss": 0.7396, "learning_rate": 5e-06, "epoch": 0.2765273311897106, "percentage": 9.22, "elapsed_time": "0:44:31", "remaining_time": "7:18:36"}
+{"current_steps": 440, "total_steps": 4665, "loss": 0.7471, "learning_rate": 5e-06, "epoch": 0.2829581993569132, "percentage": 9.43, "elapsed_time": "0:45:34", "remaining_time": "7:17:33"}
+{"current_steps": 450, "total_steps": 4665, "loss": 0.7449, "learning_rate": 5e-06, "epoch": 0.28938906752411575, "percentage": 9.65, "elapsed_time": "0:46:36", "remaining_time": "7:16:33"}
+{"current_steps": 460, "total_steps": 4665, "loss": 0.7483, "learning_rate": 5e-06, "epoch": 0.2958199356913183, "percentage": 9.86, "elapsed_time": "0:47:38", "remaining_time": "7:15:31"}
+{"current_steps": 470, "total_steps": 4665, "loss": 0.7451, "learning_rate": 5e-06, "epoch": 0.3022508038585209, "percentage": 10.08, "elapsed_time": "0:48:40", "remaining_time": "7:14:30"}
+{"current_steps": 480, "total_steps": 4665, "loss": 0.7463, "learning_rate": 5e-06, "epoch": 0.3086816720257235, "percentage": 10.29, "elapsed_time": "0:49:42", "remaining_time": "7:13:27"}
+{"current_steps": 490, "total_steps": 4665, "loss": 0.7403, "learning_rate": 5e-06, "epoch": 0.31511254019292606, "percentage": 10.5, "elapsed_time": "0:50:45", "remaining_time": "7:12:25"}
+{"current_steps": 500, "total_steps": 4665, "loss": 0.7425, "learning_rate": 5e-06, "epoch": 0.3215434083601286, "percentage": 10.72, "elapsed_time": "0:51:47", "remaining_time": "7:11:23"}
+{"current_steps": 510, "total_steps": 4665, "loss": 0.7506, "learning_rate": 5e-06, "epoch": 0.3279742765273312, "percentage": 10.93, "elapsed_time": "0:52:49", "remaining_time": "7:10:21"}
+{"current_steps": 520, "total_steps": 4665, "loss": 0.7404, "learning_rate": 5e-06, "epoch": 0.33440514469453375, "percentage": 11.15, "elapsed_time": "0:53:51", "remaining_time": "7:09:18"}
+{"current_steps": 530, "total_steps": 4665, "loss": 0.7465, "learning_rate": 5e-06, "epoch": 0.3408360128617363, "percentage": 11.36, "elapsed_time": "0:54:53", "remaining_time": "7:08:16"}
+{"current_steps": 540, "total_steps": 4665, "loss": 0.7531, "learning_rate": 5e-06, "epoch": 0.34726688102893893, "percentage": 11.58, "elapsed_time": "0:55:55", "remaining_time": "7:07:14"}
+{"current_steps": 550, "total_steps": 4665, "loss": 0.7428, "learning_rate": 5e-06, "epoch": 0.3536977491961415, "percentage": 11.79, "elapsed_time": "0:56:57", "remaining_time": "7:06:12"}
+{"current_steps": 560, "total_steps": 4665, "loss": 0.7427, "learning_rate": 5e-06, "epoch": 0.36012861736334406, "percentage": 12.0, "elapsed_time": "0:58:00", "remaining_time": "7:05:10"}
+{"current_steps": 570, "total_steps": 4665, "loss": 0.7408, "learning_rate": 5e-06, "epoch": 0.3665594855305466, "percentage": 12.22, "elapsed_time": "0:59:02", "remaining_time": "7:04:08"}
+{"current_steps": 580, "total_steps": 4665, "loss": 0.7423, "learning_rate": 5e-06, "epoch": 0.3729903536977492, "percentage": 12.43, "elapsed_time": "1:00:04", "remaining_time": "7:03:06"}
+{"current_steps": 590, "total_steps": 4665, "loss": 0.7383, "learning_rate": 5e-06, "epoch": 0.37942122186495175, "percentage": 12.65, "elapsed_time": "1:01:06", "remaining_time": "7:02:03"}
+{"current_steps": 600, "total_steps": 4665, "loss": 0.7509, "learning_rate": 5e-06, "epoch": 0.3858520900321543, "percentage": 12.86, "elapsed_time": "1:02:08", "remaining_time": "7:01:01"}
+{"current_steps": 610, "total_steps": 4665, "loss": 0.7387, "learning_rate": 5e-06, "epoch": 0.39228295819935693, "percentage": 13.08, "elapsed_time": "1:03:10", "remaining_time": "6:59:59"}
+{"current_steps": 620, "total_steps": 4665, "loss": 0.7379, "learning_rate": 5e-06, "epoch": 0.3987138263665595, "percentage": 13.29, "elapsed_time": "1:04:12", "remaining_time": "6:58:57"}
+{"current_steps": 630, "total_steps": 4665, "loss": 0.7384, "learning_rate": 5e-06, "epoch": 0.40514469453376206, "percentage": 13.5, "elapsed_time": "1:05:15", "remaining_time": "6:57:56"}
+{"current_steps": 640, "total_steps": 4665, "loss": 0.7349, "learning_rate": 5e-06, "epoch": 0.4115755627009646, "percentage": 13.72, "elapsed_time": "1:06:18", "remaining_time": "6:56:59"}
+{"current_steps": 650, "total_steps": 4665, "loss": 0.7379, "learning_rate": 5e-06, "epoch": 0.4180064308681672, "percentage": 13.93, "elapsed_time": "1:07:20", "remaining_time": "6:55:57"}
+{"current_steps": 660, "total_steps": 4665, "loss": 0.7361, "learning_rate": 5e-06, "epoch": 0.42443729903536975, "percentage": 14.15, "elapsed_time": "1:08:22", "remaining_time": "6:54:55"}
+{"current_steps": 670, "total_steps": 4665, "loss": 0.7373, "learning_rate": 5e-06, "epoch": 0.43086816720257237, "percentage": 14.36, "elapsed_time": "1:09:24", "remaining_time": "6:53:53"}
+{"current_steps": 680, "total_steps": 4665, "loss": 0.7428, "learning_rate": 5e-06, "epoch": 0.43729903536977494, "percentage": 14.58, "elapsed_time": "1:10:26", "remaining_time": "6:52:51"}
+{"current_steps": 690, "total_steps": 4665, "loss": 0.7397, "learning_rate": 5e-06, "epoch": 0.4437299035369775, "percentage": 14.79, "elapsed_time": "1:11:29", "remaining_time": "6:51:49"}
+{"current_steps": 700, "total_steps": 4665, "loss": 0.7375, "learning_rate": 5e-06, "epoch": 0.45016077170418006, "percentage": 15.01, "elapsed_time": "1:12:31", "remaining_time": "6:50:46"}
+{"current_steps": 710, "total_steps": 4665, "loss": 0.7352, "learning_rate": 5e-06, "epoch": 0.4565916398713826, "percentage": 15.22, "elapsed_time": "1:13:33", "remaining_time": "6:49:44"}
+{"current_steps": 720, "total_steps": 4665, "loss": 0.7385, "learning_rate": 5e-06, "epoch": 0.4630225080385852, "percentage": 15.43, "elapsed_time": "1:14:35", "remaining_time": "6:48:42"}
+{"current_steps": 730, "total_steps": 4665, "loss": 0.7364, "learning_rate": 5e-06, "epoch": 0.4694533762057878, "percentage": 15.65, "elapsed_time": "1:15:37", "remaining_time": "6:47:40"}
+{"current_steps": 740, "total_steps": 4665, "loss": 0.7368, "learning_rate": 5e-06, "epoch": 0.4758842443729904, "percentage": 15.86, "elapsed_time": "1:16:39", "remaining_time": "6:46:38"}
+{"current_steps": 750, "total_steps": 4665, "loss": 0.7286, "learning_rate": 5e-06, "epoch": 0.48231511254019294, "percentage": 16.08, "elapsed_time": "1:17:42", "remaining_time": "6:45:35"}
+{"current_steps": 760, "total_steps": 4665, "loss": 0.7368, "learning_rate": 5e-06, "epoch": 0.4887459807073955, "percentage": 16.29, "elapsed_time": "1:18:44", "remaining_time": "6:44:34"}
+{"current_steps": 770, "total_steps": 4665, "loss": 0.7432, "learning_rate": 5e-06, "epoch": 0.49517684887459806, "percentage": 16.51, "elapsed_time": "1:19:46", "remaining_time": "6:43:32"}
+{"current_steps": 780, "total_steps": 4665, "loss": 0.7405, "learning_rate": 5e-06, "epoch": 0.5016077170418006, "percentage": 16.72, "elapsed_time": "1:20:48", "remaining_time": "6:42:31"}
+{"current_steps": 790, "total_steps": 4665, "loss": 0.7346, "learning_rate": 5e-06, "epoch": 0.5080385852090032, "percentage": 16.93, "elapsed_time": "1:21:51", "remaining_time": "6:41:29"}
+{"current_steps": 800, "total_steps": 4665, "loss": 0.7343, "learning_rate": 5e-06, "epoch": 0.5144694533762058, "percentage": 17.15, "elapsed_time": "1:22:53", "remaining_time": "6:40:27"}
+{"current_steps": 810, "total_steps": 4665, "loss": 0.7401, "learning_rate": 5e-06, "epoch": 0.5209003215434084, "percentage": 17.36, "elapsed_time": "1:23:55", "remaining_time": "6:39:24"}
+{"current_steps": 820, "total_steps": 4665, "loss": 0.7333, "learning_rate": 5e-06, "epoch": 0.5273311897106109, "percentage": 17.58, "elapsed_time": "1:24:57", "remaining_time": "6:38:22"}
+{"current_steps": 830, "total_steps": 4665, "loss": 0.7405, "learning_rate": 5e-06, "epoch": 0.5337620578778135, "percentage": 17.79, "elapsed_time": "1:25:59", "remaining_time": "6:37:20"}
+{"current_steps": 840, "total_steps": 4665, "loss": 0.735, "learning_rate": 5e-06, "epoch": 0.5401929260450161, "percentage": 18.01, "elapsed_time": "1:27:02", "remaining_time": "6:36:19"}
+{"current_steps": 850, "total_steps": 4665, "loss": 0.7235, "learning_rate": 5e-06, "epoch": 0.5466237942122186, "percentage": 18.22, "elapsed_time": "1:28:04", "remaining_time": "6:35:16"}
+{"current_steps": 860, "total_steps": 4665, "loss": 0.7398, "learning_rate": 5e-06, "epoch": 0.5530546623794212, "percentage": 18.44, "elapsed_time": "1:29:06", "remaining_time": "6:34:16"}
+{"current_steps": 870, "total_steps": 4665, "loss": 0.7383, "learning_rate": 5e-06, "epoch": 0.5594855305466238, "percentage": 18.65, "elapsed_time": "1:30:09", "remaining_time": "6:33:14"}
+{"current_steps": 880, "total_steps": 4665, "loss": 0.741, "learning_rate": 5e-06, "epoch": 0.5659163987138264, "percentage": 18.86, "elapsed_time": "1:31:11", "remaining_time": "6:32:13"}
+{"current_steps": 890, "total_steps": 4665, "loss": 0.7304, "learning_rate": 5e-06, "epoch": 0.572347266881029, "percentage": 19.08, "elapsed_time": "1:32:13", "remaining_time": "6:31:11"}
+{"current_steps": 900, "total_steps": 4665, "loss": 0.7351, "learning_rate": 5e-06, "epoch": 0.5787781350482315, "percentage": 19.29, "elapsed_time": "1:33:15", "remaining_time": "6:30:09"}
+{"current_steps": 910, "total_steps": 4665, "loss": 0.732, "learning_rate": 5e-06, "epoch": 0.5852090032154341, "percentage": 19.51, "elapsed_time": "1:34:18", "remaining_time": "6:29:07"}
+{"current_steps": 920, "total_steps": 4665, "loss": 0.7357, "learning_rate": 5e-06, "epoch": 0.5916398713826366, "percentage": 19.72, "elapsed_time": "1:35:20", "remaining_time": "6:28:04"}
+{"current_steps": 930, "total_steps": 4665, "loss": 0.739, "learning_rate": 5e-06, "epoch": 0.5980707395498392, "percentage": 19.94, "elapsed_time": "1:36:22", "remaining_time": "6:27:02"}
+{"current_steps": 940, "total_steps": 4665, "loss": 0.7421, "learning_rate": 5e-06, "epoch": 0.6045016077170418, "percentage": 20.15, "elapsed_time": "1:37:24", "remaining_time": "6:26:00"}
+{"current_steps": 950, "total_steps": 4665, "loss": 0.733, "learning_rate": 5e-06, "epoch": 0.6109324758842444, "percentage": 20.36, "elapsed_time": "1:38:26", "remaining_time": "6:24:58"}
+{"current_steps": 960, "total_steps": 4665, "loss": 0.7306, "learning_rate": 5e-06, "epoch": 0.617363344051447, "percentage": 20.58, "elapsed_time": "1:39:29", "remaining_time": "6:23:57"}
+{"current_steps": 970, "total_steps": 4665, "loss": 0.7267, "learning_rate": 5e-06, "epoch": 0.6237942122186495, "percentage": 20.79, "elapsed_time": "1:40:31", "remaining_time": "6:22:55"}
+{"current_steps": 980, "total_steps": 4665, "loss": 0.7339, "learning_rate": 5e-06, "epoch": 0.6302250803858521, "percentage": 21.01, "elapsed_time": "1:41:33", "remaining_time": "6:21:53"}
+{"current_steps": 990, "total_steps": 4665, "loss": 0.7321, "learning_rate": 5e-06, "epoch": 0.6366559485530546, "percentage": 21.22, "elapsed_time": "1:42:35", "remaining_time": "6:20:50"}
+{"current_steps": 1000, "total_steps": 4665, "loss": 0.7244, "learning_rate": 5e-06, "epoch": 0.6430868167202572, "percentage": 21.44, "elapsed_time": "1:43:37", "remaining_time": "6:19:48"}
+{"current_steps": 1010, "total_steps": 4665, "loss": 0.7339, "learning_rate": 5e-06, "epoch": 0.6495176848874598, "percentage": 21.65, "elapsed_time": "1:44:39", "remaining_time": "6:18:46"}
+{"current_steps": 1020, "total_steps": 4665, "loss": 0.7317, "learning_rate": 5e-06, "epoch": 0.6559485530546624, "percentage": 21.86, "elapsed_time": "1:45:42", "remaining_time": "6:17:43"}
+{"current_steps": 1030, "total_steps": 4665, "loss": 0.7294, "learning_rate": 5e-06, "epoch": 0.662379421221865, "percentage": 22.08, "elapsed_time": "1:46:44", "remaining_time": "6:16:41"}
+{"current_steps": 1040, "total_steps": 4665, "loss": 0.7306, "learning_rate": 5e-06, "epoch": 0.6688102893890675, "percentage": 22.29, "elapsed_time": "1:47:46", "remaining_time": "6:15:40"}
+{"current_steps": 1050, "total_steps": 4665, "loss": 0.7234, "learning_rate": 5e-06, "epoch": 0.6752411575562701, "percentage": 22.51, "elapsed_time": "1:48:48", "remaining_time": "6:14:38"}
+{"current_steps": 1060, "total_steps": 4665, "loss": 0.7346, "learning_rate": 5e-06, "epoch": 0.6816720257234726, "percentage": 22.72, "elapsed_time": "1:49:51", "remaining_time": "6:13:37"}
+{"current_steps": 1070, "total_steps": 4665, "loss": 0.7323, "learning_rate": 5e-06, "epoch": 0.6881028938906752, "percentage": 22.94, "elapsed_time": "1:50:53", "remaining_time": "6:12:36"}
+{"current_steps": 1080, "total_steps": 4665, "loss": 0.7348, "learning_rate": 5e-06, "epoch": 0.6945337620578779, "percentage": 23.15, "elapsed_time": "1:51:56", "remaining_time": "6:11:34"}
+{"current_steps": 1090, "total_steps": 4665, "loss": 0.7267, "learning_rate": 5e-06, "epoch": 0.7009646302250804, "percentage": 23.37, "elapsed_time": "1:52:58", "remaining_time": "6:10:32"}
+{"current_steps": 1100, "total_steps": 4665, "loss": 0.7305, "learning_rate": 5e-06, "epoch": 0.707395498392283, "percentage": 23.58, "elapsed_time": "1:54:00", "remaining_time": "6:09:30"}
+{"current_steps": 1110, "total_steps": 4665, "loss": 0.7311, "learning_rate": 5e-06, "epoch": 0.7138263665594855, "percentage": 23.79, "elapsed_time": "1:55:02", "remaining_time": "6:08:27"}
+{"current_steps": 1120, "total_steps": 4665, "loss": 0.7277, "learning_rate": 5e-06, "epoch": 0.7202572347266881, "percentage": 24.01, "elapsed_time": "1:56:05", "remaining_time": "6:07:25"}
+{"current_steps": 1130, "total_steps": 4665, "loss": 0.7319, "learning_rate": 5e-06, "epoch": 0.7266881028938906, "percentage": 24.22, "elapsed_time": "1:57:07", "remaining_time": "6:06:23"}
+{"current_steps": 1140, "total_steps": 4665, "loss": 0.7251, "learning_rate": 5e-06, "epoch": 0.7331189710610932, "percentage": 24.44, "elapsed_time": "1:58:09", "remaining_time": "6:05:20"}
+{"current_steps": 1150, "total_steps": 4665, "loss": 0.7403, "learning_rate": 5e-06, "epoch": 0.7395498392282959, "percentage": 24.65, "elapsed_time": "1:59:11", "remaining_time": "6:04:18"}
+{"current_steps": 1160, "total_steps": 4665, "loss": 0.7319, "learning_rate": 5e-06, "epoch": 0.7459807073954984, "percentage": 24.87, "elapsed_time": "2:00:13", "remaining_time": "6:03:16"}
+{"current_steps": 1170, "total_steps": 4665, "loss": 0.7315, "learning_rate": 5e-06, "epoch": 0.752411575562701, "percentage": 25.08, "elapsed_time": "2:01:15", "remaining_time": "6:02:14"}
+{"current_steps": 1180, "total_steps": 4665, "loss": 0.7287, "learning_rate": 5e-06, "epoch": 0.7588424437299035, "percentage": 25.29, "elapsed_time": "2:02:18", "remaining_time": "6:01:11"}
+{"current_steps": 1190, "total_steps": 4665, "loss": 0.7294, "learning_rate": 5e-06, "epoch": 0.7652733118971061, "percentage": 25.51, "elapsed_time": "2:03:20", "remaining_time": "6:00:09"}
+{"current_steps": 1200, "total_steps": 4665, "loss": 0.7218, "learning_rate": 5e-06, "epoch": 0.7717041800643086, "percentage": 25.72, "elapsed_time": "2:04:22", "remaining_time": "5:59:07"}
+{"current_steps": 1210, "total_steps": 4665, "loss": 0.7297, "learning_rate": 5e-06, "epoch": 0.7781350482315113, "percentage": 25.94, "elapsed_time": "2:05:24", "remaining_time": "5:58:05"}
+{"current_steps": 1220, "total_steps": 4665, "loss": 0.7299, "learning_rate": 5e-06, "epoch": 0.7845659163987139, "percentage": 26.15, "elapsed_time": "2:06:26", "remaining_time": "5:57:03"}
+{"current_steps": 1230, "total_steps": 4665, "loss": 0.7299, "learning_rate": 5e-06, "epoch": 0.7909967845659164, "percentage": 26.37, "elapsed_time": "2:07:28", "remaining_time": "5:56:00"}
+{"current_steps": 1240, "total_steps": 4665, "loss": 0.738, "learning_rate": 5e-06, "epoch": 0.797427652733119, "percentage": 26.58, "elapsed_time": "2:08:30", "remaining_time": "5:54:58"}
+{"current_steps": 1250, "total_steps": 4665, "loss": 0.7324, "learning_rate": 5e-06, "epoch": 0.8038585209003215, "percentage": 26.8, "elapsed_time": "2:09:33", "remaining_time": "5:53:56"}
+{"current_steps": 1260, "total_steps": 4665, "loss": 0.7219, "learning_rate": 5e-06, "epoch": 0.8102893890675241, "percentage": 27.01, "elapsed_time": "2:10:35", "remaining_time": "5:52:54"}
+{"current_steps": 1270, "total_steps": 4665, "loss": 0.725, "learning_rate": 5e-06, "epoch": 0.8167202572347267, "percentage": 27.22, "elapsed_time": "2:11:37", "remaining_time": "5:51:52"}
+{"current_steps": 1280, "total_steps": 4665, "loss": 0.7307, "learning_rate": 5e-06, "epoch": 0.8231511254019293, "percentage": 27.44, "elapsed_time": "2:12:39", "remaining_time": "5:50:49"}
+{"current_steps": 1290, "total_steps": 4665, "loss": 0.7203, "learning_rate": 5e-06, "epoch": 0.8295819935691319, "percentage": 27.65, "elapsed_time": "2:13:41", "remaining_time": "5:49:47"}
+{"current_steps": 1300, "total_steps": 4665, "loss": 0.7242, "learning_rate": 5e-06, "epoch": 0.8360128617363344, "percentage": 27.87, "elapsed_time": "2:14:43", "remaining_time": "5:48:45"}
+{"current_steps": 1310, "total_steps": 4665, "loss": 0.7182, "learning_rate": 5e-06, "epoch": 0.842443729903537, "percentage": 28.08, "elapsed_time": "2:15:46", "remaining_time": "5:47:42"}
+{"current_steps": 1320, "total_steps": 4665, "loss": 0.7259, "learning_rate": 5e-06, "epoch": 0.8488745980707395, "percentage": 28.3, "elapsed_time": "2:16:48", "remaining_time": "5:46:40"}
+{"current_steps": 1330, "total_steps": 4665, "loss": 0.7164, "learning_rate": 5e-06, "epoch": 0.8553054662379421, "percentage": 28.51, "elapsed_time": "2:17:50", "remaining_time": "5:45:38"}
+{"current_steps": 1340, "total_steps": 4665, "loss": 0.7198, "learning_rate": 5e-06, "epoch": 0.8617363344051447, "percentage": 28.72, "elapsed_time": "2:18:52", "remaining_time": "5:44:36"}
+{"current_steps": 1350, "total_steps": 4665, "loss": 0.7255, "learning_rate": 5e-06, "epoch": 0.8681672025723473, "percentage": 28.94, "elapsed_time": "2:19:54", "remaining_time": "5:43:33"}
+{"current_steps": 1360, "total_steps": 4665, "loss": 0.7273, "learning_rate": 5e-06, "epoch": 0.8745980707395499, "percentage": 29.15, "elapsed_time": "2:20:56", "remaining_time": "5:42:31"}
+{"current_steps": 1370, "total_steps": 4665, "loss": 0.7247, "learning_rate": 5e-06, "epoch": 0.8810289389067524, "percentage": 29.37, "elapsed_time": "2:21:59", "remaining_time": "5:41:29"}
+{"current_steps": 1380, "total_steps": 4665, "loss": 0.7268, "learning_rate": 5e-06, "epoch": 0.887459807073955, "percentage": 29.58, "elapsed_time": "2:23:01", "remaining_time": "5:40:26"}
+{"current_steps": 1390, "total_steps": 4665, "loss": 0.7285, "learning_rate": 5e-06, "epoch": 0.8938906752411575, "percentage": 29.8, "elapsed_time": "2:24:03", "remaining_time": "5:39:24"}
+{"current_steps": 1400, "total_steps": 4665, "loss": 0.7249, "learning_rate": 5e-06, "epoch": 0.9003215434083601, "percentage": 30.01, "elapsed_time": "2:25:05", "remaining_time": "5:38:22"}
+{"current_steps": 1410, "total_steps": 4665, "loss": 0.7249, "learning_rate": 5e-06, "epoch": 0.9067524115755627, "percentage": 30.23, "elapsed_time": "2:26:07", "remaining_time": "5:37:20"}
+{"current_steps": 1420, "total_steps": 4665, "loss": 0.7245, "learning_rate": 5e-06, "epoch": 0.9131832797427653, "percentage": 30.44, "elapsed_time": "2:27:09", "remaining_time": "5:36:17"}
+{"current_steps": 1430, "total_steps": 4665, "loss": 0.7305, "learning_rate": 5e-06, "epoch": 0.9196141479099679, "percentage": 30.65, "elapsed_time": "2:28:11", "remaining_time": "5:35:15"}
+{"current_steps": 1440, "total_steps": 4665, "loss": 0.7294, "learning_rate": 5e-06, "epoch": 0.9260450160771704, "percentage": 30.87, "elapsed_time": "2:29:14", "remaining_time": "5:34:13"}
+{"current_steps": 1450, "total_steps": 4665, "loss": 0.7215, "learning_rate": 5e-06, "epoch": 0.932475884244373, "percentage": 31.08, "elapsed_time": "2:30:16", "remaining_time": "5:33:11"}
+{"current_steps": 1460, "total_steps": 4665, "loss": 0.7292, "learning_rate": 5e-06, "epoch": 0.9389067524115756, "percentage": 31.3, "elapsed_time": "2:31:18", "remaining_time": "5:32:08"}
+{"current_steps": 1470, "total_steps": 4665, "loss": 0.7155, "learning_rate": 5e-06, "epoch": 0.9453376205787781, "percentage": 31.51, "elapsed_time": "2:32:20", "remaining_time": "5:31:06"}
+{"current_steps": 1480, "total_steps": 4665, "loss": 0.7198, "learning_rate": 5e-06, "epoch": 0.9517684887459807, "percentage": 31.73, "elapsed_time": "2:33:22", "remaining_time": "5:30:04"}
+{"current_steps": 1490, "total_steps": 4665, "loss": 0.7297, "learning_rate": 5e-06, "epoch": 0.9581993569131833, "percentage": 31.94, "elapsed_time": "2:34:24", "remaining_time": "5:29:02"}
+{"current_steps": 1500, "total_steps": 4665, "loss": 0.7287, "learning_rate": 5e-06, "epoch": 0.9646302250803859, "percentage": 32.15, "elapsed_time": "2:35:27", "remaining_time": "5:28:00"}
+{"current_steps": 1510, "total_steps": 4665, "loss": 0.7209, "learning_rate": 5e-06, "epoch": 0.9710610932475884, "percentage": 32.37, "elapsed_time": "2:36:29", "remaining_time": "5:26:57"}
+{"current_steps": 1520, "total_steps": 4665, "loss": 0.7246, "learning_rate": 5e-06, "epoch": 0.977491961414791, "percentage": 32.58, "elapsed_time": "2:37:31", "remaining_time": "5:25:55"}
+{"current_steps": 1530, "total_steps": 4665, "loss": 0.7281, "learning_rate": 5e-06, "epoch": 0.9839228295819936, "percentage": 32.8, "elapsed_time": "2:38:33", "remaining_time": "5:24:53"}
+{"current_steps": 1540, "total_steps": 4665, "loss": 0.7264, "learning_rate": 5e-06, "epoch": 0.9903536977491961, "percentage": 33.01, "elapsed_time": "2:39:35", "remaining_time": "5:23:51"}
+{"current_steps": 1550, "total_steps": 4665, "loss": 0.7345, "learning_rate": 5e-06, "epoch": 0.9967845659163987, "percentage": 33.23, "elapsed_time": "2:40:37", "remaining_time": "5:22:48"}
+{"current_steps": 1555, "total_steps": 4665, "eval_loss": 0.7232183814048767, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "2:43:28", "remaining_time": "5:26:57"}
+{"current_steps": 1560, "total_steps": 4665, "loss": 0.7137, "learning_rate": 5e-06, "epoch": 1.0032154340836013, "percentage": 33.44, "elapsed_time": "2:48:27", "remaining_time": "5:35:17"}
+{"current_steps": 1570, "total_steps": 4665, "loss": 0.682, "learning_rate": 5e-06, "epoch": 1.0096463022508038, "percentage": 33.65, "elapsed_time": "2:49:29", "remaining_time": "5:34:07"}
+{"current_steps": 1580, "total_steps": 4665, "loss": 0.6971, "learning_rate": 5e-06, "epoch": 1.0160771704180065, "percentage": 33.87, "elapsed_time": "2:50:31", "remaining_time": "5:32:57"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f551435f7b9e3b919e6badb2e182da9653324207589f1c9c029af14ac7ffe0
+size 6904