Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 438250533027840.0,
+    "train_loss": 0.3635299830593717,
+    "train_runtime": 20239.4479,
+    "train_samples_per_second": 14.013,
+    "train_steps_per_second": 0.11
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "/GLOBALFS/gznwp_3/qxj/lgzhong/handbook/models/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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": "4.43.4",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.4"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a19adfc08f3f8ea01bbc54dc217c659b5f21b6ab725837aea4a348e662c735
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6a1e13b0fe868bed0e5e118e534d42ea7d27d305318ee8444e9e70733bc9c8
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d9035883d67512496345ae286ccd1cb59f89f332a3845b833b0b1ddffeeb46
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1ba38d77974ed1e2a6ee54956c03d6592ebf1b0501195cca423aef66c3fdc0
+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 +1,2062 @@
+{
+  "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": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 438250533027840.0,
+    "train_loss": 0.3635299830593717,
+    "train_runtime": 20239.4479,
+    "train_samples_per_second": 14.013,
+    "train_steps_per_second": 0.11
+}

trainer_state.json

@@ -0,0 +1,1589 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2217,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013531799729364006,
+      "grad_norm": 3.034516595682754,
+      "learning_rate": 2.2522522522522524e-07,
+      "loss": 0.6411,
+      "step": 10
+    },
+    {
+      "epoch": 0.02706359945872801,
+      "grad_norm": 2.7841028225351487,
+      "learning_rate": 4.504504504504505e-07,
+      "loss": 0.6332,
+      "step": 20
+    },
+    {
+      "epoch": 0.04059539918809202,
+      "grad_norm": 1.8710512230715446,
+      "learning_rate": 6.756756756756758e-07,
+      "loss": 0.6135,
+      "step": 30
+    },
+    {
+      "epoch": 0.05412719891745602,
+      "grad_norm": 1.5248415557438793,
+      "learning_rate": 9.00900900900901e-07,
+      "loss": 0.6095,
+      "step": 40
+    },
+    {
+      "epoch": 0.06765899864682003,
+      "grad_norm": 1.330731637337357,
+      "learning_rate": 1.1261261261261262e-06,
+      "loss": 0.5672,
+      "step": 50
+    },
+    {
+      "epoch": 0.08119079837618404,
+      "grad_norm": 1.1702536060306041,
+      "learning_rate": 1.3513513513513515e-06,
+      "loss": 0.5592,
+      "step": 60
+    },
+    {
+      "epoch": 0.09472259810554803,
+      "grad_norm": 1.2129816143771526,
+      "learning_rate": 1.5765765765765766e-06,
+      "loss": 0.527,
+      "step": 70
+    },
+    {
+      "epoch": 0.10825439783491204,
+      "grad_norm": 1.234538155408458,
+      "learning_rate": 1.801801801801802e-06,
+      "loss": 0.5421,
+      "step": 80
+    },
+    {
+      "epoch": 0.12178619756427606,
+      "grad_norm": 1.1711228120854185,
+      "learning_rate": 2.0270270270270273e-06,
+      "loss": 0.5292,
+      "step": 90
+    },
+    {
+      "epoch": 0.13531799729364005,
+      "grad_norm": 1.2936648719718322,
+      "learning_rate": 2.2522522522522524e-06,
+      "loss": 0.5479,
+      "step": 100
+    },
+    {
+      "epoch": 0.14884979702300405,
+      "grad_norm": 1.291284989397587,
+      "learning_rate": 2.4774774774774775e-06,
+      "loss": 0.5416,
+      "step": 110
+    },
+    {
+      "epoch": 0.16238159675236807,
+      "grad_norm": 1.34797590127609,
+      "learning_rate": 2.702702702702703e-06,
+      "loss": 0.5152,
+      "step": 120
+    },
+    {
+      "epoch": 0.17591339648173207,
+      "grad_norm": 1.360973654533329,
+      "learning_rate": 2.927927927927928e-06,
+      "loss": 0.5129,
+      "step": 130
+    },
+    {
+      "epoch": 0.18944519621109607,
+      "grad_norm": 1.2536822051142262,
+      "learning_rate": 3.1531531531531532e-06,
+      "loss": 0.5281,
+      "step": 140
+    },
+    {
+      "epoch": 0.2029769959404601,
+      "grad_norm": 1.3088135261215759,
+      "learning_rate": 3.3783783783783788e-06,
+      "loss": 0.5209,
+      "step": 150
+    },
+    {
+      "epoch": 0.2165087956698241,
+      "grad_norm": 1.288765418316905,
+      "learning_rate": 3.603603603603604e-06,
+      "loss": 0.5174,
+      "step": 160
+    },
+    {
+      "epoch": 0.23004059539918809,
+      "grad_norm": 1.393215959864774,
+      "learning_rate": 3.828828828828829e-06,
+      "loss": 0.5207,
+      "step": 170
+    },
+    {
+      "epoch": 0.2435723951285521,
+      "grad_norm": 1.2564229102790085,
+      "learning_rate": 4.0540540540540545e-06,
+      "loss": 0.5273,
+      "step": 180
+    },
+    {
+      "epoch": 0.2571041948579161,
+      "grad_norm": 1.2582309298347993,
+      "learning_rate": 4.27927927927928e-06,
+      "loss": 0.4934,
+      "step": 190
+    },
+    {
+      "epoch": 0.2706359945872801,
+      "grad_norm": 1.227173613438421,
+      "learning_rate": 4.504504504504505e-06,
+      "loss": 0.5112,
+      "step": 200
+    },
+    {
+      "epoch": 0.28416779431664413,
+      "grad_norm": 1.3112186763708722,
+      "learning_rate": 4.72972972972973e-06,
+      "loss": 0.4982,
+      "step": 210
+    },
+    {
+      "epoch": 0.2976995940460081,
+      "grad_norm": 1.3637637039109458,
+      "learning_rate": 4.954954954954955e-06,
+      "loss": 0.5229,
+      "step": 220
+    },
+    {
+      "epoch": 0.3112313937753721,
+      "grad_norm": 1.375489718620912,
+      "learning_rate": 4.999801619861762e-06,
+      "loss": 0.5042,
+      "step": 230
+    },
+    {
+      "epoch": 0.32476319350473615,
+      "grad_norm": 1.2608972862462173,
+      "learning_rate": 4.99899575450882e-06,
+      "loss": 0.5127,
+      "step": 240
+    },
+    {
+      "epoch": 0.3382949932341001,
+      "grad_norm": 1.2911890277318863,
+      "learning_rate": 4.9975702048619155e-06,
+      "loss": 0.5033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35182679296346414,
+      "grad_norm": 1.3078317427998958,
+      "learning_rate": 4.995525324419338e-06,
+      "loss": 0.5002,
+      "step": 260
+    },
+    {
+      "epoch": 0.36535859269282817,
+      "grad_norm": 1.3588495282283148,
+      "learning_rate": 4.992861620256898e-06,
+      "loss": 0.5065,
+      "step": 270
+    },
+    {
+      "epoch": 0.37889039242219213,
+      "grad_norm": 1.3626322380792617,
+      "learning_rate": 4.98957975290218e-06,
+      "loss": 0.511,
+      "step": 280
+    },
+    {
+      "epoch": 0.39242219215155616,
+      "grad_norm": 1.3701159835791592,
+      "learning_rate": 4.985680536170754e-06,
+      "loss": 0.5137,
+      "step": 290
+    },
+    {
+      "epoch": 0.4059539918809202,
+      "grad_norm": 1.2997955232042016,
+      "learning_rate": 4.981164936964371e-06,
+      "loss": 0.4965,
+      "step": 300
+    },
+    {
+      "epoch": 0.41948579161028415,
+      "grad_norm": 1.3519542829203703,
+      "learning_rate": 4.976034075031193e-06,
+      "loss": 0.512,
+      "step": 310
+    },
+    {
+      "epoch": 0.4330175913396482,
+      "grad_norm": 1.2630076374904904,
+      "learning_rate": 4.970289222688129e-06,
+      "loss": 0.5028,
+      "step": 320
+    },
+    {
+      "epoch": 0.4465493910690122,
+      "grad_norm": 1.2707537109175924,
+      "learning_rate": 4.963931804505335e-06,
+      "loss": 0.5032,
+      "step": 330
+    },
+    {
+      "epoch": 0.46008119079837617,
+      "grad_norm": 1.2589722075840526,
+      "learning_rate": 4.956963396952954e-06,
+      "loss": 0.4913,
+      "step": 340
+    },
+    {
+      "epoch": 0.4736129905277402,
+      "grad_norm": 1.250431061653177,
+      "learning_rate": 4.949385728010199e-06,
+      "loss": 0.4805,
+      "step": 350
+    },
+    {
+      "epoch": 0.4871447902571042,
+      "grad_norm": 1.3372965532968473,
+      "learning_rate": 4.941200676736856e-06,
+      "loss": 0.4991,
+      "step": 360
+    },
+    {
+      "epoch": 0.5006765899864682,
+      "grad_norm": 1.342662150633839,
+      "learning_rate": 4.932410272807328e-06,
+      "loss": 0.5066,
+      "step": 370
+    },
+    {
+      "epoch": 0.5142083897158322,
+      "grad_norm": 1.2238441786277905,
+      "learning_rate": 4.9230166960073325e-06,
+      "loss": 0.4863,
+      "step": 380
+    },
+    {
+      "epoch": 0.5277401894451962,
+      "grad_norm": 1.359535295509501,
+      "learning_rate": 4.913022275693372e-06,
+      "loss": 0.4949,
+      "step": 390
+    },
+    {
+      "epoch": 0.5412719891745602,
+      "grad_norm": 1.2168352667558966,
+      "learning_rate": 4.902429490215112e-06,
+      "loss": 0.4887,
+      "step": 400
+    },
+    {
+      "epoch": 0.5548037889039242,
+      "grad_norm": 1.4624621853482647,
+      "learning_rate": 4.891240966300822e-06,
+      "loss": 0.4969,
+      "step": 410
+    },
+    {
+      "epoch": 0.5683355886332883,
+      "grad_norm": 1.238588018136266,
+      "learning_rate": 4.879459478406012e-06,
+      "loss": 0.5067,
+      "step": 420
+    },
+    {
+      "epoch": 0.5818673883626523,
+      "grad_norm": 1.3181900309459351,
+      "learning_rate": 4.867087948025444e-06,
+      "loss": 0.4791,
+      "step": 430
+    },
+    {
+      "epoch": 0.5953991880920162,
+      "grad_norm": 1.2954274899523053,
+      "learning_rate": 4.854129442968679e-06,
+      "loss": 0.4927,
+      "step": 440
+    },
+    {
+      "epoch": 0.6089309878213802,
+      "grad_norm": 1.4125967606025722,
+      "learning_rate": 4.8405871765993435e-06,
+      "loss": 0.4879,
+      "step": 450
+    },
+    {
+      "epoch": 0.6224627875507442,
+      "grad_norm": 1.3930229082121182,
+      "learning_rate": 4.8264645070382964e-06,
+      "loss": 0.5073,
+      "step": 460
+    },
+    {
+      "epoch": 0.6359945872801083,
+      "grad_norm": 1.0709300883023405,
+      "learning_rate": 4.8117649363309105e-06,
+      "loss": 0.4729,
+      "step": 470
+    },
+    {
+      "epoch": 0.6495263870094723,
+      "grad_norm": 1.2926318844200286,
+      "learning_rate": 4.796492109578655e-06,
+      "loss": 0.4956,
+      "step": 480
+    },
+    {
+      "epoch": 0.6630581867388363,
+      "grad_norm": 1.2313258024791178,
+      "learning_rate": 4.780649814035205e-06,
+      "loss": 0.5152,
+      "step": 490
+    },
+    {
+      "epoch": 0.6765899864682002,
+      "grad_norm": 1.178544127732,
+      "learning_rate": 4.764241978167314e-06,
+      "loss": 0.4859,
+      "step": 500
+    },
+    {
+      "epoch": 0.6901217861975643,
+      "grad_norm": 1.3295118207561514,
+      "learning_rate": 4.747272670680646e-06,
+      "loss": 0.4676,
+      "step": 510
+    },
+    {
+      "epoch": 0.7036535859269283,
+      "grad_norm": 1.2304742068887151,
+      "learning_rate": 4.729746099510853e-06,
+      "loss": 0.4678,
+      "step": 520
+    },
+    {
+      "epoch": 0.7171853856562923,
+      "grad_norm": 1.3372876193995562,
+      "learning_rate": 4.711666610780115e-06,
+      "loss": 0.4831,
+      "step": 530
+    },
+    {
+      "epoch": 0.7307171853856563,
+      "grad_norm": 1.1886552687072083,
+      "learning_rate": 4.693038687719424e-06,
+      "loss": 0.4767,
+      "step": 540
+    },
+    {
+      "epoch": 0.7442489851150202,
+      "grad_norm": 1.1599254136343242,
+      "learning_rate": 4.673866949556854e-06,
+      "loss": 0.4936,
+      "step": 550
+    },
+    {
+      "epoch": 0.7577807848443843,
+      "grad_norm": 1.3619743128031154,
+      "learning_rate": 4.654156150372123e-06,
+      "loss": 0.4932,
+      "step": 560
+    },
+    {
+      "epoch": 0.7713125845737483,
+      "grad_norm": 1.2317704190385679,
+      "learning_rate": 4.633911177917701e-06,
+      "loss": 0.4823,
+      "step": 570
+    },
+    {
+      "epoch": 0.7848443843031123,
+      "grad_norm": 1.1895331578985897,
+      "learning_rate": 4.613137052406783e-06,
+      "loss": 0.4828,
+      "step": 580
+    },
+    {
+      "epoch": 0.7983761840324763,
+      "grad_norm": 1.2879457390422215,
+      "learning_rate": 4.5918389252684115e-06,
+      "loss": 0.4779,
+      "step": 590
+    },
+    {
+      "epoch": 0.8119079837618404,
+      "grad_norm": 1.2202436257043876,
+      "learning_rate": 4.570022077870051e-06,
+      "loss": 0.4875,
+      "step": 600
+    },
+    {
+      "epoch": 0.8254397834912043,
+      "grad_norm": 1.191014968745712,
+      "learning_rate": 4.547691920207958e-06,
+      "loss": 0.4726,
+      "step": 610
+    },
+    {
+      "epoch": 0.8389715832205683,
+      "grad_norm": 1.3456732382536576,
+      "learning_rate": 4.524853989565644e-06,
+      "loss": 0.4716,
+      "step": 620
+    },
+    {
+      "epoch": 0.8525033829499323,
+      "grad_norm": 1.1703319949253694,
+      "learning_rate": 4.501513949140776e-06,
+      "loss": 0.4715,
+      "step": 630
+    },
+    {
+      "epoch": 0.8660351826792964,
+      "grad_norm": 1.2604743747219656,
+      "learning_rate": 4.477677586640854e-06,
+      "loss": 0.483,
+      "step": 640
+    },
+    {
+      "epoch": 0.8795669824086604,
+      "grad_norm": 1.2589734283703884,
+      "learning_rate": 4.453350812848014e-06,
+      "loss": 0.4788,
+      "step": 650
+    },
+    {
+      "epoch": 0.8930987821380244,
+      "grad_norm": 1.3165298623822046,
+      "learning_rate": 4.428539660153315e-06,
+      "loss": 0.4781,
+      "step": 660
+    },
+    {
+      "epoch": 0.9066305818673883,
+      "grad_norm": 1.2879141623482424,
+      "learning_rate": 4.403250281060862e-06,
+      "loss": 0.4663,
+      "step": 670
+    },
+    {
+      "epoch": 0.9201623815967523,
+      "grad_norm": 1.2076038888483498,
+      "learning_rate": 4.377488946662152e-06,
+      "loss": 0.4808,
+      "step": 680
+    },
+    {
+      "epoch": 0.9336941813261164,
+      "grad_norm": 1.1851588037695613,
+      "learning_rate": 4.3512620450810115e-06,
+      "loss": 0.4793,
+      "step": 690
+    },
+    {
+      "epoch": 0.9472259810554804,
+      "grad_norm": 1.2950814486817164,
+      "learning_rate": 4.324576079889508e-06,
+      "loss": 0.4922,
+      "step": 700
+    },
+    {
+      "epoch": 0.9607577807848444,
+      "grad_norm": 1.201177645302697,
+      "learning_rate": 4.297437668495241e-06,
+      "loss": 0.4789,
+      "step": 710
+    },
+    {
+      "epoch": 0.9742895805142084,
+      "grad_norm": 1.217638325880889,
+      "learning_rate": 4.269853540500404e-06,
+      "loss": 0.4777,
+      "step": 720
+    },
+    {
+      "epoch": 0.9878213802435724,
+      "grad_norm": 1.2410357155495917,
+      "learning_rate": 4.2418305360330135e-06,
+      "loss": 0.4677,
+      "step": 730
+    },
+    {
+      "epoch": 1.0013531799729365,
+      "grad_norm": 1.4640185730269493,
+      "learning_rate": 4.21337560405075e-06,
+      "loss": 0.4706,
+      "step": 740
+    },
+    {
+      "epoch": 1.0148849797023005,
+      "grad_norm": 1.38525301927104,
+      "learning_rate": 4.184495800617795e-06,
+      "loss": 0.3663,
+      "step": 750
+    },
+    {
+      "epoch": 1.0284167794316643,
+      "grad_norm": 1.3150399206192376,
+      "learning_rate": 4.1551982871551195e-06,
+      "loss": 0.3446,
+      "step": 760
+    },
+    {
+      "epoch": 1.0419485791610283,
+      "grad_norm": 1.2508231428791732,
+      "learning_rate": 4.125490328664639e-06,
+      "loss": 0.3433,
+      "step": 770
+    },
+    {
+      "epoch": 1.0554803788903924,
+      "grad_norm": 1.1828710966111038,
+      "learning_rate": 4.095379291927689e-06,
+      "loss": 0.3372,
+      "step": 780
+    },
+    {
+      "epoch": 1.0690121786197564,
+      "grad_norm": 1.3234842465450887,
+      "learning_rate": 4.064872643678261e-06,
+      "loss": 0.3492,
+      "step": 790
+    },
+    {
+      "epoch": 1.0825439783491204,
+      "grad_norm": 1.3510823566344805,
+      "learning_rate": 4.033977948751445e-06,
+      "loss": 0.3538,
+      "step": 800
+    },
+    {
+      "epoch": 1.0960757780784844,
+      "grad_norm": 1.162520339907919,
+      "learning_rate": 4.002702868207563e-06,
+      "loss": 0.3462,
+      "step": 810
+    },
+    {
+      "epoch": 1.1096075778078485,
+      "grad_norm": 1.2976046378570087,
+      "learning_rate": 3.971055157432421e-06,
+      "loss": 0.3474,
+      "step": 820
+    },
+    {
+      "epoch": 1.1231393775372125,
+      "grad_norm": 1.2857491708515112,
+      "learning_rate": 3.939042664214185e-06,
+      "loss": 0.3365,
+      "step": 830
+    },
+    {
+      "epoch": 1.1366711772665765,
+      "grad_norm": 1.2956865515811835,
+      "learning_rate": 3.9066733267973335e-06,
+      "loss": 0.3483,
+      "step": 840
+    },
+    {
+      "epoch": 1.1502029769959405,
+      "grad_norm": 1.2863826250955843,
+      "learning_rate": 3.873955171914196e-06,
+      "loss": 0.3515,
+      "step": 850
+    },
+    {
+      "epoch": 1.1637347767253043,
+      "grad_norm": 1.48236681103959,
+      "learning_rate": 3.840896312794523e-06,
+      "loss": 0.3502,
+      "step": 860
+    },
+    {
+      "epoch": 1.1772665764546684,
+      "grad_norm": 1.333493280950809,
+      "learning_rate": 3.8075049471536317e-06,
+      "loss": 0.3402,
+      "step": 870
+    },
+    {
+      "epoch": 1.1907983761840324,
+      "grad_norm": 1.3845427764767562,
+      "learning_rate": 3.773789355159587e-06,
+      "loss": 0.3634,
+      "step": 880
+    },
+    {
+      "epoch": 1.2043301759133964,
+      "grad_norm": 1.1768813996050986,
+      "learning_rate": 3.7397578973799432e-06,
+      "loss": 0.3426,
+      "step": 890
+    },
+    {
+      "epoch": 1.2178619756427604,
+      "grad_norm": 1.2400576449491367,
+      "learning_rate": 3.7054190127085414e-06,
+      "loss": 0.3643,
+      "step": 900
+    },
+    {
+      "epoch": 1.2313937753721245,
+      "grad_norm": 1.3771269453073722,
+      "learning_rate": 3.6707812162728963e-06,
+      "loss": 0.3618,
+      "step": 910
+    },
+    {
+      "epoch": 1.2449255751014885,
+      "grad_norm": 1.342260391925942,
+      "learning_rate": 3.6358530973226634e-06,
+      "loss": 0.3619,
+      "step": 920
+    },
+    {
+      "epoch": 1.2584573748308525,
+      "grad_norm": 1.305612405058302,
+      "learning_rate": 3.600643317099742e-06,
+      "loss": 0.343,
+      "step": 930
+    },
+    {
+      "epoch": 1.2719891745602165,
+      "grad_norm": 1.2499532104940625,
+      "learning_rate": 3.5651606066905125e-06,
+      "loss": 0.3469,
+      "step": 940
+    },
+    {
+      "epoch": 1.2855209742895806,
+      "grad_norm": 1.3139038237546603,
+      "learning_rate": 3.529413764860763e-06,
+      "loss": 0.3547,
+      "step": 950
+    },
+    {
+      "epoch": 1.2990527740189446,
+      "grad_norm": 1.3891975036748492,
+      "learning_rate": 3.493411655873826e-06,
+      "loss": 0.3565,
+      "step": 960
+    },
+    {
+      "epoch": 1.3125845737483086,
+      "grad_norm": 1.31663081113206,
+      "learning_rate": 3.4571632072924853e-06,
+      "loss": 0.3459,
+      "step": 970
+    },
+    {
+      "epoch": 1.3261163734776726,
+      "grad_norm": 1.4316096903150302,
+      "learning_rate": 3.4206774077651706e-06,
+      "loss": 0.3435,
+      "step": 980
+    },
+    {
+      "epoch": 1.3396481732070367,
+      "grad_norm": 1.2148334230866564,
+      "learning_rate": 3.383963304797016e-06,
+      "loss": 0.3505,
+      "step": 990
+    },
+    {
+      "epoch": 1.3531799729364005,
+      "grad_norm": 1.371605209380619,
+      "learning_rate": 3.347030002506321e-06,
+      "loss": 0.3367,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3667117726657645,
+      "grad_norm": 1.2492881761277035,
+      "learning_rate": 3.309886659366967e-06,
+      "loss": 0.3409,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3802435723951285,
+      "grad_norm": 1.3599908217112529,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.3485,
+      "step": 1020
+    },
+    {
+      "epoch": 1.3937753721244925,
+      "grad_norm": 1.3587500825976617,
+      "learning_rate": 3.2350067425764932e-06,
+      "loss": 0.3564,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4073071718538566,
+      "grad_norm": 1.286120602039562,
+      "learning_rate": 3.1972887371475404e-06,
+      "loss": 0.3445,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4208389715832206,
+      "grad_norm": 1.3034585004391024,
+      "learning_rate": 3.1593978227098442e-06,
+      "loss": 0.3499,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4343707713125846,
+      "grad_norm": 1.4093897542299632,
+      "learning_rate": 3.1213433951995585e-06,
+      "loss": 0.3476,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4479025710419486,
+      "grad_norm": 1.2311850270587112,
+      "learning_rate": 3.0831348910997206e-06,
+      "loss": 0.3364,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4614343707713127,
+      "grad_norm": 1.222347605205662,
+      "learning_rate": 3.0447817851002493e-06,
+      "loss": 0.3479,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4749661705006765,
+      "grad_norm": 1.296829055261883,
+      "learning_rate": 3.0062935877484807e-06,
+      "loss": 0.3483,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4884979702300405,
+      "grad_norm": 1.4143686463454304,
+      "learning_rate": 2.9676798430908e-06,
+      "loss": 0.3468,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5020297699594045,
+      "grad_norm": 1.3314404969152827,
+      "learning_rate": 2.9289501263059796e-06,
+      "loss": 0.3526,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5155615696887685,
+      "grad_norm": 1.2209137417793836,
+      "learning_rate": 2.890114041330782e-06,
+      "loss": 0.3527,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5290933694181326,
+      "grad_norm": 1.3653030646734905,
+      "learning_rate": 2.8511812184784476e-06,
+      "loss": 0.3486,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5426251691474966,
+      "grad_norm": 1.3012446208990969,
+      "learning_rate": 2.8121613120506274e-06,
+      "loss": 0.3541,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5561569688768606,
+      "grad_norm": 1.1960147547589701,
+      "learning_rate": 2.7730639979433778e-06,
+      "loss": 0.3473,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5696887686062246,
+      "grad_norm": 1.4960354983589137,
+      "learning_rate": 2.733898971247795e-06,
+      "loss": 0.3456,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5832205683355887,
+      "grad_norm": 1.2152217200297626,
+      "learning_rate": 2.6946759438458898e-06,
+      "loss": 0.3433,
+      "step": 1170
+    },
+    {
+      "epoch": 1.5967523680649527,
+      "grad_norm": 1.3453974757862506,
+      "learning_rate": 2.655404642002304e-06,
+      "loss": 0.3409,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6102841677943167,
+      "grad_norm": 1.3428793347679469,
+      "learning_rate": 2.6160948039524497e-06,
+      "loss": 0.3419,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6238159675236807,
+      "grad_norm": 1.2285874250356115,
+      "learning_rate": 2.576756177487694e-06,
+      "loss": 0.3508,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6373477672530448,
+      "grad_norm": 1.3449344602808873,
+      "learning_rate": 2.5373985175381595e-06,
+      "loss": 0.3503,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6508795669824088,
+      "grad_norm": 1.296420958776628,
+      "learning_rate": 2.4980315837537682e-06,
+      "loss": 0.3562,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6644113667117728,
+      "grad_norm": 1.3437387415224382,
+      "learning_rate": 2.458665138084104e-06,
+      "loss": 0.3405,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6779431664411368,
+      "grad_norm": 1.388342667143761,
+      "learning_rate": 2.4193089423577125e-06,
+      "loss": 0.3609,
+      "step": 1240
+    },
+    {
+      "epoch": 1.6914749661705006,
+      "grad_norm": 1.2780103853967297,
+      "learning_rate": 2.379972755861427e-06,
+      "loss": 0.3464,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7050067658998647,
+      "grad_norm": 1.3272035289197703,
+      "learning_rate": 2.3406663329203235e-06,
+      "loss": 0.3495,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7185385656292287,
+      "grad_norm": 1.329132748454747,
+      "learning_rate": 2.3013994204789125e-06,
+      "loss": 0.3445,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7320703653585927,
+      "grad_norm": 1.398385700455576,
+      "learning_rate": 2.262181755684152e-06,
+      "loss": 0.3525,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7456021650879567,
+      "grad_norm": 1.3017040678134042,
+      "learning_rate": 2.2230230634709004e-06,
+      "loss": 0.3437,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7591339648173205,
+      "grad_norm": 1.2733756916822523,
+      "learning_rate": 2.1839330541503846e-06,
+      "loss": 0.3507,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7726657645466846,
+      "grad_norm": 1.2687781856621299,
+      "learning_rate": 2.14492142100231e-06,
+      "loss": 0.343,
+      "step": 1310
+    },
+    {
+      "epoch": 1.7861975642760486,
+      "grad_norm": 1.2837756754284302,
+      "learning_rate": 2.105997837871179e-06,
+      "loss": 0.3567,
+      "step": 1320
+    },
+    {
+      "epoch": 1.7997293640054126,
+      "grad_norm": 1.2388730929923404,
+      "learning_rate": 2.0671719567674396e-06,
+      "loss": 0.344,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8132611637347766,
+      "grad_norm": 1.2901053029094909,
+      "learning_rate": 2.028453405474043e-06,
+      "loss": 0.3517,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8267929634641407,
+      "grad_norm": 1.2731165360362213,
+      "learning_rate": 1.9898517851590085e-06,
+      "loss": 0.3386,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8403247631935047,
+      "grad_norm": 1.3976657362615021,
+      "learning_rate": 1.951376667994594e-06,
+      "loss": 0.341,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8538565629228687,
+      "grad_norm": 1.3707046787252906,
+      "learning_rate": 1.913037594783648e-06,
+      "loss": 0.3537,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8673883626522327,
+      "grad_norm": 1.2631835198560484,
+      "learning_rate": 1.8748440725937485e-06,
+      "loss": 0.3565,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8809201623815968,
+      "grad_norm": 1.2721719565376515,
+      "learning_rate": 1.8368055723997013e-06,
+      "loss": 0.3522,
+      "step": 1390
+    },
+    {
+      "epoch": 1.8944519621109608,
+      "grad_norm": 1.2577752707995227,
+      "learning_rate": 1.7989315267349936e-06,
+      "loss": 0.3454,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9079837618403248,
+      "grad_norm": 1.514027269766047,
+      "learning_rate": 1.7612313273527731e-06,
+      "loss": 0.3496,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9215155615696888,
+      "grad_norm": 1.292691163793762,
+      "learning_rate": 1.7237143228969488e-06,
+      "loss": 0.348,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9350473612990529,
+      "grad_norm": 1.3014087462969852,
+      "learning_rate": 1.686389816583973e-06,
+      "loss": 0.3577,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9485791610284169,
+      "grad_norm": 1.214993986220213,
+      "learning_rate": 1.6492670638958924e-06,
+      "loss": 0.3362,
+      "step": 1440
+    },
+    {
+      "epoch": 1.962110960757781,
+      "grad_norm": 1.221639454284981,
+      "learning_rate": 1.6123552702852375e-06,
+      "loss": 0.3347,
+      "step": 1450
+    },
+    {
+      "epoch": 1.975642760487145,
+      "grad_norm": 1.36951304107227,
+      "learning_rate": 1.5756635888923122e-06,
+      "loss": 0.3408,
+      "step": 1460
+    },
+    {
+      "epoch": 1.989174560216509,
+      "grad_norm": 1.291050299529943,
+      "learning_rate": 1.539201118275463e-06,
+      "loss": 0.3516,
+      "step": 1470
+    },
+    {
+      "epoch": 2.002706359945873,
+      "grad_norm": 1.5299892777665929,
+      "learning_rate": 1.502976900154876e-06,
+      "loss": 0.3294,
+      "step": 1480
+    },
+    {
+      "epoch": 2.016238159675237,
+      "grad_norm": 1.4268912812659167,
+      "learning_rate": 1.4669999171704742e-06,
+      "loss": 0.2451,
+      "step": 1490
+    },
+    {
+      "epoch": 2.029769959404601,
+      "grad_norm": 1.3062098172273324,
+      "learning_rate": 1.43127909065446e-06,
+      "loss": 0.2438,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0433017591339646,
+      "grad_norm": 1.4093327122429686,
+      "learning_rate": 1.395823278419065e-06,
+      "loss": 0.2458,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0568335588633286,
+      "grad_norm": 1.3446778247332223,
+      "learning_rate": 1.3606412725600471e-06,
+      "loss": 0.2483,
+      "step": 1520
+    },
+    {
+      "epoch": 2.0703653585926927,
+      "grad_norm": 1.288956301952182,
+      "learning_rate": 1.3257417972764853e-06,
+      "loss": 0.242,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0838971583220567,
+      "grad_norm": 1.2722385458217775,
+      "learning_rate": 1.2911335067074108e-06,
+      "loss": 0.2318,
+      "step": 1540
+    },
+    {
+      "epoch": 2.0974289580514207,
+      "grad_norm": 1.3902319886251955,
+      "learning_rate": 1.2568249827858153e-06,
+      "loss": 0.2331,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1109607577807847,
+      "grad_norm": 1.343020265634266,
+      "learning_rate": 1.2228247331105541e-06,
+      "loss": 0.242,
+      "step": 1560
+    },
+    {
+      "epoch": 2.1244925575101488,
+      "grad_norm": 1.3796390105439542,
+      "learning_rate": 1.1891411888366933e-06,
+      "loss": 0.2494,
+      "step": 1570
+    },
+    {
+      "epoch": 2.138024357239513,
+      "grad_norm": 1.287377449079076,
+      "learning_rate": 1.1557827025848048e-06,
+      "loss": 0.2373,
+      "step": 1580
+    },
+    {
+      "epoch": 2.151556156968877,
+      "grad_norm": 1.2636968613031825,
+      "learning_rate": 1.122757546369744e-06,
+      "loss": 0.2276,
+      "step": 1590
+    },
+    {
+      "epoch": 2.165087956698241,
+      "grad_norm": 1.3768480512381478,
+      "learning_rate": 1.0900739095494053e-06,
+      "loss": 0.2392,
+      "step": 1600
+    },
+    {
+      "epoch": 2.178619756427605,
+      "grad_norm": 1.3082506088448747,
+      "learning_rate": 1.0577398967939824e-06,
+      "loss": 0.2361,
+      "step": 1610
+    },
+    {
+      "epoch": 2.192151556156969,
+      "grad_norm": 1.4034690066329039,
+      "learning_rate": 1.0257635260762281e-06,
+      "loss": 0.2319,
+      "step": 1620
+    },
+    {
+      "epoch": 2.205683355886333,
+      "grad_norm": 1.2317759668032917,
+      "learning_rate": 9.941527266832064e-07,
+      "loss": 0.2493,
+      "step": 1630
+    },
+    {
+      "epoch": 2.219215155615697,
+      "grad_norm": 1.2971411614293273,
+      "learning_rate": 9.62915337250044e-07,
+      "loss": 0.2277,
+      "step": 1640
+    },
+    {
+      "epoch": 2.232746955345061,
+      "grad_norm": 1.3135829424346515,
+      "learning_rate": 9.320591038161575e-07,
+      "loss": 0.2328,
+      "step": 1650
+    },
+    {
+      "epoch": 2.246278755074425,
+      "grad_norm": 1.38689896774966,
+      "learning_rate": 9.015916779044429e-07,
+      "loss": 0.2376,
+      "step": 1660
+    },
+    {
+      "epoch": 2.259810554803789,
+      "grad_norm": 1.3904871269861285,
+      "learning_rate": 8.715206146238989e-07,
+      "loss": 0.2365,
+      "step": 1670
+    },
+    {
+      "epoch": 2.273342354533153,
+      "grad_norm": 1.2344911252878241,
+      "learning_rate": 8.418533707961635e-07,
+      "loss": 0.2398,
+      "step": 1680
+    },
+    {
+      "epoch": 2.286874154262517,
+      "grad_norm": 1.404914010406795,
+      "learning_rate": 8.125973031064241e-07,
+      "loss": 0.2375,
+      "step": 1690
+    },
+    {
+      "epoch": 2.300405953991881,
+      "grad_norm": 1.4005244602892066,
+      "learning_rate": 7.837596662791492e-07,
+      "loss": 0.2418,
+      "step": 1700
+    },
+    {
+      "epoch": 2.313937753721245,
+      "grad_norm": 1.3420607852511892,
+      "learning_rate": 7.553476112791156e-07,
+      "loss": 0.2332,
+      "step": 1710
+    },
+    {
+      "epoch": 2.3274695534506087,
+      "grad_norm": 1.3547101946313251,
+      "learning_rate": 7.273681835381569e-07,
+      "loss": 0.229,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3410013531799727,
+      "grad_norm": 1.4020705762318206,
+      "learning_rate": 6.998283212080873e-07,
+      "loss": 0.2328,
+      "step": 1730
+    },
+    {
+      "epoch": 2.3545331529093367,
+      "grad_norm": 1.3623596919516412,
+      "learning_rate": 6.727348534402217e-07,
+      "loss": 0.2525,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3680649526387008,
+      "grad_norm": 1.3512700634608603,
+      "learning_rate": 6.460944986919296e-07,
+      "loss": 0.2408,
+      "step": 1750
+    },
+    {
+      "epoch": 2.381596752368065,
+      "grad_norm": 1.3266784606321098,
+      "learning_rate": 6.199138630606389e-07,
+      "loss": 0.234,
+      "step": 1760
+    },
+    {
+      "epoch": 2.395128552097429,
+      "grad_norm": 1.3645670227625384,
+      "learning_rate": 5.941994386456962e-07,
+      "loss": 0.2339,
+      "step": 1770
+    },
+    {
+      "epoch": 2.408660351826793,
+      "grad_norm": 1.4293775086324754,
+      "learning_rate": 5.689576019385015e-07,
+      "loss": 0.2386,
+      "step": 1780
+    },
+    {
+      "epoch": 2.422192151556157,
+      "grad_norm": 1.4511738533160017,
+      "learning_rate": 5.441946122413086e-07,
+      "loss": 0.2456,
+      "step": 1790
+    },
+    {
+      "epoch": 2.435723951285521,
+      "grad_norm": 1.4144969812794062,
+      "learning_rate": 5.199166101150854e-07,
+      "loss": 0.242,
+      "step": 1800
+    },
+    {
+      "epoch": 2.449255751014885,
+      "grad_norm": 1.3760683860213159,
+      "learning_rate": 4.96129615856816e-07,
+      "loss": 0.2319,
+      "step": 1810
+    },
+    {
+      "epoch": 2.462787550744249,
+      "grad_norm": 1.2962323322234228,
+      "learning_rate": 4.7283952800663086e-07,
+      "loss": 0.239,
+      "step": 1820
+    },
+    {
+      "epoch": 2.476319350473613,
+      "grad_norm": 1.3785919346369462,
+      "learning_rate": 4.500521218851234e-07,
+      "loss": 0.2291,
+      "step": 1830
+    },
+    {
+      "epoch": 2.489851150202977,
+      "grad_norm": 1.3198852846590903,
+      "learning_rate": 4.2777304816122744e-07,
+      "loss": 0.2294,
+      "step": 1840
+    },
+    {
+      "epoch": 2.503382949932341,
+      "grad_norm": 1.3791429787991882,
+      "learning_rate": 4.0600783145099935e-07,
+      "loss": 0.2398,
+      "step": 1850
+    },
+    {
+      "epoch": 2.516914749661705,
+      "grad_norm": 1.3758327911725443,
+      "learning_rate": 3.847618689476612e-07,
+      "loss": 0.2311,
+      "step": 1860
+    },
+    {
+      "epoch": 2.530446549391069,
+      "grad_norm": 1.329309433256462,
+      "learning_rate": 3.640404290832433e-07,
+      "loss": 0.2322,
+      "step": 1870
+    },
+    {
+      "epoch": 2.543978349120433,
+      "grad_norm": 1.3667475875891038,
+      "learning_rate": 3.438486502221494e-07,
+      "loss": 0.2471,
+      "step": 1880
+    },
+    {
+      "epoch": 2.557510148849797,
+      "grad_norm": 1.4518282018049613,
+      "learning_rate": 3.2419153938698295e-07,
+      "loss": 0.2346,
+      "step": 1890
+    },
+    {
+      "epoch": 2.571041948579161,
+      "grad_norm": 1.334115365965958,
+      "learning_rate": 3.0507397101693565e-07,
+      "loss": 0.2383,
+      "step": 1900
+    },
+    {
+      "epoch": 2.584573748308525,
+      "grad_norm": 1.368769415739159,
+      "learning_rate": 2.865006857590619e-07,
+      "loss": 0.2344,
+      "step": 1910
+    },
+    {
+      "epoch": 2.598105548037889,
+      "grad_norm": 1.2174336094447944,
+      "learning_rate": 2.684762892927184e-07,
+      "loss": 0.2354,
+      "step": 1920
+    },
+    {
+      "epoch": 2.611637347767253,
+      "grad_norm": 1.3104470556604222,
+      "learning_rate": 2.510052511874822e-07,
+      "loss": 0.2297,
+      "step": 1930
+    },
+    {
+      "epoch": 2.6251691474966172,
+      "grad_norm": 1.3766509507609574,
+      "learning_rate": 2.3409190379481723e-07,
+      "loss": 0.2294,
+      "step": 1940
+    },
+    {
+      "epoch": 2.6387009472259813,
+      "grad_norm": 1.2110460902512004,
+      "learning_rate": 2.1774044117376407e-07,
+      "loss": 0.2273,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6522327469553453,
+      "grad_norm": 1.294674188348231,
+      "learning_rate": 2.019549180509267e-07,
+      "loss": 0.2304,
+      "step": 1960
+    },
+    {
+      "epoch": 2.6657645466847093,
+      "grad_norm": 1.4025491240100805,
+      "learning_rate": 1.8673924881500826e-07,
+      "loss": 0.2361,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6792963464140733,
+      "grad_norm": 1.3312582202000482,
+      "learning_rate": 1.7209720654614793e-07,
+      "loss": 0.2417,
+      "step": 1980
+    },
+    {
+      "epoch": 2.6928281461434374,
+      "grad_norm": 1.279370227399727,
+      "learning_rate": 1.580324220802959e-07,
+      "loss": 0.2306,
+      "step": 1990
+    },
+    {
+      "epoch": 2.706359945872801,
+      "grad_norm": 1.32387777543638,
+      "learning_rate": 1.4454838310886427e-07,
+      "loss": 0.2293,
+      "step": 2000
+    },
+    {
+      "epoch": 2.719891745602165,
+      "grad_norm": 1.4245015480114729,
+      "learning_rate": 1.3164843331387123e-07,
+      "loss": 0.2311,
+      "step": 2010
+    },
+    {
+      "epoch": 2.733423545331529,
+      "grad_norm": 1.3831803662571336,
+      "learning_rate": 1.1933577153879993e-07,
+      "loss": 0.2387,
+      "step": 2020
+    },
+    {
+      "epoch": 2.746955345060893,
+      "grad_norm": 1.341165321378542,
+      "learning_rate": 1.0761345099536691e-07,
+      "loss": 0.2406,
+      "step": 2030
+    },
+    {
+      "epoch": 2.760487144790257,
+      "grad_norm": 1.4225949777687765,
+      "learning_rate": 9.648437850640929e-08,
+      "loss": 0.2334,
+      "step": 2040
+    },
+    {
+      "epoch": 2.774018944519621,
+      "grad_norm": 1.2903746437594332,
+      "learning_rate": 8.595131378507038e-08,
+      "loss": 0.2302,
+      "step": 2050
+    },
+    {
+      "epoch": 2.787550744248985,
+      "grad_norm": 1.4459041867407572,
+      "learning_rate": 7.601686875046338e-08,
+      "loss": 0.2357,
+      "step": 2060
+    },
+    {
+      "epoch": 2.801082543978349,
+      "grad_norm": 1.43510005352293,
+      "learning_rate": 6.668350687998565e-08,
+      "loss": 0.2354,
+      "step": 2070
+    },
+    {
+      "epoch": 2.814614343707713,
+      "grad_norm": 1.3495037373612448,
+      "learning_rate": 5.7953542598441215e-08,
+      "loss": 0.2299,
+      "step": 2080
+    },
+    {
+      "epoch": 2.828146143437077,
+      "grad_norm": 1.2822048194805191,
+      "learning_rate": 4.9829140704127644e-08,
+      "loss": 0.2304,
+      "step": 2090
+    },
+    {
+      "epoch": 2.841677943166441,
+      "grad_norm": 1.4152294147048579,
+      "learning_rate": 4.231231583201989e-08,
+      "loss": 0.2373,
+      "step": 2100
+    },
+    {
+      "epoch": 2.855209742895805,
+      "grad_norm": 1.4204373591003197,
+      "learning_rate": 3.5404931954197696e-08,
+      "loss": 0.2359,
+      "step": 2110
+    },
+    {
+      "epoch": 2.8687415426251692,
+      "grad_norm": 1.3793380734018237,
+      "learning_rate": 2.9108701917630043e-08,
+      "loss": 0.2447,
+      "step": 2120
+    },
+    {
+      "epoch": 2.8822733423545333,
+      "grad_norm": 1.2804260757138324,
+      "learning_rate": 2.3425187019432415e-08,
+      "loss": 0.2446,
+      "step": 2130
+    },
+    {
+      "epoch": 2.8958051420838973,
+      "grad_norm": 1.3777377768354557,
+      "learning_rate": 1.8355796619708988e-08,
+      "loss": 0.2367,
+      "step": 2140
+    },
+    {
+      "epoch": 2.9093369418132613,
+      "grad_norm": 1.3764369341392175,
+      "learning_rate": 1.39017877920683e-08,
+      "loss": 0.2357,
+      "step": 2150
+    },
+    {
+      "epoch": 2.9228687415426253,
+      "grad_norm": 1.4731353222848615,
+      "learning_rate": 1.006426501190233e-08,
+      "loss": 0.2355,
+      "step": 2160
+    },
+    {
+      "epoch": 2.936400541271989,
+      "grad_norm": 1.3695944357270635,
+      "learning_rate": 6.844179882506685e-09,
+      "loss": 0.2312,
+      "step": 2170
+    },
+    {
+      "epoch": 2.949932341001353,
+      "grad_norm": 1.3973969195223515,
+      "learning_rate": 4.242330899106861e-09,
+      "loss": 0.2403,
+      "step": 2180
+    },
+    {
+      "epoch": 2.963464140730717,
+      "grad_norm": 1.330953340046642,
+      "learning_rate": 2.259363250854685e-09,
+      "loss": 0.2264,
+      "step": 2190
+    },
+    {
+      "epoch": 2.976995940460081,
+      "grad_norm": 1.305324417569301,
+      "learning_rate": 8.957686608371263e-10,
+      "loss": 0.2328,
+      "step": 2200
+    },
+    {
+      "epoch": 2.990527740189445,
+      "grad_norm": 1.349805214463894,
+      "learning_rate": 1.5188526414244842e-10,
+      "loss": 0.2348,
+      "step": 2210
+    },
+    {
+      "epoch": 3.0,
+      "step": 2217,
+      "total_flos": 438250533027840.0,
+      "train_loss": 0.3635299830593717,
+      "train_runtime": 20239.4479,
+      "train_samples_per_second": 14.013,
+      "train_steps_per_second": 0.11
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2217,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10086,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 438250533027840.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2e19d6a756d90fc02a891c7d33cb2246c057b150f2b155634ba4dadb1f5c29
+size 7160