Training in progress, step 500, checkpoint

checkpoint-500/config.json

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

checkpoint-500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

checkpoint-500/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696a83834835d9cfb4f3898af12f091ce41cb7bc917e533a94e15a6954269e6d
+size 4976698672

checkpoint-500/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0cab6eb04fbe360da573438be40528ba1f6d7824e346c0f4b4d8e7d59f9459
+size 4999802720

checkpoint-500/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84848938d824dca98e68aaedc9b8dc89d706456e6fa48a1c0d32848011e6b486
+size 4915916176

checkpoint-500/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e78c16db1d430a38b2b1b23f07d75705a2c998e0f7efdcd1ae76f75195b06e
+size 1168138808

checkpoint-500/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"
+  }
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073a9c27f5c1d1ef20f691d852d4d673177845f21060f8530b36e46de97f4d91
+size 16092243016

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983a4ca70134caca3d448a5d4ad8b72b0baaf98bc1854382ca50fb8e85b6f5b7
+size 14308

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0646dd0ba316f9b16196fbc6de365ed95580f96de0138a012392a2f7e7a83578
+size 1064

checkpoint-500/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": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

checkpoint-500/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|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,3533 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.005,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1e-05,
+      "grad_norm": 8.875,
+      "learning_rate": 9.999999997532599e-06,
+      "loss": 1.6459,
+      "step": 1
+    },
+    {
+      "epoch": 2e-05,
+      "grad_norm": 4.40625,
+      "learning_rate": 9.999999990130395e-06,
+      "loss": 1.6742,
+      "step": 2
+    },
+    {
+      "epoch": 3e-05,
+      "grad_norm": 4.3125,
+      "learning_rate": 9.99999997779339e-06,
+      "loss": 1.6223,
+      "step": 3
+    },
+    {
+      "epoch": 4e-05,
+      "grad_norm": 4.0625,
+      "learning_rate": 9.999999960521582e-06,
+      "loss": 1.5398,
+      "step": 4
+    },
+    {
+      "epoch": 5e-05,
+      "grad_norm": 3.375,
+      "learning_rate": 9.999999938314972e-06,
+      "loss": 1.5666,
+      "step": 5
+    },
+    {
+      "epoch": 6e-05,
+      "grad_norm": 1.859375,
+      "learning_rate": 9.999999911173561e-06,
+      "loss": 1.5981,
+      "step": 6
+    },
+    {
+      "epoch": 7e-05,
+      "grad_norm": 1.734375,
+      "learning_rate": 9.999999879097347e-06,
+      "loss": 1.644,
+      "step": 7
+    },
+    {
+      "epoch": 8e-05,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.999999842086332e-06,
+      "loss": 1.6331,
+      "step": 8
+    },
+    {
+      "epoch": 9e-05,
+      "grad_norm": 1.3125,
+      "learning_rate": 9.999999800140514e-06,
+      "loss": 1.626,
+      "step": 9
+    },
+    {
+      "epoch": 0.0001,
+      "grad_norm": 1.9296875,
+      "learning_rate": 9.999999753259893e-06,
+      "loss": 1.5778,
+      "step": 10
+    },
+    {
+      "epoch": 0.00011,
+      "grad_norm": 1.34375,
+      "learning_rate": 9.99999970144447e-06,
+      "loss": 1.6286,
+      "step": 11
+    },
+    {
+      "epoch": 0.00012,
+      "grad_norm": 1.203125,
+      "learning_rate": 9.999999644694247e-06,
+      "loss": 1.5614,
+      "step": 12
+    },
+    {
+      "epoch": 0.00013,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.999999583009221e-06,
+      "loss": 1.6447,
+      "step": 13
+    },
+    {
+      "epoch": 0.00014,
+      "grad_norm": 1.3359375,
+      "learning_rate": 9.999999516389394e-06,
+      "loss": 1.5258,
+      "step": 14
+    },
+    {
+      "epoch": 0.00015,
+      "grad_norm": 1.25,
+      "learning_rate": 9.999999444834763e-06,
+      "loss": 1.6336,
+      "step": 15
+    },
+    {
+      "epoch": 0.00016,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.999999368345333e-06,
+      "loss": 1.6073,
+      "step": 16
+    },
+    {
+      "epoch": 0.00017,
+      "grad_norm": 1.34375,
+      "learning_rate": 9.999999286921101e-06,
+      "loss": 1.5919,
+      "step": 17
+    },
+    {
+      "epoch": 0.00018,
+      "grad_norm": 0.96875,
+      "learning_rate": 9.999999200562065e-06,
+      "loss": 1.543,
+      "step": 18
+    },
+    {
+      "epoch": 0.00019,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.99999910926823e-06,
+      "loss": 1.6101,
+      "step": 19
+    },
+    {
+      "epoch": 0.0002,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.999999013039593e-06,
+      "loss": 1.5796,
+      "step": 20
+    },
+    {
+      "epoch": 0.00021,
+      "grad_norm": 2.578125,
+      "learning_rate": 9.999998911876154e-06,
+      "loss": 1.5748,
+      "step": 21
+    },
+    {
+      "epoch": 0.00022,
+      "grad_norm": 1.203125,
+      "learning_rate": 9.999998805777915e-06,
+      "loss": 1.5479,
+      "step": 22
+    },
+    {
+      "epoch": 0.00023,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.999998694744875e-06,
+      "loss": 1.5318,
+      "step": 23
+    },
+    {
+      "epoch": 0.00024,
+      "grad_norm": 1.125,
+      "learning_rate": 9.999998578777036e-06,
+      "loss": 1.6259,
+      "step": 24
+    },
+    {
+      "epoch": 0.00025,
+      "grad_norm": 2.21875,
+      "learning_rate": 9.999998457874392e-06,
+      "loss": 1.5525,
+      "step": 25
+    },
+    {
+      "epoch": 0.00026,
+      "grad_norm": 3.234375,
+      "learning_rate": 9.99999833203695e-06,
+      "loss": 1.5576,
+      "step": 26
+    },
+    {
+      "epoch": 0.00027,
+      "grad_norm": 2.046875,
+      "learning_rate": 9.999998201264707e-06,
+      "loss": 1.3934,
+      "step": 27
+    },
+    {
+      "epoch": 0.00028,
+      "grad_norm": 3.15625,
+      "learning_rate": 9.999998065557664e-06,
+      "loss": 1.5423,
+      "step": 28
+    },
+    {
+      "epoch": 0.00029,
+      "grad_norm": 1.2734375,
+      "learning_rate": 9.999997924915818e-06,
+      "loss": 1.5679,
+      "step": 29
+    },
+    {
+      "epoch": 0.0003,
+      "grad_norm": 1.625,
+      "learning_rate": 9.999997779339175e-06,
+      "loss": 1.5329,
+      "step": 30
+    },
+    {
+      "epoch": 0.00031,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.999997628827732e-06,
+      "loss": 1.4603,
+      "step": 31
+    },
+    {
+      "epoch": 0.00032,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.999997473381487e-06,
+      "loss": 1.5774,
+      "step": 32
+    },
+    {
+      "epoch": 0.00033,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.999997313000444e-06,
+      "loss": 1.5522,
+      "step": 33
+    },
+    {
+      "epoch": 0.00034,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.9999971476846e-06,
+      "loss": 1.5964,
+      "step": 34
+    },
+    {
+      "epoch": 0.00035,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.999996977433957e-06,
+      "loss": 1.6129,
+      "step": 35
+    },
+    {
+      "epoch": 0.00036,
+      "grad_norm": 1.78125,
+      "learning_rate": 9.999996802248514e-06,
+      "loss": 1.548,
+      "step": 36
+    },
+    {
+      "epoch": 0.00037,
+      "grad_norm": 0.94140625,
+      "learning_rate": 9.999996622128274e-06,
+      "loss": 1.5662,
+      "step": 37
+    },
+    {
+      "epoch": 0.00038,
+      "grad_norm": 4.84375,
+      "learning_rate": 9.999996437073236e-06,
+      "loss": 1.6197,
+      "step": 38
+    },
+    {
+      "epoch": 0.00039,
+      "grad_norm": 3.234375,
+      "learning_rate": 9.999996247083397e-06,
+      "loss": 1.5308,
+      "step": 39
+    },
+    {
+      "epoch": 0.0004,
+      "grad_norm": 1.375,
+      "learning_rate": 9.99999605215876e-06,
+      "loss": 1.5846,
+      "step": 40
+    },
+    {
+      "epoch": 0.00041,
+      "grad_norm": 1.34375,
+      "learning_rate": 9.999995852299324e-06,
+      "loss": 1.4274,
+      "step": 41
+    },
+    {
+      "epoch": 0.00042,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.999995647505092e-06,
+      "loss": 1.4986,
+      "step": 42
+    },
+    {
+      "epoch": 0.00043,
+      "grad_norm": 0.94140625,
+      "learning_rate": 9.99999543777606e-06,
+      "loss": 1.5135,
+      "step": 43
+    },
+    {
+      "epoch": 0.00044,
+      "grad_norm": 0.8125,
+      "learning_rate": 9.999995223112231e-06,
+      "loss": 1.5472,
+      "step": 44
+    },
+    {
+      "epoch": 0.00045,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.999995003513605e-06,
+      "loss": 1.5635,
+      "step": 45
+    },
+    {
+      "epoch": 0.00046,
+      "grad_norm": 3.34375,
+      "learning_rate": 9.999994778980182e-06,
+      "loss": 1.5506,
+      "step": 46
+    },
+    {
+      "epoch": 0.00047,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.99999454951196e-06,
+      "loss": 1.5071,
+      "step": 47
+    },
+    {
+      "epoch": 0.00048,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.999994315108943e-06,
+      "loss": 1.5532,
+      "step": 48
+    },
+    {
+      "epoch": 0.00049,
+      "grad_norm": 1.828125,
+      "learning_rate": 9.999994075771128e-06,
+      "loss": 1.6061,
+      "step": 49
+    },
+    {
+      "epoch": 0.0005,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.999993831498517e-06,
+      "loss": 1.5629,
+      "step": 50
+    },
+    {
+      "epoch": 0.00051,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.999993582291112e-06,
+      "loss": 1.5536,
+      "step": 51
+    },
+    {
+      "epoch": 0.00052,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.999993328148909e-06,
+      "loss": 1.5013,
+      "step": 52
+    },
+    {
+      "epoch": 0.00053,
+      "grad_norm": 1.171875,
+      "learning_rate": 9.999993069071912e-06,
+      "loss": 1.4943,
+      "step": 53
+    },
+    {
+      "epoch": 0.00054,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.999992805060117e-06,
+      "loss": 1.5057,
+      "step": 54
+    },
+    {
+      "epoch": 0.00055,
+      "grad_norm": 0.97265625,
+      "learning_rate": 9.99999253611353e-06,
+      "loss": 1.6486,
+      "step": 55
+    },
+    {
+      "epoch": 0.00056,
+      "grad_norm": 3.765625,
+      "learning_rate": 9.999992262232145e-06,
+      "loss": 1.4421,
+      "step": 56
+    },
+    {
+      "epoch": 0.00057,
+      "grad_norm": 2.21875,
+      "learning_rate": 9.999991983415968e-06,
+      "loss": 1.5346,
+      "step": 57
+    },
+    {
+      "epoch": 0.00058,
+      "grad_norm": 0.953125,
+      "learning_rate": 9.999991699664996e-06,
+      "loss": 1.5433,
+      "step": 58
+    },
+    {
+      "epoch": 0.00059,
+      "grad_norm": 3.171875,
+      "learning_rate": 9.99999141097923e-06,
+      "loss": 1.5306,
+      "step": 59
+    },
+    {
+      "epoch": 0.0006,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.99999111735867e-06,
+      "loss": 1.4453,
+      "step": 60
+    },
+    {
+      "epoch": 0.00061,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.999990818803316e-06,
+      "loss": 1.6219,
+      "step": 61
+    },
+    {
+      "epoch": 0.00062,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.99999051531317e-06,
+      "loss": 1.5296,
+      "step": 62
+    },
+    {
+      "epoch": 0.00063,
+      "grad_norm": 1.2109375,
+      "learning_rate": 9.999990206888231e-06,
+      "loss": 1.5165,
+      "step": 63
+    },
+    {
+      "epoch": 0.00064,
+      "grad_norm": 1.0234375,
+      "learning_rate": 9.999989893528499e-06,
+      "loss": 1.5697,
+      "step": 64
+    },
+    {
+      "epoch": 0.00065,
+      "grad_norm": 3.0625,
+      "learning_rate": 9.999989575233975e-06,
+      "loss": 1.5121,
+      "step": 65
+    },
+    {
+      "epoch": 0.00066,
+      "grad_norm": 0.9296875,
+      "learning_rate": 9.999989252004657e-06,
+      "loss": 1.4815,
+      "step": 66
+    },
+    {
+      "epoch": 0.00067,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.999988923840551e-06,
+      "loss": 1.4624,
+      "step": 67
+    },
+    {
+      "epoch": 0.00068,
+      "grad_norm": 0.80859375,
+      "learning_rate": 9.999988590741651e-06,
+      "loss": 1.5089,
+      "step": 68
+    },
+    {
+      "epoch": 0.00069,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.999988252707961e-06,
+      "loss": 1.4864,
+      "step": 69
+    },
+    {
+      "epoch": 0.0007,
+      "grad_norm": 2.328125,
+      "learning_rate": 9.999987909739481e-06,
+      "loss": 1.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.00071,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.99998756183621e-06,
+      "loss": 1.4759,
+      "step": 71
+    },
+    {
+      "epoch": 0.00072,
+      "grad_norm": 1.2890625,
+      "learning_rate": 9.999987208998151e-06,
+      "loss": 1.5659,
+      "step": 72
+    },
+    {
+      "epoch": 0.00073,
+      "grad_norm": 3.1875,
+      "learning_rate": 9.9999868512253e-06,
+      "loss": 1.6112,
+      "step": 73
+    },
+    {
+      "epoch": 0.00074,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.999986488517661e-06,
+      "loss": 1.503,
+      "step": 74
+    },
+    {
+      "epoch": 0.00075,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.999986120875233e-06,
+      "loss": 1.4688,
+      "step": 75
+    },
+    {
+      "epoch": 0.00076,
+      "grad_norm": 2.09375,
+      "learning_rate": 9.999985748298016e-06,
+      "loss": 1.543,
+      "step": 76
+    },
+    {
+      "epoch": 0.00077,
+      "grad_norm": 0.89453125,
+      "learning_rate": 9.999985370786011e-06,
+      "loss": 1.5166,
+      "step": 77
+    },
+    {
+      "epoch": 0.00078,
+      "grad_norm": 1.859375,
+      "learning_rate": 9.999984988339219e-06,
+      "loss": 1.5451,
+      "step": 78
+    },
+    {
+      "epoch": 0.00079,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.999984600957639e-06,
+      "loss": 1.5026,
+      "step": 79
+    },
+    {
+      "epoch": 0.0008,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.999984208641271e-06,
+      "loss": 1.4629,
+      "step": 80
+    },
+    {
+      "epoch": 0.00081,
+      "grad_norm": 1.0,
+      "learning_rate": 9.999983811390117e-06,
+      "loss": 1.5866,
+      "step": 81
+    },
+    {
+      "epoch": 0.00082,
+      "grad_norm": 1.2734375,
+      "learning_rate": 9.999983409204178e-06,
+      "loss": 1.4361,
+      "step": 82
+    },
+    {
+      "epoch": 0.00083,
+      "grad_norm": 1.9609375,
+      "learning_rate": 9.999983002083451e-06,
+      "loss": 1.5498,
+      "step": 83
+    },
+    {
+      "epoch": 0.00084,
+      "grad_norm": 3.125,
+      "learning_rate": 9.999982590027942e-06,
+      "loss": 1.5787,
+      "step": 84
+    },
+    {
+      "epoch": 0.00085,
+      "grad_norm": 0.9453125,
+      "learning_rate": 9.999982173037645e-06,
+      "loss": 1.5674,
+      "step": 85
+    },
+    {
+      "epoch": 0.00086,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.999981751112563e-06,
+      "loss": 1.5676,
+      "step": 86
+    },
+    {
+      "epoch": 0.00087,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.999981324252698e-06,
+      "loss": 1.5031,
+      "step": 87
+    },
+    {
+      "epoch": 0.00088,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.99998089245805e-06,
+      "loss": 1.5127,
+      "step": 88
+    },
+    {
+      "epoch": 0.00089,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.999980455728618e-06,
+      "loss": 1.5867,
+      "step": 89
+    },
+    {
+      "epoch": 0.0009,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.999980014064404e-06,
+      "loss": 1.4413,
+      "step": 90
+    },
+    {
+      "epoch": 0.00091,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.999979567465405e-06,
+      "loss": 1.3676,
+      "step": 91
+    },
+    {
+      "epoch": 0.00092,
+      "grad_norm": 0.9609375,
+      "learning_rate": 9.999979115931626e-06,
+      "loss": 1.5553,
+      "step": 92
+    },
+    {
+      "epoch": 0.00093,
+      "grad_norm": 0.75,
+      "learning_rate": 9.999978659463065e-06,
+      "loss": 1.4763,
+      "step": 93
+    },
+    {
+      "epoch": 0.00094,
+      "grad_norm": 0.6796875,
+      "learning_rate": 9.999978198059722e-06,
+      "loss": 1.4483,
+      "step": 94
+    },
+    {
+      "epoch": 0.00095,
+      "grad_norm": 0.8046875,
+      "learning_rate": 9.9999777317216e-06,
+      "loss": 1.5449,
+      "step": 95
+    },
+    {
+      "epoch": 0.00096,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.999977260448697e-06,
+      "loss": 1.4965,
+      "step": 96
+    },
+    {
+      "epoch": 0.00097,
+      "grad_norm": 1.0,
+      "learning_rate": 9.999976784241014e-06,
+      "loss": 1.596,
+      "step": 97
+    },
+    {
+      "epoch": 0.00098,
+      "grad_norm": 0.94921875,
+      "learning_rate": 9.999976303098552e-06,
+      "loss": 1.5585,
+      "step": 98
+    },
+    {
+      "epoch": 0.00099,
+      "grad_norm": 0.921875,
+      "learning_rate": 9.99997581702131e-06,
+      "loss": 1.501,
+      "step": 99
+    },
+    {
+      "epoch": 0.001,
+      "grad_norm": 1.8984375,
+      "learning_rate": 9.999975326009292e-06,
+      "loss": 1.4553,
+      "step": 100
+    },
+    {
+      "epoch": 0.00101,
+      "grad_norm": 0.7890625,
+      "learning_rate": 9.999974830062494e-06,
+      "loss": 1.5695,
+      "step": 101
+    },
+    {
+      "epoch": 0.00102,
+      "grad_norm": 0.73046875,
+      "learning_rate": 9.99997432918092e-06,
+      "loss": 1.4606,
+      "step": 102
+    },
+    {
+      "epoch": 0.00103,
+      "grad_norm": 0.98828125,
+      "learning_rate": 9.999973823364568e-06,
+      "loss": 1.5428,
+      "step": 103
+    },
+    {
+      "epoch": 0.00104,
+      "grad_norm": 0.90234375,
+      "learning_rate": 9.99997331261344e-06,
+      "loss": 1.5081,
+      "step": 104
+    },
+    {
+      "epoch": 0.00105,
+      "grad_norm": 1.875,
+      "learning_rate": 9.999972796927537e-06,
+      "loss": 1.5,
+      "step": 105
+    },
+    {
+      "epoch": 0.00106,
+      "grad_norm": 0.95703125,
+      "learning_rate": 9.999972276306858e-06,
+      "loss": 1.5322,
+      "step": 106
+    },
+    {
+      "epoch": 0.00107,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.999971750751405e-06,
+      "loss": 1.5786,
+      "step": 107
+    },
+    {
+      "epoch": 0.00108,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.999971220261177e-06,
+      "loss": 1.4891,
+      "step": 108
+    },
+    {
+      "epoch": 0.00109,
+      "grad_norm": 1.34375,
+      "learning_rate": 9.999970684836174e-06,
+      "loss": 1.4762,
+      "step": 109
+    },
+    {
+      "epoch": 0.0011,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.9999701444764e-06,
+      "loss": 1.5361,
+      "step": 110
+    },
+    {
+      "epoch": 0.00111,
+      "grad_norm": 0.88671875,
+      "learning_rate": 9.999969599181852e-06,
+      "loss": 1.4876,
+      "step": 111
+    },
+    {
+      "epoch": 0.00112,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.999969048952532e-06,
+      "loss": 1.4864,
+      "step": 112
+    },
+    {
+      "epoch": 0.00113,
+      "grad_norm": 0.875,
+      "learning_rate": 9.99996849378844e-06,
+      "loss": 1.5043,
+      "step": 113
+    },
+    {
+      "epoch": 0.00114,
+      "grad_norm": 0.8515625,
+      "learning_rate": 9.999967933689577e-06,
+      "loss": 1.4646,
+      "step": 114
+    },
+    {
+      "epoch": 0.00115,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.999967368655942e-06,
+      "loss": 1.5111,
+      "step": 115
+    },
+    {
+      "epoch": 0.00116,
+      "grad_norm": 1.125,
+      "learning_rate": 9.99996679868754e-06,
+      "loss": 1.4959,
+      "step": 116
+    },
+    {
+      "epoch": 0.00117,
+      "grad_norm": 0.8984375,
+      "learning_rate": 9.999966223784368e-06,
+      "loss": 1.5595,
+      "step": 117
+    },
+    {
+      "epoch": 0.00118,
+      "grad_norm": 3.703125,
+      "learning_rate": 9.999965643946425e-06,
+      "loss": 1.1576,
+      "step": 118
+    },
+    {
+      "epoch": 0.00119,
+      "grad_norm": 0.96484375,
+      "learning_rate": 9.999965059173715e-06,
+      "loss": 1.5184,
+      "step": 119
+    },
+    {
+      "epoch": 0.0012,
+      "grad_norm": 0.96484375,
+      "learning_rate": 9.999964469466236e-06,
+      "loss": 1.4559,
+      "step": 120
+    },
+    {
+      "epoch": 0.00121,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.999963874823993e-06,
+      "loss": 1.5143,
+      "step": 121
+    },
+    {
+      "epoch": 0.00122,
+      "grad_norm": 0.6640625,
+      "learning_rate": 9.999963275246983e-06,
+      "loss": 1.5526,
+      "step": 122
+    },
+    {
+      "epoch": 0.00123,
+      "grad_norm": 0.6640625,
+      "learning_rate": 9.999962670735205e-06,
+      "loss": 1.5328,
+      "step": 123
+    },
+    {
+      "epoch": 0.00124,
+      "grad_norm": 0.65625,
+      "learning_rate": 9.999962061288662e-06,
+      "loss": 1.5333,
+      "step": 124
+    },
+    {
+      "epoch": 0.00125,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.999961446907354e-06,
+      "loss": 1.5423,
+      "step": 125
+    },
+    {
+      "epoch": 0.00126,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.999960827591283e-06,
+      "loss": 1.5687,
+      "step": 126
+    },
+    {
+      "epoch": 0.00127,
+      "grad_norm": 0.671875,
+      "learning_rate": 9.999960203340447e-06,
+      "loss": 1.5186,
+      "step": 127
+    },
+    {
+      "epoch": 0.00128,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.99995957415485e-06,
+      "loss": 1.5319,
+      "step": 128
+    },
+    {
+      "epoch": 0.00129,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.99995894003449e-06,
+      "loss": 1.4797,
+      "step": 129
+    },
+    {
+      "epoch": 0.0013,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.999958300979367e-06,
+      "loss": 1.5232,
+      "step": 130
+    },
+    {
+      "epoch": 0.00131,
+      "grad_norm": 0.6953125,
+      "learning_rate": 9.999957656989482e-06,
+      "loss": 1.4463,
+      "step": 131
+    },
+    {
+      "epoch": 0.00132,
+      "grad_norm": 0.65234375,
+      "learning_rate": 9.99995700806484e-06,
+      "loss": 1.4935,
+      "step": 132
+    },
+    {
+      "epoch": 0.00133,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.999956354205437e-06,
+      "loss": 1.6034,
+      "step": 133
+    },
+    {
+      "epoch": 0.00134,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.999955695411274e-06,
+      "loss": 1.5081,
+      "step": 134
+    },
+    {
+      "epoch": 0.00135,
+      "grad_norm": 0.6640625,
+      "learning_rate": 9.999955031682354e-06,
+      "loss": 1.4503,
+      "step": 135
+    },
+    {
+      "epoch": 0.00136,
+      "grad_norm": 0.5625,
+      "learning_rate": 9.999954363018675e-06,
+      "loss": 1.3321,
+      "step": 136
+    },
+    {
+      "epoch": 0.00137,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.999953689420238e-06,
+      "loss": 1.5462,
+      "step": 137
+    },
+    {
+      "epoch": 0.00138,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.999953010887047e-06,
+      "loss": 1.5052,
+      "step": 138
+    },
+    {
+      "epoch": 0.00139,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999952327419098e-06,
+      "loss": 1.3766,
+      "step": 139
+    },
+    {
+      "epoch": 0.0014,
+      "grad_norm": 0.66796875,
+      "learning_rate": 9.999951639016396e-06,
+      "loss": 1.6074,
+      "step": 140
+    },
+    {
+      "epoch": 0.00141,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.999950945678939e-06,
+      "loss": 1.5381,
+      "step": 141
+    },
+    {
+      "epoch": 0.00142,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999950247406725e-06,
+      "loss": 1.5463,
+      "step": 142
+    },
+    {
+      "epoch": 0.00143,
+      "grad_norm": 0.625,
+      "learning_rate": 9.99994954419976e-06,
+      "loss": 1.5013,
+      "step": 143
+    },
+    {
+      "epoch": 0.00144,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999948836058045e-06,
+      "loss": 1.4789,
+      "step": 144
+    },
+    {
+      "epoch": 0.00145,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.999948122981576e-06,
+      "loss": 1.4872,
+      "step": 145
+    },
+    {
+      "epoch": 0.00146,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999947404970356e-06,
+      "loss": 1.5426,
+      "step": 146
+    },
+    {
+      "epoch": 0.00147,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.999946682024386e-06,
+      "loss": 1.5073,
+      "step": 147
+    },
+    {
+      "epoch": 0.00148,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999945954143665e-06,
+      "loss": 1.5537,
+      "step": 148
+    },
+    {
+      "epoch": 0.00149,
+      "grad_norm": 0.89453125,
+      "learning_rate": 9.999945221328198e-06,
+      "loss": 1.5759,
+      "step": 149
+    },
+    {
+      "epoch": 0.0015,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999944483577982e-06,
+      "loss": 1.5019,
+      "step": 150
+    },
+    {
+      "epoch": 0.00151,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999943740893017e-06,
+      "loss": 1.4706,
+      "step": 151
+    },
+    {
+      "epoch": 0.00152,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.999942993273306e-06,
+      "loss": 1.5303,
+      "step": 152
+    },
+    {
+      "epoch": 0.00153,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.99994224071885e-06,
+      "loss": 1.5028,
+      "step": 153
+    },
+    {
+      "epoch": 0.00154,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.999941483229646e-06,
+      "loss": 1.5878,
+      "step": 154
+    },
+    {
+      "epoch": 0.00155,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.9999407208057e-06,
+      "loss": 1.4271,
+      "step": 155
+    },
+    {
+      "epoch": 0.00156,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999939953447012e-06,
+      "loss": 1.4115,
+      "step": 156
+    },
+    {
+      "epoch": 0.00157,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.999939181153578e-06,
+      "loss": 1.5243,
+      "step": 157
+    },
+    {
+      "epoch": 0.00158,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999938403925404e-06,
+      "loss": 1.4749,
+      "step": 158
+    },
+    {
+      "epoch": 0.00159,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999937621762487e-06,
+      "loss": 1.5109,
+      "step": 159
+    },
+    {
+      "epoch": 0.0016,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.99993683466483e-06,
+      "loss": 1.5235,
+      "step": 160
+    },
+    {
+      "epoch": 0.00161,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.999936042632433e-06,
+      "loss": 1.5407,
+      "step": 161
+    },
+    {
+      "epoch": 0.00162,
+      "grad_norm": 0.55859375,
+      "learning_rate": 9.999935245665296e-06,
+      "loss": 1.4664,
+      "step": 162
+    },
+    {
+      "epoch": 0.00163,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999934443763421e-06,
+      "loss": 1.6013,
+      "step": 163
+    },
+    {
+      "epoch": 0.00164,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.99993363692681e-06,
+      "loss": 1.5297,
+      "step": 164
+    },
+    {
+      "epoch": 0.00165,
+      "grad_norm": 0.625,
+      "learning_rate": 9.999932825155462e-06,
+      "loss": 1.5636,
+      "step": 165
+    },
+    {
+      "epoch": 0.00166,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.999932008449377e-06,
+      "loss": 1.4603,
+      "step": 166
+    },
+    {
+      "epoch": 0.00167,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999931186808558e-06,
+      "loss": 1.5884,
+      "step": 167
+    },
+    {
+      "epoch": 0.00168,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999930360233003e-06,
+      "loss": 1.4181,
+      "step": 168
+    },
+    {
+      "epoch": 0.00169,
+      "grad_norm": 0.85546875,
+      "learning_rate": 9.999929528722716e-06,
+      "loss": 1.4743,
+      "step": 169
+    },
+    {
+      "epoch": 0.0017,
+      "grad_norm": 0.62109375,
+      "learning_rate": 9.999928692277696e-06,
+      "loss": 1.6229,
+      "step": 170
+    },
+    {
+      "epoch": 0.00171,
+      "grad_norm": 0.64453125,
+      "learning_rate": 9.999927850897944e-06,
+      "loss": 1.5356,
+      "step": 171
+    },
+    {
+      "epoch": 0.00172,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999927004583462e-06,
+      "loss": 1.5382,
+      "step": 172
+    },
+    {
+      "epoch": 0.00173,
+      "grad_norm": 0.78125,
+      "learning_rate": 9.99992615333425e-06,
+      "loss": 1.5174,
+      "step": 173
+    },
+    {
+      "epoch": 0.00174,
+      "grad_norm": 0.64453125,
+      "learning_rate": 9.999925297150307e-06,
+      "loss": 1.4997,
+      "step": 174
+    },
+    {
+      "epoch": 0.00175,
+      "grad_norm": 0.625,
+      "learning_rate": 9.999924436031636e-06,
+      "loss": 1.4769,
+      "step": 175
+    },
+    {
+      "epoch": 0.00176,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999923569978238e-06,
+      "loss": 1.517,
+      "step": 176
+    },
+    {
+      "epoch": 0.00177,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.999922698990112e-06,
+      "loss": 1.5596,
+      "step": 177
+    },
+    {
+      "epoch": 0.00178,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.999921823067263e-06,
+      "loss": 1.5257,
+      "step": 178
+    },
+    {
+      "epoch": 0.00179,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.999920942209686e-06,
+      "loss": 1.4666,
+      "step": 179
+    },
+    {
+      "epoch": 0.0018,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.999920056417385e-06,
+      "loss": 1.493,
+      "step": 180
+    },
+    {
+      "epoch": 0.00181,
+      "grad_norm": 0.62109375,
+      "learning_rate": 9.999919165690362e-06,
+      "loss": 1.5201,
+      "step": 181
+    },
+    {
+      "epoch": 0.00182,
+      "grad_norm": 0.62109375,
+      "learning_rate": 9.999918270028616e-06,
+      "loss": 1.5152,
+      "step": 182
+    },
+    {
+      "epoch": 0.00183,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999917369432148e-06,
+      "loss": 1.5456,
+      "step": 183
+    },
+    {
+      "epoch": 0.00184,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999916463900961e-06,
+      "loss": 1.5257,
+      "step": 184
+    },
+    {
+      "epoch": 0.00185,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999915553435053e-06,
+      "loss": 1.3887,
+      "step": 185
+    },
+    {
+      "epoch": 0.00186,
+      "grad_norm": 0.65234375,
+      "learning_rate": 9.999914638034426e-06,
+      "loss": 1.5393,
+      "step": 186
+    },
+    {
+      "epoch": 0.00187,
+      "grad_norm": 0.64453125,
+      "learning_rate": 9.999913717699081e-06,
+      "loss": 1.5807,
+      "step": 187
+    },
+    {
+      "epoch": 0.00188,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.99991279242902e-06,
+      "loss": 1.5917,
+      "step": 188
+    },
+    {
+      "epoch": 0.00189,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999911862224242e-06,
+      "loss": 1.4811,
+      "step": 189
+    },
+    {
+      "epoch": 0.0019,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.999910927084748e-06,
+      "loss": 1.5421,
+      "step": 190
+    },
+    {
+      "epoch": 0.00191,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999909987010541e-06,
+      "loss": 1.5756,
+      "step": 191
+    },
+    {
+      "epoch": 0.00192,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999909042001621e-06,
+      "loss": 1.4599,
+      "step": 192
+    },
+    {
+      "epoch": 0.00193,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999908092057988e-06,
+      "loss": 1.4314,
+      "step": 193
+    },
+    {
+      "epoch": 0.00194,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999907137179644e-06,
+      "loss": 1.5985,
+      "step": 194
+    },
+    {
+      "epoch": 0.00195,
+      "grad_norm": 0.6875,
+      "learning_rate": 9.999906177366587e-06,
+      "loss": 1.5923,
+      "step": 195
+    },
+    {
+      "epoch": 0.00196,
+      "grad_norm": 0.640625,
+      "learning_rate": 9.999905212618822e-06,
+      "loss": 1.5388,
+      "step": 196
+    },
+    {
+      "epoch": 0.00197,
+      "grad_norm": 0.55078125,
+      "learning_rate": 9.999904242936349e-06,
+      "loss": 1.313,
+      "step": 197
+    },
+    {
+      "epoch": 0.00198,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999903268319167e-06,
+      "loss": 1.5182,
+      "step": 198
+    },
+    {
+      "epoch": 0.00199,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.99990228876728e-06,
+      "loss": 1.4396,
+      "step": 199
+    },
+    {
+      "epoch": 0.002,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.999901304280686e-06,
+      "loss": 1.489,
+      "step": 200
+    },
+    {
+      "epoch": 0.00201,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999900314859388e-06,
+      "loss": 1.4867,
+      "step": 201
+    },
+    {
+      "epoch": 0.00202,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999899320503386e-06,
+      "loss": 1.5109,
+      "step": 202
+    },
+    {
+      "epoch": 0.00203,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999898321212681e-06,
+      "loss": 1.5289,
+      "step": 203
+    },
+    {
+      "epoch": 0.00204,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999897316987273e-06,
+      "loss": 1.4972,
+      "step": 204
+    },
+    {
+      "epoch": 0.00205,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999896307827167e-06,
+      "loss": 1.4926,
+      "step": 205
+    },
+    {
+      "epoch": 0.00206,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999895293732358e-06,
+      "loss": 1.5496,
+      "step": 206
+    },
+    {
+      "epoch": 0.00207,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999894274702853e-06,
+      "loss": 1.4316,
+      "step": 207
+    },
+    {
+      "epoch": 0.00208,
+      "grad_norm": 2.953125,
+      "learning_rate": 9.999893250738649e-06,
+      "loss": 1.5131,
+      "step": 208
+    },
+    {
+      "epoch": 0.00209,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999892221839747e-06,
+      "loss": 1.4639,
+      "step": 209
+    },
+    {
+      "epoch": 0.0021,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.99989118800615e-06,
+      "loss": 1.5029,
+      "step": 210
+    },
+    {
+      "epoch": 0.00211,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999890149237857e-06,
+      "loss": 1.5104,
+      "step": 211
+    },
+    {
+      "epoch": 0.00212,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999889105534873e-06,
+      "loss": 1.5475,
+      "step": 212
+    },
+    {
+      "epoch": 0.00213,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999888056897193e-06,
+      "loss": 1.4491,
+      "step": 213
+    },
+    {
+      "epoch": 0.00214,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999887003324825e-06,
+      "loss": 1.5361,
+      "step": 214
+    },
+    {
+      "epoch": 0.00215,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999885944817762e-06,
+      "loss": 1.5162,
+      "step": 215
+    },
+    {
+      "epoch": 0.00216,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999884881376012e-06,
+      "loss": 1.5086,
+      "step": 216
+    },
+    {
+      "epoch": 0.00217,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999883812999574e-06,
+      "loss": 1.4937,
+      "step": 217
+    },
+    {
+      "epoch": 0.00218,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999882739688446e-06,
+      "loss": 1.5327,
+      "step": 218
+    },
+    {
+      "epoch": 0.00219,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999881661442635e-06,
+      "loss": 1.4829,
+      "step": 219
+    },
+    {
+      "epoch": 0.0022,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999880578262135e-06,
+      "loss": 1.4377,
+      "step": 220
+    },
+    {
+      "epoch": 0.00221,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.999879490146953e-06,
+      "loss": 1.4425,
+      "step": 221
+    },
+    {
+      "epoch": 0.00222,
+      "grad_norm": 0.64453125,
+      "learning_rate": 9.999878397097086e-06,
+      "loss": 1.5688,
+      "step": 222
+    },
+    {
+      "epoch": 0.00223,
+      "grad_norm": 0.6875,
+      "learning_rate": 9.999877299112539e-06,
+      "loss": 1.4533,
+      "step": 223
+    },
+    {
+      "epoch": 0.00224,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.99987619619331e-06,
+      "loss": 1.5631,
+      "step": 224
+    },
+    {
+      "epoch": 0.00225,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999875088339401e-06,
+      "loss": 1.451,
+      "step": 225
+    },
+    {
+      "epoch": 0.00226,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999873975550812e-06,
+      "loss": 1.4725,
+      "step": 226
+    },
+    {
+      "epoch": 0.00227,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999872857827546e-06,
+      "loss": 1.5389,
+      "step": 227
+    },
+    {
+      "epoch": 0.00228,
+      "grad_norm": 0.65625,
+      "learning_rate": 9.999871735169603e-06,
+      "loss": 1.5243,
+      "step": 228
+    },
+    {
+      "epoch": 0.00229,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999870607576984e-06,
+      "loss": 1.5612,
+      "step": 229
+    },
+    {
+      "epoch": 0.0023,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999869475049693e-06,
+      "loss": 1.5469,
+      "step": 230
+    },
+    {
+      "epoch": 0.00231,
+      "grad_norm": 0.5625,
+      "learning_rate": 9.999868337587725e-06,
+      "loss": 1.3031,
+      "step": 231
+    },
+    {
+      "epoch": 0.00232,
+      "grad_norm": 0.5625,
+      "learning_rate": 9.99986719519109e-06,
+      "loss": 1.4403,
+      "step": 232
+    },
+    {
+      "epoch": 0.00233,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999866047859778e-06,
+      "loss": 1.438,
+      "step": 233
+    },
+    {
+      "epoch": 0.00234,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999864895593799e-06,
+      "loss": 1.4921,
+      "step": 234
+    },
+    {
+      "epoch": 0.00235,
+      "grad_norm": 0.5625,
+      "learning_rate": 9.99986373839315e-06,
+      "loss": 1.456,
+      "step": 235
+    },
+    {
+      "epoch": 0.00236,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999862576257836e-06,
+      "loss": 1.4828,
+      "step": 236
+    },
+    {
+      "epoch": 0.00237,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999861409187851e-06,
+      "loss": 1.3898,
+      "step": 237
+    },
+    {
+      "epoch": 0.00238,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999860237183202e-06,
+      "loss": 1.5977,
+      "step": 238
+    },
+    {
+      "epoch": 0.00239,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.99985906024389e-06,
+      "loss": 1.4885,
+      "step": 239
+    },
+    {
+      "epoch": 0.0024,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.999857878369917e-06,
+      "loss": 1.4311,
+      "step": 240
+    },
+    {
+      "epoch": 0.00241,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999856691561278e-06,
+      "loss": 1.4091,
+      "step": 241
+    },
+    {
+      "epoch": 0.00242,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.99985549981798e-06,
+      "loss": 1.6187,
+      "step": 242
+    },
+    {
+      "epoch": 0.00243,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.999854303140022e-06,
+      "loss": 1.5306,
+      "step": 243
+    },
+    {
+      "epoch": 0.00244,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999853101527406e-06,
+      "loss": 1.5455,
+      "step": 244
+    },
+    {
+      "epoch": 0.00245,
+      "grad_norm": 0.67578125,
+      "learning_rate": 9.999851894980133e-06,
+      "loss": 1.5096,
+      "step": 245
+    },
+    {
+      "epoch": 0.00246,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999850683498204e-06,
+      "loss": 1.4124,
+      "step": 246
+    },
+    {
+      "epoch": 0.00247,
+      "grad_norm": 0.62109375,
+      "learning_rate": 9.999849467081619e-06,
+      "loss": 1.5054,
+      "step": 247
+    },
+    {
+      "epoch": 0.00248,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.999848245730382e-06,
+      "loss": 1.5263,
+      "step": 248
+    },
+    {
+      "epoch": 0.00249,
+      "grad_norm": 0.640625,
+      "learning_rate": 9.99984701944449e-06,
+      "loss": 1.4857,
+      "step": 249
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.99984578822395e-06,
+      "loss": 1.451,
+      "step": 250
+    },
+    {
+      "epoch": 0.00251,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999844552068759e-06,
+      "loss": 1.5749,
+      "step": 251
+    },
+    {
+      "epoch": 0.00252,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999843310978919e-06,
+      "loss": 1.5781,
+      "step": 252
+    },
+    {
+      "epoch": 0.00253,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.99984206495443e-06,
+      "loss": 1.5356,
+      "step": 253
+    },
+    {
+      "epoch": 0.00254,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.999840813995296e-06,
+      "loss": 1.532,
+      "step": 254
+    },
+    {
+      "epoch": 0.00255,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999839558101517e-06,
+      "loss": 1.513,
+      "step": 255
+    },
+    {
+      "epoch": 0.00256,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999838297273093e-06,
+      "loss": 1.5514,
+      "step": 256
+    },
+    {
+      "epoch": 0.00257,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999837031510027e-06,
+      "loss": 1.529,
+      "step": 257
+    },
+    {
+      "epoch": 0.00258,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.99983576081232e-06,
+      "loss": 1.4506,
+      "step": 258
+    },
+    {
+      "epoch": 0.00259,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999834485179974e-06,
+      "loss": 1.4989,
+      "step": 259
+    },
+    {
+      "epoch": 0.0026,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.999833204612988e-06,
+      "loss": 1.4701,
+      "step": 260
+    },
+    {
+      "epoch": 0.00261,
+      "grad_norm": 0.625,
+      "learning_rate": 9.999831919111363e-06,
+      "loss": 1.4888,
+      "step": 261
+    },
+    {
+      "epoch": 0.00262,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999830628675105e-06,
+      "loss": 1.4784,
+      "step": 262
+    },
+    {
+      "epoch": 0.00263,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.99982933330421e-06,
+      "loss": 1.5459,
+      "step": 263
+    },
+    {
+      "epoch": 0.00264,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.99982803299868e-06,
+      "loss": 1.525,
+      "step": 264
+    },
+    {
+      "epoch": 0.00265,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.99982672775852e-06,
+      "loss": 1.4649,
+      "step": 265
+    },
+    {
+      "epoch": 0.00266,
+      "grad_norm": 0.625,
+      "learning_rate": 9.999825417583727e-06,
+      "loss": 1.5024,
+      "step": 266
+    },
+    {
+      "epoch": 0.00267,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999824102474304e-06,
+      "loss": 1.5069,
+      "step": 267
+    },
+    {
+      "epoch": 0.00268,
+      "grad_norm": 0.83984375,
+      "learning_rate": 9.999822782430253e-06,
+      "loss": 1.3715,
+      "step": 268
+    },
+    {
+      "epoch": 0.00269,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999821457451576e-06,
+      "loss": 1.5258,
+      "step": 269
+    },
+    {
+      "epoch": 0.0027,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999820127538271e-06,
+      "loss": 1.5928,
+      "step": 270
+    },
+    {
+      "epoch": 0.00271,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.999818792690344e-06,
+      "loss": 1.4709,
+      "step": 271
+    },
+    {
+      "epoch": 0.00272,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.99981745290779e-06,
+      "loss": 1.5465,
+      "step": 272
+    },
+    {
+      "epoch": 0.00273,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.999816108190616e-06,
+      "loss": 1.4847,
+      "step": 273
+    },
+    {
+      "epoch": 0.00274,
+      "grad_norm": 0.7890625,
+      "learning_rate": 9.999814758538821e-06,
+      "loss": 1.5317,
+      "step": 274
+    },
+    {
+      "epoch": 0.00275,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.999813403952407e-06,
+      "loss": 1.5641,
+      "step": 275
+    },
+    {
+      "epoch": 0.00276,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.999812044431374e-06,
+      "loss": 1.5378,
+      "step": 276
+    },
+    {
+      "epoch": 0.00277,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.999810679975725e-06,
+      "loss": 1.4964,
+      "step": 277
+    },
+    {
+      "epoch": 0.00278,
+      "grad_norm": 0.5546875,
+      "learning_rate": 9.999809310585462e-06,
+      "loss": 1.3405,
+      "step": 278
+    },
+    {
+      "epoch": 0.00279,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999807936260583e-06,
+      "loss": 1.4228,
+      "step": 279
+    },
+    {
+      "epoch": 0.0028,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999806557001092e-06,
+      "loss": 1.4399,
+      "step": 280
+    },
+    {
+      "epoch": 0.00281,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.99980517280699e-06,
+      "loss": 1.4913,
+      "step": 281
+    },
+    {
+      "epoch": 0.00282,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.999803783678276e-06,
+      "loss": 1.4801,
+      "step": 282
+    },
+    {
+      "epoch": 0.00283,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999802389614957e-06,
+      "loss": 1.5795,
+      "step": 283
+    },
+    {
+      "epoch": 0.00284,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.99980099061703e-06,
+      "loss": 1.5647,
+      "step": 284
+    },
+    {
+      "epoch": 0.00285,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999799586684495e-06,
+      "loss": 1.4144,
+      "step": 285
+    },
+    {
+      "epoch": 0.00286,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999798177817357e-06,
+      "loss": 1.5315,
+      "step": 286
+    },
+    {
+      "epoch": 0.00287,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999796764015617e-06,
+      "loss": 1.5143,
+      "step": 287
+    },
+    {
+      "epoch": 0.00288,
+      "grad_norm": 0.5625,
+      "learning_rate": 9.999795345279273e-06,
+      "loss": 1.4468,
+      "step": 288
+    },
+    {
+      "epoch": 0.00289,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.999793921608331e-06,
+      "loss": 1.4191,
+      "step": 289
+    },
+    {
+      "epoch": 0.0029,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.99979249300279e-06,
+      "loss": 1.5005,
+      "step": 290
+    },
+    {
+      "epoch": 0.00291,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999791059462649e-06,
+      "loss": 1.5497,
+      "step": 291
+    },
+    {
+      "epoch": 0.00292,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.999789620987914e-06,
+      "loss": 1.4732,
+      "step": 292
+    },
+    {
+      "epoch": 0.00293,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999788177578585e-06,
+      "loss": 1.5058,
+      "step": 293
+    },
+    {
+      "epoch": 0.00294,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999786729234661e-06,
+      "loss": 1.5243,
+      "step": 294
+    },
+    {
+      "epoch": 0.00295,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.999785275956147e-06,
+      "loss": 1.5668,
+      "step": 295
+    },
+    {
+      "epoch": 0.00296,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.999783817743043e-06,
+      "loss": 1.4874,
+      "step": 296
+    },
+    {
+      "epoch": 0.00297,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999782354595349e-06,
+      "loss": 1.5466,
+      "step": 297
+    },
+    {
+      "epoch": 0.00298,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999780886513069e-06,
+      "loss": 1.5114,
+      "step": 298
+    },
+    {
+      "epoch": 0.00299,
+      "grad_norm": 0.5546875,
+      "learning_rate": 9.9997794134962e-06,
+      "loss": 1.4656,
+      "step": 299
+    },
+    {
+      "epoch": 0.003,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.99977793554475e-06,
+      "loss": 1.4512,
+      "step": 300
+    },
+    {
+      "epoch": 0.00301,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999776452658716e-06,
+      "loss": 1.4278,
+      "step": 301
+    },
+    {
+      "epoch": 0.00302,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999774964838099e-06,
+      "loss": 1.4672,
+      "step": 302
+    },
+    {
+      "epoch": 0.00303,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.999773472082903e-06,
+      "loss": 1.5091,
+      "step": 303
+    },
+    {
+      "epoch": 0.00304,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999771974393129e-06,
+      "loss": 1.4843,
+      "step": 304
+    },
+    {
+      "epoch": 0.00305,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999770471768778e-06,
+      "loss": 1.424,
+      "step": 305
+    },
+    {
+      "epoch": 0.00306,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999768964209848e-06,
+      "loss": 1.3624,
+      "step": 306
+    },
+    {
+      "epoch": 0.00307,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999767451716347e-06,
+      "loss": 1.5685,
+      "step": 307
+    },
+    {
+      "epoch": 0.00308,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999765934288272e-06,
+      "loss": 1.563,
+      "step": 308
+    },
+    {
+      "epoch": 0.00309,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.999764411925628e-06,
+      "loss": 1.5428,
+      "step": 309
+    },
+    {
+      "epoch": 0.0031,
+      "grad_norm": 0.625,
+      "learning_rate": 9.999762884628413e-06,
+      "loss": 1.5119,
+      "step": 310
+    },
+    {
+      "epoch": 0.00311,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999761352396628e-06,
+      "loss": 1.5343,
+      "step": 311
+    },
+    {
+      "epoch": 0.00312,
+      "grad_norm": 0.625,
+      "learning_rate": 9.999759815230277e-06,
+      "loss": 1.5505,
+      "step": 312
+    },
+    {
+      "epoch": 0.00313,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999758273129362e-06,
+      "loss": 1.4687,
+      "step": 313
+    },
+    {
+      "epoch": 0.00314,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.999756726093883e-06,
+      "loss": 1.4969,
+      "step": 314
+    },
+    {
+      "epoch": 0.00315,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999755174123842e-06,
+      "loss": 1.5959,
+      "step": 315
+    },
+    {
+      "epoch": 0.00316,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.999753617219241e-06,
+      "loss": 1.2334,
+      "step": 316
+    },
+    {
+      "epoch": 0.00317,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.99975205538008e-06,
+      "loss": 1.4491,
+      "step": 317
+    },
+    {
+      "epoch": 0.00318,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999750488606362e-06,
+      "loss": 1.468,
+      "step": 318
+    },
+    {
+      "epoch": 0.00319,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999748916898088e-06,
+      "loss": 1.4278,
+      "step": 319
+    },
+    {
+      "epoch": 0.0032,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.99974734025526e-06,
+      "loss": 1.5056,
+      "step": 320
+    },
+    {
+      "epoch": 0.00321,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999745758677878e-06,
+      "loss": 1.4188,
+      "step": 321
+    },
+    {
+      "epoch": 0.00322,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999744172165945e-06,
+      "loss": 1.3937,
+      "step": 322
+    },
+    {
+      "epoch": 0.00323,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999742580719463e-06,
+      "loss": 1.5149,
+      "step": 323
+    },
+    {
+      "epoch": 0.00324,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999740984338433e-06,
+      "loss": 1.4844,
+      "step": 324
+    },
+    {
+      "epoch": 0.00325,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999739383022856e-06,
+      "loss": 1.4974,
+      "step": 325
+    },
+    {
+      "epoch": 0.00326,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999737776772735e-06,
+      "loss": 1.4215,
+      "step": 326
+    },
+    {
+      "epoch": 0.00327,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.99973616558807e-06,
+      "loss": 1.578,
+      "step": 327
+    },
+    {
+      "epoch": 0.00328,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.999734549468863e-06,
+      "loss": 1.5505,
+      "step": 328
+    },
+    {
+      "epoch": 0.00329,
+      "grad_norm": 0.54296875,
+      "learning_rate": 9.999732928415115e-06,
+      "loss": 1.3222,
+      "step": 329
+    },
+    {
+      "epoch": 0.0033,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999731302426829e-06,
+      "loss": 1.5815,
+      "step": 330
+    },
+    {
+      "epoch": 0.00331,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999729671504007e-06,
+      "loss": 1.4017,
+      "step": 331
+    },
+    {
+      "epoch": 0.00332,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999728035646648e-06,
+      "loss": 1.507,
+      "step": 332
+    },
+    {
+      "epoch": 0.00333,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999726394854755e-06,
+      "loss": 1.441,
+      "step": 333
+    },
+    {
+      "epoch": 0.00334,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.99972474912833e-06,
+      "loss": 1.5628,
+      "step": 334
+    },
+    {
+      "epoch": 0.00335,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999723098467375e-06,
+      "loss": 1.464,
+      "step": 335
+    },
+    {
+      "epoch": 0.00336,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999721442871892e-06,
+      "loss": 1.4567,
+      "step": 336
+    },
+    {
+      "epoch": 0.00337,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.99971978234188e-06,
+      "loss": 1.5087,
+      "step": 337
+    },
+    {
+      "epoch": 0.00338,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999718116877344e-06,
+      "loss": 1.5264,
+      "step": 338
+    },
+    {
+      "epoch": 0.00339,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999716446478284e-06,
+      "loss": 1.4069,
+      "step": 339
+    },
+    {
+      "epoch": 0.0034,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.9997147711447e-06,
+      "loss": 1.4323,
+      "step": 340
+    },
+    {
+      "epoch": 0.00341,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999713090876597e-06,
+      "loss": 1.5584,
+      "step": 341
+    },
+    {
+      "epoch": 0.00342,
+      "grad_norm": 0.56640625,
+      "learning_rate": 9.999711405673974e-06,
+      "loss": 1.4787,
+      "step": 342
+    },
+    {
+      "epoch": 0.00343,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.999709715536833e-06,
+      "loss": 1.5732,
+      "step": 343
+    },
+    {
+      "epoch": 0.00344,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999708020465177e-06,
+      "loss": 1.3899,
+      "step": 344
+    },
+    {
+      "epoch": 0.00345,
+      "grad_norm": 1.9453125,
+      "learning_rate": 9.999706320459008e-06,
+      "loss": 1.3948,
+      "step": 345
+    },
+    {
+      "epoch": 0.00346,
+      "grad_norm": 0.5546875,
+      "learning_rate": 9.999704615518327e-06,
+      "loss": 1.5258,
+      "step": 346
+    },
+    {
+      "epoch": 0.00347,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999702905643133e-06,
+      "loss": 1.4421,
+      "step": 347
+    },
+    {
+      "epoch": 0.00348,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999701190833431e-06,
+      "loss": 1.5647,
+      "step": 348
+    },
+    {
+      "epoch": 0.00349,
+      "grad_norm": 0.640625,
+      "learning_rate": 9.999699471089223e-06,
+      "loss": 1.6083,
+      "step": 349
+    },
+    {
+      "epoch": 0.0035,
+      "grad_norm": 0.56640625,
+      "learning_rate": 9.999697746410509e-06,
+      "loss": 1.5287,
+      "step": 350
+    },
+    {
+      "epoch": 0.00351,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.99969601679729e-06,
+      "loss": 1.4517,
+      "step": 351
+    },
+    {
+      "epoch": 0.00352,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.999694282249568e-06,
+      "loss": 1.5041,
+      "step": 352
+    },
+    {
+      "epoch": 0.00353,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999692542767347e-06,
+      "loss": 1.4867,
+      "step": 353
+    },
+    {
+      "epoch": 0.00354,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999690798350628e-06,
+      "loss": 1.5221,
+      "step": 354
+    },
+    {
+      "epoch": 0.00355,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999689048999411e-06,
+      "loss": 1.5112,
+      "step": 355
+    },
+    {
+      "epoch": 0.00356,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999687294713697e-06,
+      "loss": 1.609,
+      "step": 356
+    },
+    {
+      "epoch": 0.00357,
+      "grad_norm": 5.53125,
+      "learning_rate": 9.999685535493491e-06,
+      "loss": 1.4672,
+      "step": 357
+    },
+    {
+      "epoch": 0.00358,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999683771338794e-06,
+      "loss": 1.5205,
+      "step": 358
+    },
+    {
+      "epoch": 0.00359,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999682002249607e-06,
+      "loss": 1.5086,
+      "step": 359
+    },
+    {
+      "epoch": 0.0036,
+      "grad_norm": 0.65234375,
+      "learning_rate": 9.99968022822593e-06,
+      "loss": 1.5032,
+      "step": 360
+    },
+    {
+      "epoch": 0.00361,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999678449267766e-06,
+      "loss": 1.4734,
+      "step": 361
+    },
+    {
+      "epoch": 0.00362,
+      "grad_norm": 0.64453125,
+      "learning_rate": 9.99967666537512e-06,
+      "loss": 1.5343,
+      "step": 362
+    },
+    {
+      "epoch": 0.00363,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999674876547989e-06,
+      "loss": 1.4186,
+      "step": 363
+    },
+    {
+      "epoch": 0.00364,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.999673082786376e-06,
+      "loss": 1.386,
+      "step": 364
+    },
+    {
+      "epoch": 0.00365,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999671284090286e-06,
+      "loss": 1.5629,
+      "step": 365
+    },
+    {
+      "epoch": 0.00366,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999669480459716e-06,
+      "loss": 1.5062,
+      "step": 366
+    },
+    {
+      "epoch": 0.00367,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.99966767189467e-06,
+      "loss": 1.4843,
+      "step": 367
+    },
+    {
+      "epoch": 0.00368,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999665858395152e-06,
+      "loss": 1.5003,
+      "step": 368
+    },
+    {
+      "epoch": 0.00369,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.99966403996116e-06,
+      "loss": 1.4893,
+      "step": 369
+    },
+    {
+      "epoch": 0.0037,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999662216592696e-06,
+      "loss": 1.4829,
+      "step": 370
+    },
+    {
+      "epoch": 0.00371,
+      "grad_norm": 0.7734375,
+      "learning_rate": 9.999660388289765e-06,
+      "loss": 1.4288,
+      "step": 371
+    },
+    {
+      "epoch": 0.00372,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999658555052368e-06,
+      "loss": 1.4853,
+      "step": 372
+    },
+    {
+      "epoch": 0.00373,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999656716880504e-06,
+      "loss": 1.4939,
+      "step": 373
+    },
+    {
+      "epoch": 0.00374,
+      "grad_norm": 0.62109375,
+      "learning_rate": 9.999654873774177e-06,
+      "loss": 1.5349,
+      "step": 374
+    },
+    {
+      "epoch": 0.00375,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999653025733386e-06,
+      "loss": 1.5811,
+      "step": 375
+    },
+    {
+      "epoch": 0.00376,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999651172758139e-06,
+      "loss": 1.5546,
+      "step": 376
+    },
+    {
+      "epoch": 0.00377,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999649314848432e-06,
+      "loss": 1.5265,
+      "step": 377
+    },
+    {
+      "epoch": 0.00378,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.99964745200427e-06,
+      "loss": 1.5653,
+      "step": 378
+    },
+    {
+      "epoch": 0.00379,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.999645584225654e-06,
+      "loss": 1.3955,
+      "step": 379
+    },
+    {
+      "epoch": 0.0038,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.999643711512586e-06,
+      "loss": 1.5375,
+      "step": 380
+    },
+    {
+      "epoch": 0.00381,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999641833865065e-06,
+      "loss": 1.5196,
+      "step": 381
+    },
+    {
+      "epoch": 0.00382,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999639951283098e-06,
+      "loss": 1.4494,
+      "step": 382
+    },
+    {
+      "epoch": 0.00383,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.99963806376668e-06,
+      "loss": 1.5654,
+      "step": 383
+    },
+    {
+      "epoch": 0.00384,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999636171315822e-06,
+      "loss": 1.5794,
+      "step": 384
+    },
+    {
+      "epoch": 0.00385,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999634273930519e-06,
+      "loss": 1.5123,
+      "step": 385
+    },
+    {
+      "epoch": 0.00386,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999632371610775e-06,
+      "loss": 1.5589,
+      "step": 386
+    },
+    {
+      "epoch": 0.00387,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.99963046435659e-06,
+      "loss": 1.5204,
+      "step": 387
+    },
+    {
+      "epoch": 0.00388,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999628552167968e-06,
+      "loss": 1.5047,
+      "step": 388
+    },
+    {
+      "epoch": 0.00389,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999626635044911e-06,
+      "loss": 1.5133,
+      "step": 389
+    },
+    {
+      "epoch": 0.0039,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.99962471298742e-06,
+      "loss": 1.5079,
+      "step": 390
+    },
+    {
+      "epoch": 0.00391,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.999622785995499e-06,
+      "loss": 1.525,
+      "step": 391
+    },
+    {
+      "epoch": 0.00392,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999620854069148e-06,
+      "loss": 1.5243,
+      "step": 392
+    },
+    {
+      "epoch": 0.00393,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.999618917208367e-06,
+      "loss": 1.5368,
+      "step": 393
+    },
+    {
+      "epoch": 0.00394,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.99961697541316e-06,
+      "loss": 1.5637,
+      "step": 394
+    },
+    {
+      "epoch": 0.00395,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.99961502868353e-06,
+      "loss": 1.5719,
+      "step": 395
+    },
+    {
+      "epoch": 0.00396,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999613077019477e-06,
+      "loss": 1.5431,
+      "step": 396
+    },
+    {
+      "epoch": 0.00397,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.999611120421004e-06,
+      "loss": 1.562,
+      "step": 397
+    },
+    {
+      "epoch": 0.00398,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999609158888112e-06,
+      "loss": 1.5388,
+      "step": 398
+    },
+    {
+      "epoch": 0.00399,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999607192420804e-06,
+      "loss": 1.4451,
+      "step": 399
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.999605221019082e-06,
+      "loss": 1.488,
+      "step": 400
+    },
+    {
+      "epoch": 0.00401,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999603244682946e-06,
+      "loss": 1.498,
+      "step": 401
+    },
+    {
+      "epoch": 0.00402,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.9996012634124e-06,
+      "loss": 1.4949,
+      "step": 402
+    },
+    {
+      "epoch": 0.00403,
+      "grad_norm": 1.28125,
+      "learning_rate": 9.999599277207445e-06,
+      "loss": 1.4222,
+      "step": 403
+    },
+    {
+      "epoch": 0.00404,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999597286068085e-06,
+      "loss": 1.4637,
+      "step": 404
+    },
+    {
+      "epoch": 0.00405,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.99959528999432e-06,
+      "loss": 1.4693,
+      "step": 405
+    },
+    {
+      "epoch": 0.00406,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999593288986151e-06,
+      "loss": 1.6096,
+      "step": 406
+    },
+    {
+      "epoch": 0.00407,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999591283043581e-06,
+      "loss": 1.4465,
+      "step": 407
+    },
+    {
+      "epoch": 0.00408,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999589272166614e-06,
+      "loss": 1.514,
+      "step": 408
+    },
+    {
+      "epoch": 0.00409,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999587256355248e-06,
+      "loss": 1.4868,
+      "step": 409
+    },
+    {
+      "epoch": 0.0041,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999585235609487e-06,
+      "loss": 1.4936,
+      "step": 410
+    },
+    {
+      "epoch": 0.00411,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999583209929335e-06,
+      "loss": 1.5555,
+      "step": 411
+    },
+    {
+      "epoch": 0.00412,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999581179314793e-06,
+      "loss": 1.4915,
+      "step": 412
+    },
+    {
+      "epoch": 0.00413,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999579143765861e-06,
+      "loss": 1.5244,
+      "step": 413
+    },
+    {
+      "epoch": 0.00414,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.999577103282541e-06,
+      "loss": 1.558,
+      "step": 414
+    },
+    {
+      "epoch": 0.00415,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.999575057864837e-06,
+      "loss": 1.5333,
+      "step": 415
+    },
+    {
+      "epoch": 0.00416,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.999573007512751e-06,
+      "loss": 1.5035,
+      "step": 416
+    },
+    {
+      "epoch": 0.00417,
+      "grad_norm": 0.64453125,
+      "learning_rate": 9.999570952226284e-06,
+      "loss": 1.5245,
+      "step": 417
+    },
+    {
+      "epoch": 0.00418,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999568892005436e-06,
+      "loss": 1.4968,
+      "step": 418
+    },
+    {
+      "epoch": 0.00419,
+      "grad_norm": 0.6953125,
+      "learning_rate": 9.999566826850214e-06,
+      "loss": 1.4418,
+      "step": 419
+    },
+    {
+      "epoch": 0.0042,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999564756760616e-06,
+      "loss": 1.6185,
+      "step": 420
+    },
+    {
+      "epoch": 0.00421,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999562681736645e-06,
+      "loss": 1.4845,
+      "step": 421
+    },
+    {
+      "epoch": 0.00422,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.999560601778303e-06,
+      "loss": 1.3121,
+      "step": 422
+    },
+    {
+      "epoch": 0.00423,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999558516885595e-06,
+      "loss": 1.5696,
+      "step": 423
+    },
+    {
+      "epoch": 0.00424,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.99955642705852e-06,
+      "loss": 1.4734,
+      "step": 424
+    },
+    {
+      "epoch": 0.00425,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999554332297079e-06,
+      "loss": 1.5252,
+      "step": 425
+    },
+    {
+      "epoch": 0.00426,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999552232601275e-06,
+      "loss": 1.5028,
+      "step": 426
+    },
+    {
+      "epoch": 0.00427,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999550127971113e-06,
+      "loss": 1.428,
+      "step": 427
+    },
+    {
+      "epoch": 0.00428,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999548018406591e-06,
+      "loss": 1.5138,
+      "step": 428
+    },
+    {
+      "epoch": 0.00429,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999545903907714e-06,
+      "loss": 1.5135,
+      "step": 429
+    },
+    {
+      "epoch": 0.0043,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999543784474484e-06,
+      "loss": 1.5209,
+      "step": 430
+    },
+    {
+      "epoch": 0.00431,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.9995416601069e-06,
+      "loss": 1.5048,
+      "step": 431
+    },
+    {
+      "epoch": 0.00432,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999539530804967e-06,
+      "loss": 1.5185,
+      "step": 432
+    },
+    {
+      "epoch": 0.00433,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999537396568685e-06,
+      "loss": 1.5269,
+      "step": 433
+    },
+    {
+      "epoch": 0.00434,
+      "grad_norm": 0.64453125,
+      "learning_rate": 9.999535257398058e-06,
+      "loss": 1.562,
+      "step": 434
+    },
+    {
+      "epoch": 0.00435,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.99953311329309e-06,
+      "loss": 1.4944,
+      "step": 435
+    },
+    {
+      "epoch": 0.00436,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.99953096425378e-06,
+      "loss": 1.487,
+      "step": 436
+    },
+    {
+      "epoch": 0.00437,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.999528810280128e-06,
+      "loss": 1.5033,
+      "step": 437
+    },
+    {
+      "epoch": 0.00438,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.99952665137214e-06,
+      "loss": 1.5232,
+      "step": 438
+    },
+    {
+      "epoch": 0.00439,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.999524487529817e-06,
+      "loss": 1.5764,
+      "step": 439
+    },
+    {
+      "epoch": 0.0044,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.99952231875316e-06,
+      "loss": 1.5068,
+      "step": 440
+    },
+    {
+      "epoch": 0.00441,
+      "grad_norm": 0.625,
+      "learning_rate": 9.999520145042174e-06,
+      "loss": 1.5465,
+      "step": 441
+    },
+    {
+      "epoch": 0.00442,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.999517966396859e-06,
+      "loss": 1.5235,
+      "step": 442
+    },
+    {
+      "epoch": 0.00443,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999515782817217e-06,
+      "loss": 1.5467,
+      "step": 443
+    },
+    {
+      "epoch": 0.00444,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999513594303251e-06,
+      "loss": 1.4685,
+      "step": 444
+    },
+    {
+      "epoch": 0.00445,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.999511400854964e-06,
+      "loss": 1.5144,
+      "step": 445
+    },
+    {
+      "epoch": 0.00446,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999509202472356e-06,
+      "loss": 1.5127,
+      "step": 446
+    },
+    {
+      "epoch": 0.00447,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.99950699915543e-06,
+      "loss": 1.4352,
+      "step": 447
+    },
+    {
+      "epoch": 0.00448,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.99950479090419e-06,
+      "loss": 1.568,
+      "step": 448
+    },
+    {
+      "epoch": 0.00449,
+      "grad_norm": 0.57421875,
+      "learning_rate": 9.999502577718634e-06,
+      "loss": 1.4572,
+      "step": 449
+    },
+    {
+      "epoch": 0.0045,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999500359598769e-06,
+      "loss": 1.4915,
+      "step": 450
+    },
+    {
+      "epoch": 0.00451,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999498136544594e-06,
+      "loss": 1.5833,
+      "step": 451
+    },
+    {
+      "epoch": 0.00452,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999495908556112e-06,
+      "loss": 1.5356,
+      "step": 452
+    },
+    {
+      "epoch": 0.00453,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.999493675633325e-06,
+      "loss": 1.4961,
+      "step": 453
+    },
+    {
+      "epoch": 0.00454,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999491437776236e-06,
+      "loss": 1.4887,
+      "step": 454
+    },
+    {
+      "epoch": 0.00455,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.999489194984846e-06,
+      "loss": 1.5002,
+      "step": 455
+    },
+    {
+      "epoch": 0.00456,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.999486947259159e-06,
+      "loss": 1.5023,
+      "step": 456
+    },
+    {
+      "epoch": 0.00457,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999484694599174e-06,
+      "loss": 1.5351,
+      "step": 457
+    },
+    {
+      "epoch": 0.00458,
+      "grad_norm": 0.5625,
+      "learning_rate": 9.999482437004898e-06,
+      "loss": 1.45,
+      "step": 458
+    },
+    {
+      "epoch": 0.00459,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.99948017447633e-06,
+      "loss": 1.496,
+      "step": 459
+    },
+    {
+      "epoch": 0.0046,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999477907013473e-06,
+      "loss": 1.6283,
+      "step": 460
+    },
+    {
+      "epoch": 0.00461,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999475634616328e-06,
+      "loss": 1.419,
+      "step": 461
+    },
+    {
+      "epoch": 0.00462,
+      "grad_norm": 0.66015625,
+      "learning_rate": 9.999473357284898e-06,
+      "loss": 1.6006,
+      "step": 462
+    },
+    {
+      "epoch": 0.00463,
+      "grad_norm": 0.55859375,
+      "learning_rate": 9.999471075019188e-06,
+      "loss": 1.5436,
+      "step": 463
+    },
+    {
+      "epoch": 0.00464,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999468787819195e-06,
+      "loss": 1.5771,
+      "step": 464
+    },
+    {
+      "epoch": 0.00465,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999466495684926e-06,
+      "loss": 1.4976,
+      "step": 465
+    },
+    {
+      "epoch": 0.00466,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.999464198616381e-06,
+      "loss": 1.4614,
+      "step": 466
+    },
+    {
+      "epoch": 0.00467,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999461896613563e-06,
+      "loss": 1.573,
+      "step": 467
+    },
+    {
+      "epoch": 0.00468,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999459589676473e-06,
+      "loss": 1.5366,
+      "step": 468
+    },
+    {
+      "epoch": 0.00469,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999457277805113e-06,
+      "loss": 1.4971,
+      "step": 469
+    },
+    {
+      "epoch": 0.0047,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.999454960999488e-06,
+      "loss": 1.5383,
+      "step": 470
+    },
+    {
+      "epoch": 0.00471,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999452639259599e-06,
+      "loss": 1.5175,
+      "step": 471
+    },
+    {
+      "epoch": 0.00472,
+      "grad_norm": 0.5625,
+      "learning_rate": 9.999450312585449e-06,
+      "loss": 1.481,
+      "step": 472
+    },
+    {
+      "epoch": 0.00473,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999447980977037e-06,
+      "loss": 1.501,
+      "step": 473
+    },
+    {
+      "epoch": 0.00474,
+      "grad_norm": 0.8046875,
+      "learning_rate": 9.99944564443437e-06,
+      "loss": 1.5477,
+      "step": 474
+    },
+    {
+      "epoch": 0.00475,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999443302957446e-06,
+      "loss": 1.5133,
+      "step": 475
+    },
+    {
+      "epoch": 0.00476,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.99944095654627e-06,
+      "loss": 1.5842,
+      "step": 476
+    },
+    {
+      "epoch": 0.00477,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999438605200841e-06,
+      "loss": 1.4929,
+      "step": 477
+    },
+    {
+      "epoch": 0.00478,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.999436248921167e-06,
+      "loss": 1.4826,
+      "step": 478
+    },
+    {
+      "epoch": 0.00479,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999433887707246e-06,
+      "loss": 1.5088,
+      "step": 479
+    },
+    {
+      "epoch": 0.0048,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999431521559081e-06,
+      "loss": 1.5755,
+      "step": 480
+    },
+    {
+      "epoch": 0.00481,
+      "grad_norm": 0.578125,
+      "learning_rate": 9.999429150476678e-06,
+      "loss": 1.5071,
+      "step": 481
+    },
+    {
+      "epoch": 0.00482,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.999426774460032e-06,
+      "loss": 1.6016,
+      "step": 482
+    },
+    {
+      "epoch": 0.00483,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999424393509153e-06,
+      "loss": 1.5384,
+      "step": 483
+    },
+    {
+      "epoch": 0.00484,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.999422007624038e-06,
+      "loss": 1.4805,
+      "step": 484
+    },
+    {
+      "epoch": 0.00485,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999419616804693e-06,
+      "loss": 1.4774,
+      "step": 485
+    },
+    {
+      "epoch": 0.00486,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999417221051116e-06,
+      "loss": 1.4592,
+      "step": 486
+    },
+    {
+      "epoch": 0.00487,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.999414820363313e-06,
+      "loss": 1.5434,
+      "step": 487
+    },
+    {
+      "epoch": 0.00488,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.999412414741286e-06,
+      "loss": 1.5352,
+      "step": 488
+    },
+    {
+      "epoch": 0.00489,
+      "grad_norm": 0.64453125,
+      "learning_rate": 9.999410004185038e-06,
+      "loss": 1.4044,
+      "step": 489
+    },
+    {
+      "epoch": 0.0049,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999407588694568e-06,
+      "loss": 1.4273,
+      "step": 490
+    },
+    {
+      "epoch": 0.00491,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.99940516826988e-06,
+      "loss": 1.5409,
+      "step": 491
+    },
+    {
+      "epoch": 0.00492,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.999402742910977e-06,
+      "loss": 1.5455,
+      "step": 492
+    },
+    {
+      "epoch": 0.00493,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.999400312617863e-06,
+      "loss": 1.461,
+      "step": 493
+    },
+    {
+      "epoch": 0.00494,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999397877390538e-06,
+      "loss": 1.446,
+      "step": 494
+    },
+    {
+      "epoch": 0.00495,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999395437229004e-06,
+      "loss": 1.5338,
+      "step": 495
+    },
+    {
+      "epoch": 0.00496,
+      "grad_norm": 0.5859375,
+      "learning_rate": 9.999392992133265e-06,
+      "loss": 1.5947,
+      "step": 496
+    },
+    {
+      "epoch": 0.00497,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.999390542103325e-06,
+      "loss": 1.5632,
+      "step": 497
+    },
+    {
+      "epoch": 0.00498,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.999388087139182e-06,
+      "loss": 1.441,
+      "step": 498
+    },
+    {
+      "epoch": 0.00499,
+      "grad_norm": 0.62109375,
+      "learning_rate": 9.99938562724084e-06,
+      "loss": 1.5702,
+      "step": 499
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.999383162408303e-06,
+      "loss": 1.5134,
+      "step": 500
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1527564296192e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489201d0ef80ec44754ed9b7096bc634ab56fa8d1c361078d73aa8493edb9c66
+size 5752