add pai-qwen1_5-7b-doc2qa model files.

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/workspace/qwen2_7b/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.37.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123349d63f4573d94b0503e05741eca5323bafd56b76b9a9ec9bd2ede75ada73
+size 4988482416

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75582a337e58a4712e1a62a4d99cf04106aae402f396ec65374b9ec29df76b17
+size 4981244328

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd70e5f6ef42ae3dd293e2794b3f071e04f3bed0e8feb6f3bb9e7c258298474
+size 4228306968

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746ec044f34a6dce2feb38e21ebbb3b12198b411f7802d0da2c67ea160fe34bd
+size 1244659840

model.safetensors.index.json

@@ -0,0 +1,394 @@
+{
+  "metadata": {
+    "total_size": 15442649088
+  },
+  "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-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.bias": "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.bias": "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-00002-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.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,4710 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1560,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.128205128205128e-07,
+      "loss": 1.2474,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0256410256410257e-06,
+      "loss": 1.1588,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.1009,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0512820512820513e-06,
+      "loss": 1.1041,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.564102564102564e-06,
+      "loss": 1.0571,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 1.0064,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.58974358974359e-06,
+      "loss": 1.0577,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.102564102564103e-06,
+      "loss": 1.0429,
+      "step": 16
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 1.0566,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.128205128205128e-06,
+      "loss": 1.025,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.641025641025641e-06,
+      "loss": 1.0348,
+      "step": 22
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 1.0395,
+      "step": 24
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0705,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 1.0066,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 1.0498,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.205128205128205e-06,
+      "loss": 1.0381,
+      "step": 32
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.717948717948719e-06,
+      "loss": 1.0386,
+      "step": 34
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 1.0641,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.743589743589744e-06,
+      "loss": 1.0387,
+      "step": 38
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0256410256410256e-05,
+      "loss": 1.0826,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 1.0797,
+      "step": 42
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.1282051282051283e-05,
+      "loss": 1.1147,
+      "step": 44
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.1794871794871796e-05,
+      "loss": 1.0696,
+      "step": 46
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 1.0447,
+      "step": 48
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2820512820512823e-05,
+      "loss": 1.0405,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.1069,
+      "step": 52
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 1.0522,
+      "step": 54
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.435897435897436e-05,
+      "loss": 1.1448,
+      "step": 56
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4871794871794874e-05,
+      "loss": 1.0508,
+      "step": 58
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 1.1121,
+      "step": 60
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.5897435897435897e-05,
+      "loss": 1.1292,
+      "step": 62
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.641025641025641e-05,
+      "loss": 1.1066,
+      "step": 64
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6923076923076924e-05,
+      "loss": 1.1084,
+      "step": 66
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.7435897435897438e-05,
+      "loss": 1.1632,
+      "step": 68
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.794871794871795e-05,
+      "loss": 1.0844,
+      "step": 70
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 1.0884,
+      "step": 72
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8974358974358975e-05,
+      "loss": 1.1601,
+      "step": 74
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9487179487179488e-05,
+      "loss": 1.1705,
+      "step": 76
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 1.1824,
+      "step": 78
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999991012628722e-05,
+      "loss": 1.153,
+      "step": 80
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999964050676434e-05,
+      "loss": 1.1438,
+      "step": 82
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999919114627769e-05,
+      "loss": 1.1805,
+      "step": 84
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999856205290442e-05,
+      "loss": 1.137,
+      "step": 86
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999775323795232e-05,
+      "loss": 1.1703,
+      "step": 88
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999676471595962e-05,
+      "loss": 1.142,
+      "step": 90
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9995596504694764e-05,
+      "loss": 1.1743,
+      "step": 92
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999424862515604e-05,
+      "loss": 1.1679,
+      "step": 94
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9992721101571238e-05,
+      "loss": 1.1924,
+      "step": 96
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.99910139613972e-05,
+      "loss": 1.1704,
+      "step": 98
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.998912723531933e-05,
+      "loss": 1.1856,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9987060957251047e-05,
+      "loss": 1.1808,
+      "step": 102
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9984815164333163e-05,
+      "loss": 1.2127,
+      "step": 104
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998238989693323e-05,
+      "loss": 1.2006,
+      "step": 106
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.997978519864481e-05,
+      "loss": 1.1249,
+      "step": 108
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9977001116286675e-05,
+      "loss": 1.2025,
+      "step": 110
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9974037699901993e-05,
+      "loss": 1.1594,
+      "step": 112
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9970895002757413e-05,
+      "loss": 1.1506,
+      "step": 114
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9967573081342103e-05,
+      "loss": 1.2164,
+      "step": 116
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9964071995366744e-05,
+      "loss": 1.1398,
+      "step": 118
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9960391807762462e-05,
+      "loss": 1.2018,
+      "step": 120
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9956532584679676e-05,
+      "loss": 1.18,
+      "step": 122
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.995249439548693e-05,
+      "loss": 1.1726,
+      "step": 124
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.994827731276963e-05,
+      "loss": 1.1302,
+      "step": 126
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.994388141232876e-05,
+      "loss": 1.1494,
+      "step": 128
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9939306773179498e-05,
+      "loss": 1.2118,
+      "step": 130
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9934553477549795e-05,
+      "loss": 1.1385,
+      "step": 132
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.992962161087893e-05,
+      "loss": 1.1837,
+      "step": 134
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9924511261815928e-05,
+      "loss": 1.1921,
+      "step": 136
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9919222522217998e-05,
+      "loss": 1.1621,
+      "step": 138
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9913755487148874e-05,
+      "loss": 1.2225,
+      "step": 140
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9908110254877107e-05,
+      "loss": 1.139,
+      "step": 142
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.990228692687429e-05,
+      "loss": 1.1651,
+      "step": 144
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9896285607813245e-05,
+      "loss": 1.1357,
+      "step": 146
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.989010640556614e-05,
+      "loss": 1.16,
+      "step": 148
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.988374943120254e-05,
+      "loss": 1.1853,
+      "step": 150
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9877214798987428e-05,
+      "loss": 1.1863,
+      "step": 152
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9870502626379127e-05,
+      "loss": 1.2025,
+      "step": 154
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9863613034027224e-05,
+      "loss": 1.1802,
+      "step": 156
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.985654614577036e-05,
+      "loss": 1.2212,
+      "step": 158
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9849302088634034e-05,
+      "loss": 1.191,
+      "step": 160
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9841880992828306e-05,
+      "loss": 1.1702,
+      "step": 162
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9834282991745465e-05,
+      "loss": 1.1982,
+      "step": 164
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9826508221957624e-05,
+      "loss": 1.1503,
+      "step": 166
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.981855682321427e-05,
+      "loss": 1.1997,
+      "step": 168
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.981042893843974e-05,
+      "loss": 1.1724,
+      "step": 170
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.980212471373068e-05,
+      "loss": 1.1611,
+      "step": 172
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.979364429835339e-05,
+      "loss": 1.1512,
+      "step": 174
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.978498784474115e-05,
+      "loss": 1.2071,
+      "step": 176
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9776155508491482e-05,
+      "loss": 1.1767,
+      "step": 178
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9767147448363366e-05,
+      "loss": 1.162,
+      "step": 180
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9757963826274357e-05,
+      "loss": 1.1688,
+      "step": 182
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.97486048072977e-05,
+      "loss": 1.1622,
+      "step": 184
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9739070559659347e-05,
+      "loss": 1.1653,
+      "step": 186
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.972936125473495e-05,
+      "loss": 1.1141,
+      "step": 188
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9719477067046768e-05,
+      "loss": 1.1571,
+      "step": 190
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 1.2207,
+      "step": 192
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9699184757182225e-05,
+      "loss": 1.1794,
+      "step": 194
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9688776999754913e-05,
+      "loss": 1.106,
+      "step": 196
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9678195089055347e-05,
+      "loss": 1.1521,
+      "step": 198
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.966743921529065e-05,
+      "loss": 1.1671,
+      "step": 200
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.965650957179488e-05,
+      "loss": 1.1579,
+      "step": 202
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9645406355025565e-05,
+      "loss": 1.2015,
+      "step": 204
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.963412976456017e-05,
+      "loss": 1.1538,
+      "step": 206
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9622680003092503e-05,
+      "loss": 1.1832,
+      "step": 208
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9611057276429085e-05,
+      "loss": 1.2082,
+      "step": 210
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9599261793485432e-05,
+      "loss": 1.1638,
+      "step": 212
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.958729376628231e-05,
+      "loss": 1.201,
+      "step": 214
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.957515340994193e-05,
+      "loss": 1.1826,
+      "step": 216
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.956284094268407e-05,
+      "loss": 1.1293,
+      "step": 218
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.955035658582216e-05,
+      "loss": 1.1935,
+      "step": 220
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9537700563759303e-05,
+      "loss": 1.1658,
+      "step": 222
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9524873103984234e-05,
+      "loss": 1.1698,
+      "step": 224
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9511874437067243e-05,
+      "loss": 1.1962,
+      "step": 226
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.949870479665602e-05,
+      "loss": 1.1148,
+      "step": 228
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9485364419471454e-05,
+      "loss": 1.1701,
+      "step": 230
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9471853545303407e-05,
+      "loss": 1.202,
+      "step": 232
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9458172417006347e-05,
+      "loss": 1.1923,
+      "step": 234
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9444321280495045e-05,
+      "loss": 1.1486,
+      "step": 236
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9430300384740108e-05,
+      "loss": 1.163,
+      "step": 238
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9416109981763526e-05,
+      "loss": 1.166,
+      "step": 240
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9401750326634144e-05,
+      "loss": 1.1528,
+      "step": 242
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9387221677463064e-05,
+      "loss": 1.1547,
+      "step": 244
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9372524295399014e-05,
+      "loss": 1.2095,
+      "step": 246
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9357658444623655e-05,
+      "loss": 1.0905,
+      "step": 248
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9342624392346826e-05,
+      "loss": 1.169,
+      "step": 250
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9327422408801744e-05,
+      "loss": 1.1979,
+      "step": 252
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9312052767240153e-05,
+      "loss": 1.1515,
+      "step": 254
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.92965157439274e-05,
+      "loss": 1.1893,
+      "step": 256
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9280811618137486e-05,
+      "loss": 1.174,
+      "step": 258
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9264940672148018e-05,
+      "loss": 1.2114,
+      "step": 260
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9248903191235177e-05,
+      "loss": 1.1677,
+      "step": 262
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9232699463668543e-05,
+      "loss": 1.1598,
+      "step": 264
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9216329780705955e-05,
+      "loss": 1.1887,
+      "step": 266
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9199794436588244e-05,
+      "loss": 1.15,
+      "step": 268
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9183093728533966e-05,
+      "loss": 1.1685,
+      "step": 270
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.916622795673405e-05,
+      "loss": 1.1508,
+      "step": 272
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9149197424346405e-05,
+      "loss": 1.1324,
+      "step": 274
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.913200243749046e-05,
+      "loss": 1.1601,
+      "step": 276
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9114643305241678e-05,
+      "loss": 1.1349,
+      "step": 278
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9097120339625994e-05,
+      "loss": 1.1617,
+      "step": 280
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9079433855614203e-05,
+      "loss": 1.1513,
+      "step": 282
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9061584171116302e-05,
+      "loss": 1.17,
+      "step": 284
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9043571606975776e-05,
+      "loss": 1.1732,
+      "step": 286
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9025396486963827e-05,
+      "loss": 1.1233,
+      "step": 288
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.900705913777356e-05,
+      "loss": 1.1701,
+      "step": 290
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.89885598890141e-05,
+      "loss": 1.161,
+      "step": 292
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8969899073204687e-05,
+      "loss": 1.1404,
+      "step": 294
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.895107702576868e-05,
+      "loss": 1.2028,
+      "step": 296
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8932094085027534e-05,
+      "loss": 1.1943,
+      "step": 298
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.891295059219472e-05,
+      "loss": 1.1376,
+      "step": 300
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.88936468913696e-05,
+      "loss": 1.1743,
+      "step": 302
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8874183329531222e-05,
+      "loss": 1.1552,
+      "step": 304
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 1.1528,
+      "step": 306
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.883477802509192e-05,
+      "loss": 1.1543,
+      "step": 308
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.88148369907912e-05,
+      "loss": 1.1008,
+      "step": 310
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 1.1573,
+      "step": 312
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.877447995019596e-05,
+      "loss": 1.1236,
+      "step": 314
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.875406466930886e-05,
+      "loss": 1.1546,
+      "step": 316
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8733492036363007e-05,
+      "loss": 1.1547,
+      "step": 318
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8712762421146185e-05,
+      "loss": 1.1608,
+      "step": 320
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8691876196267892e-05,
+      "loss": 1.1708,
+      "step": 322
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.867083373715264e-05,
+      "loss": 1.1485,
+      "step": 324
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8649635422033218e-05,
+      "loss": 1.213,
+      "step": 326
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.862828163194388e-05,
+      "loss": 1.137,
+      "step": 328
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8606772750713503e-05,
+      "loss": 1.1987,
+      "step": 330
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8585109164958698e-05,
+      "loss": 1.1287,
+      "step": 332
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8563291264076834e-05,
+      "loss": 1.1653,
+      "step": 334
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8541319440239066e-05,
+      "loss": 1.1305,
+      "step": 336
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.851919408838327e-05,
+      "loss": 1.186,
+      "step": 338
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8496915606206952e-05,
+      "loss": 1.1371,
+      "step": 340
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.847448439416009e-05,
+      "loss": 1.1589,
+      "step": 342
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.845190085543795e-05,
+      "loss": 1.0932,
+      "step": 344
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.842916539597382e-05,
+      "loss": 1.1354,
+      "step": 346
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8406278424431737e-05,
+      "loss": 1.1056,
+      "step": 348
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8383240352199118e-05,
+      "loss": 1.1402,
+      "step": 350
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8360051593379383e-05,
+      "loss": 1.1689,
+      "step": 352
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8336712564784506e-05,
+      "loss": 1.1761,
+      "step": 354
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8313223685927507e-05,
+      "loss": 1.101,
+      "step": 356
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8289585379014942e-05,
+      "loss": 1.1944,
+      "step": 358
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8265798068939295e-05,
+      "loss": 1.2067,
+      "step": 360
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8241862183271338e-05,
+      "loss": 1.1291,
+      "step": 362
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.821777815225245e-05,
+      "loss": 1.1814,
+      "step": 364
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.81935464087869e-05,
+      "loss": 1.1324,
+      "step": 366
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8169167388434024e-05,
+      "loss": 1.1929,
+      "step": 368
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8144641529400445e-05,
+      "loss": 1.1131,
+      "step": 370
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8119969272532164e-05,
+      "loss": 1.1646,
+      "step": 372
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8095151061306647e-05,
+      "loss": 1.1554,
+      "step": 374
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8070187341824848e-05,
+      "loss": 1.1406,
+      "step": 376
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8045078562803203e-05,
+      "loss": 1.1385,
+      "step": 378
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.8019825175565544e-05,
+      "loss": 1.1865,
+      "step": 380
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.7994427634035016e-05,
+      "loss": 1.1631,
+      "step": 382
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.7968886394725876e-05,
+      "loss": 1.1112,
+      "step": 384
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.7943201916735337e-05,
+      "loss": 1.1238,
+      "step": 386
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.791737466173527e-05,
+      "loss": 1.1653,
+      "step": 388
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.789140509396394e-05,
+      "loss": 1.1407,
+      "step": 390
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.7865293680217636e-05,
+      "loss": 1.1344,
+      "step": 392
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7839040889842307e-05,
+      "loss": 1.1513,
+      "step": 394
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7812647194725093e-05,
+      "loss": 1.1392,
+      "step": 396
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7786113069285877e-05,
+      "loss": 1.0903,
+      "step": 398
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7759438990468726e-05,
+      "loss": 1.1068,
+      "step": 400
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7732625437733338e-05,
+      "loss": 1.1482,
+      "step": 402
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7705672893046425e-05,
+      "loss": 1.1475,
+      "step": 404
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.767858184087304e-05,
+      "loss": 1.1514,
+      "step": 406
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.765135276816787e-05,
+      "loss": 1.1395,
+      "step": 408
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7623986164366487e-05,
+      "loss": 1.1084,
+      "step": 410
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7596482521376546e-05,
+      "loss": 1.1748,
+      "step": 412
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7568842333568952e-05,
+      "loss": 1.1709,
+      "step": 414
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7541066097768965e-05,
+      "loss": 1.1961,
+      "step": 416
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7513154313247273e-05,
+      "loss": 1.1287,
+      "step": 418
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 1.1484,
+      "step": 420
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7456926107294765e-05,
+      "loss": 1.1195,
+      "step": 422
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.742861069655148e-05,
+      "loss": 1.1157,
+      "step": 424
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7400161758443377e-05,
+      "loss": 1.1829,
+      "step": 426
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.737157980433279e-05,
+      "loss": 1.1937,
+      "step": 428
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7342865347972987e-05,
+      "loss": 1.0915,
+      "step": 430
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7314018905498932e-05,
+      "loss": 1.1741,
+      "step": 432
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.7285040995418003e-05,
+      "loss": 1.1407,
+      "step": 434
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.7255932138600665e-05,
+      "loss": 1.1625,
+      "step": 436
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.7226692858271133e-05,
+      "loss": 1.17,
+      "step": 438
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.7197323679997943e-05,
+      "loss": 1.1736,
+      "step": 440
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7167825131684516e-05,
+      "loss": 1.1646,
+      "step": 442
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7138197743559656e-05,
+      "loss": 1.1301,
+      "step": 444
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7108442048168038e-05,
+      "loss": 1.1564,
+      "step": 446
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.707855858036063e-05,
+      "loss": 1.1653,
+      "step": 448
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.7048547877285078e-05,
+      "loss": 1.1335,
+      "step": 450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.7018410478376033e-05,
+      "loss": 1.1478,
+      "step": 452
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.6988146925345487e-05,
+      "loss": 1.1436,
+      "step": 454
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.695775776217301e-05,
+      "loss": 1.1958,
+      "step": 456
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6927243535095995e-05,
+      "loss": 1.1215,
+      "step": 458
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6896604792599813e-05,
+      "loss": 1.1639,
+      "step": 460
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.686584208540797e-05,
+      "loss": 1.1605,
+      "step": 462
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6834955966472214e-05,
+      "loss": 1.0812,
+      "step": 464
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6803946990962577e-05,
+      "loss": 1.1427,
+      "step": 466
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6772815716257414e-05,
+      "loss": 1.1497,
+      "step": 468
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6741562701933366e-05,
+      "loss": 1.1058,
+      "step": 470
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.671018850975533e-05,
+      "loss": 1.095,
+      "step": 472
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6678693703666327e-05,
+      "loss": 1.1272,
+      "step": 474
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.664707884977739e-05,
+      "loss": 1.1257,
+      "step": 476
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.661534451635738e-05,
+      "loss": 1.1318,
+      "step": 478
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6583491273822763e-05,
+      "loss": 1.1335,
+      "step": 480
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.655151969472738e-05,
+      "loss": 1.1529,
+      "step": 482
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6519430353752138e-05,
+      "loss": 1.1674,
+      "step": 484
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6487223827694673e-05,
+      "loss": 1.1743,
+      "step": 486
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6454900695459e-05,
+      "loss": 1.186,
+      "step": 488
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6422461538045104e-05,
+      "loss": 1.1251,
+      "step": 490
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.638990693853848e-05,
+      "loss": 1.0951,
+      "step": 492
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6357237482099682e-05,
+      "loss": 1.1618,
+      "step": 494
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.6324453755953772e-05,
+      "loss": 1.1283,
+      "step": 496
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.6291556349379794e-05,
+      "loss": 1.1174,
+      "step": 498
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.6258545853700157e-05,
+      "loss": 1.17,
+      "step": 500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.622542286227003e-05,
+      "loss": 1.1735,
+      "step": 502
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.6192187970466646e-05,
+      "loss": 1.0973,
+      "step": 504
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.615884177567863e-05,
+      "loss": 1.1478,
+      "step": 506
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.6125384877295255e-05,
+      "loss": 1.1254,
+      "step": 508
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.6091817876695655e-05,
+      "loss": 1.1599,
+      "step": 510
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.6058141377238026e-05,
+      "loss": 1.1401,
+      "step": 512
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.602435598424877e-05,
+      "loss": 1.1241,
+      "step": 514
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.599046230501163e-05,
+      "loss": 1.1915,
+      "step": 516
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.5956460948756765e-05,
+      "loss": 1.1119,
+      "step": 518
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.5922352526649803e-05,
+      "loss": 1.1226,
+      "step": 520
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.5888137651780847e-05,
+      "loss": 1.1635,
+      "step": 522
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.585381693915346e-05,
+      "loss": 1.123,
+      "step": 524
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.581939100567363e-05,
+      "loss": 1.178,
+      "step": 526
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5784860470138633e-05,
+      "loss": 1.152,
+      "step": 528
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5750225953225968e-05,
+      "loss": 1.1314,
+      "step": 530
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5715488077482152e-05,
+      "loss": 1.1556,
+      "step": 532
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 1.1427,
+      "step": 534
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5645704748965193e-05,
+      "loss": 1.1633,
+      "step": 536
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5610660550529413e-05,
+      "loss": 1.1237,
+      "step": 538
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.557551550191467e-05,
+      "loss": 1.1241,
+      "step": 540
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.554027023484416e-05,
+      "loss": 1.1212,
+      "step": 542
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.550492538284249e-05,
+      "loss": 1.1125,
+      "step": 544
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5469481581224274e-05,
+      "loss": 1.1345,
+      "step": 546
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5433939467082713e-05,
+      "loss": 1.0837,
+      "step": 548
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5398299679278172e-05,
+      "loss": 1.1531,
+      "step": 550
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5362562858426655e-05,
+      "loss": 1.179,
+      "step": 552
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5326729646888314e-05,
+      "loss": 1.1123,
+      "step": 554
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5290800688755906e-05,
+      "loss": 1.1616,
+      "step": 556
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.5254776629843204e-05,
+      "loss": 1.1236,
+      "step": 558
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.5218658117673389e-05,
+      "loss": 1.1254,
+      "step": 560
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.518244580146742e-05,
+      "loss": 1.0994,
+      "step": 562
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.5146140332132359e-05,
+      "loss": 1.0841,
+      "step": 564
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5109742362249673e-05,
+      "loss": 1.1284,
+      "step": 566
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5073252546063493e-05,
+      "loss": 1.108,
+      "step": 568
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5036671539468879e-05,
+      "loss": 1.1494,
+      "step": 570
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.1226,
+      "step": 572
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4963238586818346e-05,
+      "loss": 1.0835,
+      "step": 574
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4926387960700843e-05,
+      "loss": 1.1047,
+      "step": 576
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.488944878402802e-05,
+      "loss": 1.0861,
+      "step": 578
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4852421720772064e-05,
+      "loss": 1.1066,
+      "step": 580
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4815307436484898e-05,
+      "loss": 1.1382,
+      "step": 582
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4778106598286235e-05,
+      "loss": 1.0789,
+      "step": 584
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4740819874851562e-05,
+      "loss": 1.1367,
+      "step": 586
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4703447936400135e-05,
+      "loss": 1.1017,
+      "step": 588
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4665991454682924e-05,
+      "loss": 1.1009,
+      "step": 590
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4628451102970546e-05,
+      "loss": 1.08,
+      "step": 592
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4590827556041158e-05,
+      "loss": 1.1003,
+      "step": 594
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4553121490168335e-05,
+      "loss": 1.1396,
+      "step": 596
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.4515333583108896e-05,
+      "loss": 1.1184,
+      "step": 598
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.4477464514090745e-05,
+      "loss": 1.1374,
+      "step": 600
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.443951496380065e-05,
+      "loss": 1.1114,
+      "step": 602
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.4401485614372009e-05,
+      "loss": 1.0906,
+      "step": 604
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.4363377149372584e-05,
+      "loss": 1.126,
+      "step": 606
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.4325190253792222e-05,
+      "loss": 1.0907,
+      "step": 608
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.4286925614030542e-05,
+      "loss": 1.126,
+      "step": 610
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.4248583917884595e-05,
+      "loss": 1.1183,
+      "step": 612
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4210165854536495e-05,
+      "loss": 1.1165,
+      "step": 614
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4171672114541042e-05,
+      "loss": 1.1149,
+      "step": 616
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4133103389813302e-05,
+      "loss": 1.1124,
+      "step": 618
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.409446037361617e-05,
+      "loss": 1.0864,
+      "step": 620
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.4055743760547918e-05,
+      "loss": 1.105,
+      "step": 622
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.4016954246529697e-05,
+      "loss": 1.1575,
+      "step": 624
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3978092528793032e-05,
+      "loss": 1.1155,
+      "step": 626
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.39391593058673e-05,
+      "loss": 1.12,
+      "step": 628
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.3900155277567157e-05,
+      "loss": 1.1048,
+      "step": 630
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.3861081144979975e-05,
+      "loss": 1.1003,
+      "step": 632
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.382193761045322e-05,
+      "loss": 1.0671,
+      "step": 634
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.378272537758185e-05,
+      "loss": 1.0981,
+      "step": 636
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3743445151195658e-05,
+      "loss": 1.132,
+      "step": 638
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.37040976373466e-05,
+      "loss": 1.1709,
+      "step": 640
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3664683543296114e-05,
+      "loss": 1.1083,
+      "step": 642
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3625203577502384e-05,
+      "loss": 1.1272,
+      "step": 644
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3585658449607632e-05,
+      "loss": 1.0967,
+      "step": 646
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 1.0316,
+      "step": 648
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3506375551927546e-05,
+      "loss": 1.0944,
+      "step": 650
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3466639207231882e-05,
+      "loss": 1.1149,
+      "step": 652
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3426840550588933e-05,
+      "loss": 1.0834,
+      "step": 654
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3386980297369308e-05,
+      "loss": 1.0853,
+      "step": 656
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3347059164050796e-05,
+      "loss": 1.0994,
+      "step": 658
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.3307077868205487e-05,
+      "loss": 1.127,
+      "step": 660
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.3267037128486883e-05,
+      "loss": 1.1307,
+      "step": 662
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.3226937664616977e-05,
+      "loss": 1.1151,
+      "step": 664
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.3186780197373306e-05,
+      "loss": 1.1228,
+      "step": 666
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.3146565448576002e-05,
+      "loss": 1.0869,
+      "step": 668
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.3106294141074825e-05,
+      "loss": 1.0714,
+      "step": 670
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.3065966998736155e-05,
+      "loss": 1.1025,
+      "step": 672
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.302558474643e-05,
+      "loss": 1.0993,
+      "step": 674
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2985148110016947e-05,
+      "loss": 1.0594,
+      "step": 676
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2944657816335124e-05,
+      "loss": 1.0898,
+      "step": 678
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2904114593187136e-05,
+      "loss": 1.1221,
+      "step": 680
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2863519169326984e-05,
+      "loss": 1.1194,
+      "step": 682
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2822872274446958e-05,
+      "loss": 1.1323,
+      "step": 684
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2782174639164528e-05,
+      "loss": 1.1366,
+      "step": 686
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2741426995009214e-05,
+      "loss": 1.096,
+      "step": 688
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2700630074409427e-05,
+      "loss": 1.0622,
+      "step": 690
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2659784610679318e-05,
+      "loss": 1.1226,
+      "step": 692
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2618891338005574e-05,
+      "loss": 1.0771,
+      "step": 694
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2577950991434249e-05,
+      "loss": 1.1363,
+      "step": 696
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2536964306857526e-05,
+      "loss": 1.0735,
+      "step": 698
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2495932021000516e-05,
+      "loss": 1.0877,
+      "step": 700
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2454854871407993e-05,
+      "loss": 1.0683,
+      "step": 702
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2413733596431141e-05,
+      "loss": 1.1172,
+      "step": 704
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.2372568935214298e-05,
+      "loss": 1.068,
+      "step": 706
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.2331361627681645e-05,
+      "loss": 1.0995,
+      "step": 708
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.2290112414523927e-05,
+      "loss": 1.0648,
+      "step": 710
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.2248822037185137e-05,
+      "loss": 1.0978,
+      "step": 712
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.2207491237849174e-05,
+      "loss": 1.0318,
+      "step": 714
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.2166120759426515e-05,
+      "loss": 1.1007,
+      "step": 716
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.2124711345540861e-05,
+      "loss": 1.0964,
+      "step": 718
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.2083263740515764e-05,
+      "loss": 1.1559,
+      "step": 720
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.2041778689361254e-05,
+      "loss": 1.1272,
+      "step": 722
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.2000256937760446e-05,
+      "loss": 1.066,
+      "step": 724
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1958699232056135e-05,
+      "loss": 1.0868,
+      "step": 726
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1917106319237386e-05,
+      "loss": 1.0778,
+      "step": 728
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1875478946926094e-05,
+      "loss": 1.0461,
+      "step": 730
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1833817863363563e-05,
+      "loss": 1.0645,
+      "step": 732
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1792123817397041e-05,
+      "loss": 1.1091,
+      "step": 734
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1750397558466273e-05,
+      "loss": 1.1129,
+      "step": 736
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1708639836590024e-05,
+      "loss": 1.0704,
+      "step": 738
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1666851402352587e-05,
+      "loss": 1.0903,
+      "step": 740
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1625033006890316e-05,
+      "loss": 1.0858,
+      "step": 742
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.15831854018781e-05,
+      "loss": 1.1189,
+      "step": 744
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.154130933951587e-05,
+      "loss": 1.0825,
+      "step": 746
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1499405572515059e-05,
+      "loss": 1.0744,
+      "step": 748
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1457474854085095e-05,
+      "loss": 1.0701,
+      "step": 750
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1415517937919846e-05,
+      "loss": 1.0705,
+      "step": 752
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.1373535578184083e-05,
+      "loss": 1.0532,
+      "step": 754
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.1331528529499909e-05,
+      "loss": 1.1365,
+      "step": 756
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.1289497546933212e-05,
+      "loss": 1.0797,
+      "step": 758
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.124744338598008e-05,
+      "loss": 1.0715,
+      "step": 760
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.1205366802553231e-05,
+      "loss": 1.1339,
+      "step": 762
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.1163268552968422e-05,
+      "loss": 1.0962,
+      "step": 764
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.112114939393085e-05,
+      "loss": 1.075,
+      "step": 766
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.1079010082521557e-05,
+      "loss": 1.056,
+      "step": 768
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.1036851376183812e-05,
+      "loss": 1.05,
+      "step": 770
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0994674032709514e-05,
+      "loss": 1.0404,
+      "step": 772
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.095247881022555e-05,
+      "loss": 1.0539,
+      "step": 774
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.091026646718018e-05,
+      "loss": 1.0554,
+      "step": 776
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0868037762329405e-05,
+      "loss": 1.0717,
+      "step": 778
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 1.0589,
+      "step": 780
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0783534303692493e-05,
+      "loss": 0.7134,
+      "step": 782
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.0741261068834266e-05,
+      "loss": 0.6371,
+      "step": 784
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.0698974509999159e-05,
+      "loss": 0.6415,
+      "step": 786
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.0656675387277183e-05,
+      "loss": 0.6547,
+      "step": 788
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.0614364460984178e-05,
+      "loss": 0.6518,
+      "step": 790
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.057204249164815e-05,
+      "loss": 0.672,
+      "step": 792
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0529710239995606e-05,
+      "loss": 0.669,
+      "step": 794
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0487368466937866e-05,
+      "loss": 0.6394,
+      "step": 796
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0445017933557404e-05,
+      "loss": 0.6664,
+      "step": 798
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.0402659401094154e-05,
+      "loss": 0.6451,
+      "step": 800
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.036029363093183e-05,
+      "loss": 0.6917,
+      "step": 802
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.0317921384584245e-05,
+      "loss": 0.6579,
+      "step": 804
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.0275543423681622e-05,
+      "loss": 0.6505,
+      "step": 806
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.0233160509956893e-05,
+      "loss": 0.636,
+      "step": 808
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.0190773405232024e-05,
+      "loss": 0.6344,
+      "step": 810
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.014838287140431e-05,
+      "loss": 0.6315,
+      "step": 812
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.010598967043268e-05,
+      "loss": 0.6549,
+      "step": 814
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.0063594564324014e-05,
+      "loss": 0.6585,
+      "step": 816
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.0021198315119426e-05,
+      "loss": 0.6358,
+      "step": 818
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.97880168488058e-06,
+      "loss": 0.6627,
+      "step": 820
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.936405435675991e-06,
+      "loss": 0.6451,
+      "step": 822
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.894010329567322e-06,
+      "loss": 0.6304,
+      "step": 824
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.851617128595694e-06,
+      "loss": 0.6271,
+      "step": 826
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.809226594767979e-06,
+      "loss": 0.6649,
+      "step": 828
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.766839490043108e-06,
+      "loss": 0.6811,
+      "step": 830
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.724456576318383e-06,
+      "loss": 0.6136,
+      "step": 832
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.682078615415755e-06,
+      "loss": 0.6876,
+      "step": 834
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.63970636906817e-06,
+      "loss": 0.6612,
+      "step": 836
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.597340598905851e-06,
+      "loss": 0.6553,
+      "step": 838
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.554982066442601e-06,
+      "loss": 0.6467,
+      "step": 840
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.512631533062138e-06,
+      "loss": 0.6705,
+      "step": 842
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.470289760004398e-06,
+      "loss": 0.6552,
+      "step": 844
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.427957508351852e-06,
+      "loss": 0.6369,
+      "step": 846
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.385635539015824e-06,
+      "loss": 0.6447,
+      "step": 848
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.343324612722819e-06,
+      "loss": 0.6566,
+      "step": 850
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.301025490000843e-06,
+      "loss": 0.6285,
+      "step": 852
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.25873893116574e-06,
+      "loss": 0.6479,
+      "step": 854
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.216465696307513e-06,
+      "loss": 0.6463,
+      "step": 856
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.174206545276678e-06,
+      "loss": 0.6277,
+      "step": 858
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.131962237670599e-06,
+      "loss": 0.6608,
+      "step": 860
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 9.089733532819825e-06,
+      "loss": 0.6512,
+      "step": 862
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 9.047521189774456e-06,
+      "loss": 0.6306,
+      "step": 864
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 9.005325967290489e-06,
+      "loss": 0.6236,
+      "step": 866
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.963148623816191e-06,
+      "loss": 0.653,
+      "step": 868
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.920989917478446e-06,
+      "loss": 0.656,
+      "step": 870
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.878850606069152e-06,
+      "loss": 0.6556,
+      "step": 872
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.836731447031581e-06,
+      "loss": 0.6574,
+      "step": 874
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.79463319744677e-06,
+      "loss": 0.6456,
+      "step": 876
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.752556614019924e-06,
+      "loss": 0.6353,
+      "step": 878
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.710502453066791e-06,
+      "loss": 0.6369,
+      "step": 880
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.668471470500094e-06,
+      "loss": 0.6316,
+      "step": 882
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.626464421815919e-06,
+      "loss": 0.6415,
+      "step": 884
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.584482062080154e-06,
+      "loss": 0.6522,
+      "step": 886
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.542525145914907e-06,
+      "loss": 0.6476,
+      "step": 888
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.500594427484946e-06,
+      "loss": 0.625,
+      "step": 890
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.458690660484134e-06,
+      "loss": 0.6545,
+      "step": 892
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.416814598121901e-06,
+      "loss": 0.6584,
+      "step": 894
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.374966993109689e-06,
+      "loss": 0.6388,
+      "step": 896
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.333148597647414e-06,
+      "loss": 0.6499,
+      "step": 898
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.291360163409978e-06,
+      "loss": 0.6556,
+      "step": 900
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.249602441533727e-06,
+      "loss": 0.6359,
+      "step": 902
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.207876182602959e-06,
+      "loss": 0.612,
+      "step": 904
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.16618213663644e-06,
+      "loss": 0.6158,
+      "step": 906
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.12452105307391e-06,
+      "loss": 0.6362,
+      "step": 908
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 8.082893680762619e-06,
+      "loss": 0.6402,
+      "step": 910
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 8.041300767943867e-06,
+      "loss": 0.6629,
+      "step": 912
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.999743062239557e-06,
+      "loss": 0.6136,
+      "step": 914
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.958221310638749e-06,
+      "loss": 0.6517,
+      "step": 916
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.916736259484239e-06,
+      "loss": 0.6635,
+      "step": 918
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.875288654459144e-06,
+      "loss": 0.6405,
+      "step": 920
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.833879240573487e-06,
+      "loss": 0.6242,
+      "step": 922
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.792508762150833e-06,
+      "loss": 0.6642,
+      "step": 924
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.751177962814867e-06,
+      "loss": 0.6297,
+      "step": 926
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.709887585476075e-06,
+      "loss": 0.6458,
+      "step": 928
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.668638372318359e-06,
+      "loss": 0.6413,
+      "step": 930
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.627431064785705e-06,
+      "loss": 0.6093,
+      "step": 932
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.5862664035688604e-06,
+      "loss": 0.6088,
+      "step": 934
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.545145128592009e-06,
+      "loss": 0.628,
+      "step": 936
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.504067978999484e-06,
+      "loss": 0.6382,
+      "step": 938
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.463035693142473e-06,
+      "loss": 0.6458,
+      "step": 940
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.422049008565757e-06,
+      "loss": 0.638,
+      "step": 942
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.38110866199443e-06,
+      "loss": 0.6704,
+      "step": 944
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.340215389320686e-06,
+      "loss": 0.6049,
+      "step": 946
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.299369925590575e-06,
+      "loss": 0.6124,
+      "step": 948
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.258573004990789e-06,
+      "loss": 0.6417,
+      "step": 950
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.217825360835475e-06,
+      "loss": 0.6359,
+      "step": 952
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.1771277255530456e-06,
+      "loss": 0.6347,
+      "step": 954
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.136480830673018e-06,
+      "loss": 0.6138,
+      "step": 956
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.095885406812866e-06,
+      "loss": 0.6218,
+      "step": 958
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.05534218366488e-06,
+      "loss": 0.614,
+      "step": 960
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.014851889983058e-06,
+      "loss": 0.6245,
+      "step": 962
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.974415253570003e-06,
+      "loss": 0.6275,
+      "step": 964
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.934033001263847e-06,
+      "loss": 0.6227,
+      "step": 966
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.893705858925179e-06,
+      "loss": 0.6287,
+      "step": 968
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.853434551424001e-06,
+      "loss": 0.6074,
+      "step": 970
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.813219802626698e-06,
+      "loss": 0.6325,
+      "step": 972
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.773062335383024e-06,
+      "loss": 0.6666,
+      "step": 974
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.73296287151312e-06,
+      "loss": 0.6135,
+      "step": 976
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.692922131794517e-06,
+      "loss": 0.5956,
+      "step": 978
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.652940835949208e-06,
+      "loss": 0.5967,
+      "step": 980
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.6130197026306945e-06,
+      "loss": 0.6195,
+      "step": 982
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.573159449411071e-06,
+      "loss": 0.6283,
+      "step": 984
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.533360792768122e-06,
+      "loss": 0.6356,
+      "step": 986
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.4936244480724575e-06,
+      "loss": 0.595,
+      "step": 988
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.453951129574644e-06,
+      "loss": 0.6115,
+      "step": 990
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.4143415503923676e-06,
+      "loss": 0.6164,
+      "step": 992
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.374796422497622e-06,
+      "loss": 0.628,
+      "step": 994
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.335316456703891e-06,
+      "loss": 0.6135,
+      "step": 996
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.295902362653401e-06,
+      "loss": 0.6223,
+      "step": 998
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.256554848804343e-06,
+      "loss": 0.6014,
+      "step": 1000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.2172746224181524e-06,
+      "loss": 0.6463,
+      "step": 1002
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.178062389546784e-06,
+      "loss": 0.6153,
+      "step": 1004
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.138918855020028e-06,
+      "loss": 0.6424,
+      "step": 1006
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.099844722432844e-06,
+      "loss": 0.6166,
+      "step": 1008
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.060840694132701e-06,
+      "loss": 0.6097,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 6.021907471206971e-06,
+      "loss": 0.6262,
+      "step": 1012
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.983045753470308e-06,
+      "loss": 0.6141,
+      "step": 1014
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.944256239452085e-06,
+      "loss": 0.6047,
+      "step": 1016
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.905539626383831e-06,
+      "loss": 0.6547,
+      "step": 1018
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.866896610186701e-06,
+      "loss": 0.5995,
+      "step": 1020
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.82832788545896e-06,
+      "loss": 0.6131,
+      "step": 1022
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.789834145463506e-06,
+      "loss": 0.6484,
+      "step": 1024
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.7514160821154085e-06,
+      "loss": 0.6497,
+      "step": 1026
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.713074385969457e-06,
+      "loss": 0.6031,
+      "step": 1028
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.67480974620778e-06,
+      "loss": 0.6294,
+      "step": 1030
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.63662285062742e-06,
+      "loss": 0.6053,
+      "step": 1032
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.598514385627997e-06,
+      "loss": 0.622,
+      "step": 1034
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.56048503619935e-06,
+      "loss": 0.6325,
+      "step": 1036
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.522535485909258e-06,
+      "loss": 0.6111,
+      "step": 1038
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.484666416891109e-06,
+      "loss": 0.6061,
+      "step": 1040
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.446878509831668e-06,
+      "loss": 0.5885,
+      "step": 1042
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.409172443958844e-06,
+      "loss": 0.6158,
+      "step": 1044
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.371548897029457e-06,
+      "loss": 0.6153,
+      "step": 1046
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.334008545317082e-06,
+      "loss": 0.5985,
+      "step": 1048
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.2965520635998676e-06,
+      "loss": 0.6004,
+      "step": 1050
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.259180125148442e-06,
+      "loss": 0.6108,
+      "step": 1052
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.22189340171377e-06,
+      "loss": 0.6343,
+      "step": 1054
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.184692563515104e-06,
+      "loss": 0.6376,
+      "step": 1056
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 5.147578279227943e-06,
+      "loss": 0.5997,
+      "step": 1058
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 5.110551215971981e-06,
+      "loss": 0.6192,
+      "step": 1060
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 5.073612039299157e-06,
+      "loss": 0.6276,
+      "step": 1062
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 5.036761413181659e-06,
+      "loss": 0.6493,
+      "step": 1064
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.5993,
+      "step": 1066
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.963328460531127e-06,
+      "loss": 0.5804,
+      "step": 1068
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.926747453936509e-06,
+      "loss": 0.6444,
+      "step": 1070
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.890257637750332e-06,
+      "loss": 0.6287,
+      "step": 1072
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.853859667867641e-06,
+      "loss": 0.5872,
+      "step": 1074
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.817554198532582e-06,
+      "loss": 0.6015,
+      "step": 1076
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.781341882326615e-06,
+      "loss": 0.5941,
+      "step": 1078
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.745223370156797e-06,
+      "loss": 0.6406,
+      "step": 1080
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.709199311244098e-06,
+      "loss": 0.6334,
+      "step": 1082
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.673270353111687e-06,
+      "loss": 0.647,
+      "step": 1084
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.63743714157335e-06,
+      "loss": 0.6168,
+      "step": 1086
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.6017003207218294e-06,
+      "loss": 0.595,
+      "step": 1088
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.566060532917288e-06,
+      "loss": 0.6195,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.530518418775734e-06,
+      "loss": 0.6084,
+      "step": 1092
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.4950746171575135e-06,
+      "loss": 0.5976,
+      "step": 1094
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.459729765155842e-06,
+      "loss": 0.6086,
+      "step": 1096
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.424484498085335e-06,
+      "loss": 0.5855,
+      "step": 1098
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.389339449470592e-06,
+      "loss": 0.6503,
+      "step": 1100
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.354295251034811e-06,
+      "loss": 0.6035,
+      "step": 1102
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.319352532688444e-06,
+      "loss": 0.5885,
+      "step": 1104
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.284511922517853e-06,
+      "loss": 0.5765,
+      "step": 1106
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.249774046774034e-06,
+      "loss": 0.6631,
+      "step": 1108
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.2151395298613675e-06,
+      "loss": 0.6236,
+      "step": 1110
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 4.180608994326371e-06,
+      "loss": 0.6516,
+      "step": 1112
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 4.1461830608465385e-06,
+      "loss": 0.6293,
+      "step": 1114
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 4.111862348219158e-06,
+      "loss": 0.6361,
+      "step": 1116
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 4.077647473350201e-06,
+      "loss": 0.6274,
+      "step": 1118
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.04353905124324e-06,
+      "loss": 0.6109,
+      "step": 1120
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.009537694988372e-06,
+      "loss": 0.5974,
+      "step": 1122
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.975644015751234e-06,
+      "loss": 0.5849,
+      "step": 1124
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.941858622761975e-06,
+      "loss": 0.6025,
+      "step": 1126
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.908182123304344e-06,
+      "loss": 0.6323,
+      "step": 1128
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.8746151227047455e-06,
+      "loss": 0.58,
+      "step": 1130
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.84115822432137e-06,
+      "loss": 0.631,
+      "step": 1132
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.807812029533362e-06,
+      "loss": 0.6424,
+      "step": 1134
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.7745771377299758e-06,
+      "loss": 0.6061,
+      "step": 1136
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.7414541462998446e-06,
+      "loss": 0.6172,
+      "step": 1138
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.708443650620206e-06,
+      "loss": 0.6402,
+      "step": 1140
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.6755462440462288e-06,
+      "loss": 0.5702,
+      "step": 1142
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.6427625179003223e-06,
+      "loss": 0.6181,
+      "step": 1144
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.6100930614615204e-06,
+      "loss": 0.6158,
+      "step": 1146
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.5775384619549e-06,
+      "loss": 0.586,
+      "step": 1148
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.5450993045409997e-06,
+      "loss": 0.6334,
+      "step": 1150
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.5127761723053313e-06,
+      "loss": 0.5789,
+      "step": 1152
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.4805696462478634e-06,
+      "loss": 0.6111,
+      "step": 1154
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.448480305272619e-06,
+      "loss": 0.5845,
+      "step": 1156
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.41650872617724e-06,
+      "loss": 0.6199,
+      "step": 1158
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.384655483642624e-06,
+      "loss": 0.6317,
+      "step": 1160
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.352921150222612e-06,
+      "loss": 0.6299,
+      "step": 1162
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.321306296333673e-06,
+      "loss": 0.5978,
+      "step": 1164
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.2898114902446708e-06,
+      "loss": 0.6216,
+      "step": 1166
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.2584372980666344e-06,
+      "loss": 0.619,
+      "step": 1168
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.2271842837425917e-06,
+      "loss": 0.6271,
+      "step": 1170
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.1960530090374277e-06,
+      "loss": 0.5788,
+      "step": 1172
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.165044033527789e-06,
+      "loss": 0.5523,
+      "step": 1174
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.134157914592032e-06,
+      "loss": 0.5863,
+      "step": 1176
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.1033952074001882e-06,
+      "loss": 0.6359,
+      "step": 1178
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.0727564649040066e-06,
+      "loss": 0.6057,
+      "step": 1180
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 3.042242237826991e-06,
+      "loss": 0.5813,
+      "step": 1182
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 3.011853074654515e-06,
+      "loss": 0.6351,
+      "step": 1184
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.981589521623973e-06,
+      "loss": 0.5861,
+      "step": 1186
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.951452122714926e-06,
+      "loss": 0.608,
+      "step": 1188
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.9214414196393702e-06,
+      "loss": 0.6156,
+      "step": 1190
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.8915579518319626e-06,
+      "loss": 0.6082,
+      "step": 1192
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.861802256440348e-06,
+      "loss": 0.6268,
+      "step": 1194
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.8321748683154893e-06,
+      "loss": 0.5921,
+      "step": 1196
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.8026763200020557e-06,
+      "loss": 0.5828,
+      "step": 1198
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.773307141728867e-06,
+      "loss": 0.6255,
+      "step": 1200
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.744067861399333e-06,
+      "loss": 0.5878,
+      "step": 1202
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.714959004582003e-06,
+      "loss": 0.6113,
+      "step": 1204
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.6859810945010687e-06,
+      "loss": 0.6255,
+      "step": 1206
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.6571346520270147e-06,
+      "loss": 0.5998,
+      "step": 1208
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.628420195667214e-06,
+      "loss": 0.607,
+      "step": 1210
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.5998382415566258e-06,
+      "loss": 0.5773,
+      "step": 1212
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.5713893034485216e-06,
+      "loss": 0.5944,
+      "step": 1214
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.5430738927052346e-06,
+      "loss": 0.6249,
+      "step": 1216
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.514892518288988e-06,
+      "loss": 0.6379,
+      "step": 1218
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.4868456867527315e-06,
+      "loss": 0.5833,
+      "step": 1220
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.4589339022310386e-06,
+      "loss": 0.5841,
+      "step": 1222
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.431157666431052e-06,
+      "loss": 0.6359,
+      "step": 1224
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.403517478623456e-06,
+      "loss": 0.575,
+      "step": 1226
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.3760138356335172e-06,
+      "loss": 0.6207,
+      "step": 1228
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.348647231832131e-06,
+      "loss": 0.6009,
+      "step": 1230
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.3214181591269603e-06,
+      "loss": 0.6267,
+      "step": 1232
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.2943271069535754e-06,
+      "loss": 0.6262,
+      "step": 1234
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.267374562266662e-06,
+      "loss": 0.5881,
+      "step": 1236
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.240561009531281e-06,
+      "loss": 0.5842,
+      "step": 1238
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.2138869307141266e-06,
+      "loss": 0.5602,
+      "step": 1240
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.1873528052749094e-06,
+      "loss": 0.596,
+      "step": 1242
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.1609591101576945e-06,
+      "loss": 0.5942,
+      "step": 1244
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.1347063197823648e-06,
+      "loss": 0.5955,
+      "step": 1246
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.1085949060360654e-06,
+      "loss": 0.6148,
+      "step": 1248
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.0826253382647334e-06,
+      "loss": 0.6484,
+      "step": 1250
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.056798083264667e-06,
+      "loss": 0.5729,
+      "step": 1252
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.0311136052741274e-06,
+      "loss": 0.6088,
+      "step": 1254
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.0055723659649907e-06,
+      "loss": 0.6047,
+      "step": 1256
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.9801748244344587e-06,
+      "loss": 0.5812,
+      "step": 1258
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.9549214371968008e-06,
+      "loss": 0.5976,
+      "step": 1260
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.9298126581751542e-06,
+      "loss": 0.6362,
+      "step": 1262
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.9048489386933545e-06,
+      "loss": 0.5954,
+      "step": 1264
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.8800307274678364e-06,
+      "loss": 0.6468,
+      "step": 1266
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.8553584705995564e-06,
+      "loss": 0.6041,
+      "step": 1268
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.8308326115659757e-06,
+      "loss": 0.5584,
+      "step": 1270
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.8064535912131032e-06,
+      "loss": 0.6246,
+      "step": 1272
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.7822218477475496e-06,
+      "loss": 0.6056,
+      "step": 1274
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.7581378167286655e-06,
+      "loss": 0.6081,
+      "step": 1276
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.7342019310607062e-06,
+      "loss": 0.5951,
+      "step": 1278
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.7104146209850591e-06,
+      "loss": 0.5586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.6867763140724969e-06,
+      "loss": 0.6417,
+      "step": 1282
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.6632874352154982e-06,
+      "loss": 0.5777,
+      "step": 1284
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.6399484066206183e-06,
+      "loss": 0.5733,
+      "step": 1286
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.6167596478008817e-06,
+      "loss": 0.6019,
+      "step": 1288
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.5937215755682667e-06,
+      "loss": 0.6216,
+      "step": 1290
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.5708346040261812e-06,
+      "loss": 0.6211,
+      "step": 1292
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.5480991445620541e-06,
+      "loss": 0.6229,
+      "step": 1294
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.5255156058399124e-06,
+      "loss": 0.6139,
+      "step": 1296
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.5030843937930485e-06,
+      "loss": 0.6054,
+      "step": 1298
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.4808059116167306e-06,
+      "loss": 0.5948,
+      "step": 1300
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.4586805597609333e-06,
+      "loss": 0.5594,
+      "step": 1302
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.4367087359231668e-06,
+      "loss": 0.6174,
+      "step": 1304
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.4148908350413048e-06,
+      "loss": 0.5938,
+      "step": 1306
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.3932272492864984e-06,
+      "loss": 0.5763,
+      "step": 1308
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.3717183680561253e-06,
+      "loss": 0.5997,
+      "step": 1310
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.3503645779667852e-06,
+      "loss": 0.564,
+      "step": 1312
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.3291662628473634e-06,
+      "loss": 0.5961,
+      "step": 1314
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.308123803732111e-06,
+      "loss": 0.627,
+      "step": 1316
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.2872375788538171e-06,
+      "loss": 0.6356,
+      "step": 1318
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.266507963636997e-06,
+      "loss": 0.6069,
+      "step": 1320
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.2459353306911438e-06,
+      "loss": 0.6107,
+      "step": 1322
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.2255200498040432e-06,
+      "loss": 0.606,
+      "step": 1324
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.2052624879351105e-06,
+      "loss": 0.583,
+      "step": 1326
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1851630092088051e-06,
+      "loss": 0.5755,
+      "step": 1328
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.1652219749080817e-06,
+      "loss": 0.5951,
+      "step": 1330
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.1454397434679022e-06,
+      "loss": 0.5939,
+      "step": 1332
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.12581667046878e-06,
+      "loss": 0.6146,
+      "step": 1334
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.1063531086304003e-06,
+      "loss": 0.5748,
+      "step": 1336
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.0870494078052796e-06,
+      "loss": 0.5867,
+      "step": 1338
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.067905914972468e-06,
+      "loss": 0.5761,
+      "step": 1340
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.0489229742313223e-06,
+      "loss": 0.592,
+      "step": 1342
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.0301009267953145e-06,
+      "loss": 0.5793,
+      "step": 1344
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.0114401109859019e-06,
+      "loss": 0.6008,
+      "step": 1346
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.929408622264448e-07,
+      "loss": 0.5669,
+      "step": 1348
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.746035130361741e-07,
+      "loss": 0.5875,
+      "step": 1350
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.564283930242258e-07,
+      "loss": 0.6218,
+      "step": 1352
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 9.384158288836987e-07,
+      "loss": 0.5938,
+      "step": 1354
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 9.205661443857994e-07,
+      "loss": 0.5622,
+      "step": 1356
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 9.028796603740097e-07,
+      "loss": 0.6239,
+      "step": 1358
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.853566947583259e-07,
+      "loss": 0.5665,
+      "step": 1360
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 8.67997562509546e-07,
+      "loss": 0.6079,
+      "step": 1362
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 8.508025756535987e-07,
+      "loss": 0.5813,
+      "step": 1364
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 8.337720432659513e-07,
+      "loss": 0.6135,
+      "step": 1366
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 8.169062714660347e-07,
+      "loss": 0.5598,
+      "step": 1368
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 8.002055634117578e-07,
+      "loss": 0.5624,
+      "step": 1370
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.836702192940493e-07,
+      "loss": 0.6002,
+      "step": 1372
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.673005363314578e-07,
+      "loss": 0.5882,
+      "step": 1374
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.510968087648262e-07,
+      "loss": 0.6119,
+      "step": 1376
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.350593278519824e-07,
+      "loss": 0.5976,
+      "step": 1378
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.19188381862519e-07,
+      "loss": 0.5798,
+      "step": 1380
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.034842560726008e-07,
+      "loss": 0.5791,
+      "step": 1382
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 6.879472327598502e-07,
+      "loss": 0.5823,
+      "step": 1384
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.725775911982602e-07,
+      "loss": 0.5993,
+      "step": 1386
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.573756076531779e-07,
+      "loss": 0.5688,
+      "step": 1388
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.423415553763479e-07,
+      "loss": 0.5925,
+      "step": 1390
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.274757046009871e-07,
+      "loss": 0.6044,
+      "step": 1392
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 6.127783225369377e-07,
+      "loss": 0.6185,
+      "step": 1394
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.982496733658582e-07,
+      "loss": 0.5809,
+      "step": 1396
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.83890018236476e-07,
+      "loss": 0.5961,
+      "step": 1398
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.696996152598966e-07,
+      "loss": 0.6069,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.556787195049573e-07,
+      "loss": 0.5802,
+      "step": 1402
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.418275829936537e-07,
+      "loss": 0.6161,
+      "step": 1404
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.281464546965953e-07,
+      "loss": 0.5966,
+      "step": 1406
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 5.146355805285452e-07,
+      "loss": 0.6,
+      "step": 1408
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 5.012952033439844e-07,
+      "loss": 0.578,
+      "step": 1410
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.881255629327608e-07,
+      "loss": 0.5885,
+      "step": 1412
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.7512689601576843e-07,
+      "loss": 0.5753,
+      "step": 1414
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.6229943624069963e-07,
+      "loss": 0.6083,
+      "step": 1416
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.4964341417784165e-07,
+      "loss": 0.6019,
+      "step": 1418
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.3715905731593233e-07,
+      "loss": 0.6016,
+      "step": 1420
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.248465900580734e-07,
+      "loss": 0.5873,
+      "step": 1422
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 4.127062337176935e-07,
+      "loss": 0.5647,
+      "step": 1424
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 4.0073820651457043e-07,
+      "loss": 0.5816,
+      "step": 1426
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.889427235709153e-07,
+      "loss": 0.5444,
+      "step": 1428
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.773199969074959e-07,
+      "loss": 0.6032,
+      "step": 1430
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.658702354398325e-07,
+      "loss": 0.5779,
+      "step": 1432
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.5459364497443696e-07,
+      "loss": 0.5919,
+      "step": 1434
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.4349042820512325e-07,
+      "loss": 0.6086,
+      "step": 1436
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.325607847093537e-07,
+      "loss": 0.5862,
+      "step": 1438
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.2180491094465414e-07,
+      "loss": 0.6099,
+      "step": 1440
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.112230002450889e-07,
+      "loss": 0.5925,
+      "step": 1442
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.0081524281777687e-07,
+      "loss": 0.6217,
+      "step": 1444
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.905818257394799e-07,
+      "loss": 0.5707,
+      "step": 1446
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.805229329532344e-07,
+      "loss": 0.6038,
+      "step": 1448
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.706387452650494e-07,
+      "loss": 0.5877,
+      "step": 1450
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.609294403406537e-07,
+      "loss": 0.5912,
+      "step": 1452
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.513951927023017e-07,
+      "loss": 0.6043,
+      "step": 1454
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.420361737256438e-07,
+      "loss": 0.5947,
+      "step": 1456
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.3285255163663535e-07,
+      "loss": 0.5927,
+      "step": 1458
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.2384449150851695e-07,
+      "loss": 0.6107,
+      "step": 1460
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.1501215525885245e-07,
+      "loss": 0.5427,
+      "step": 1462
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.063557016466111e-07,
+      "loss": 0.5792,
+      "step": 1464
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.978752862693212e-07,
+      "loss": 0.5775,
+      "step": 1466
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8957106156026084e-07,
+      "loss": 0.5554,
+      "step": 1468
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8144317678573497e-07,
+      "loss": 0.5464,
+      "step": 1470
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.7349177804237837e-07,
+      "loss": 0.5882,
+      "step": 1472
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.6571700825453674e-07,
+      "loss": 0.5718,
+      "step": 1474
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.5811900717169537e-07,
+      "loss": 0.5631,
+      "step": 1476
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.506979113659679e-07,
+      "loss": 0.6137,
+      "step": 1478
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.4345385422964043e-07,
+      "loss": 0.5804,
+      "step": 1480
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.3638696597277678e-07,
+      "loss": 0.5713,
+      "step": 1482
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.2949737362087156e-07,
+      "loss": 0.5563,
+      "step": 1484
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.227852010125752e-07,
+      "loss": 0.5885,
+      "step": 1486
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.1625056879746133e-07,
+      "loss": 0.5563,
+      "step": 1488
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.0989359443386305e-07,
+      "loss": 0.5924,
+      "step": 1490
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.0371439218675671e-07,
+      "loss": 0.613,
+      "step": 1492
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.771307312571254e-08,
+      "loss": 0.5946,
+      "step": 1494
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.188974512289617e-08,
+      "loss": 0.5728,
+      "step": 1496
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.624451285112689e-08,
+      "loss": 0.5644,
+      "step": 1498
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.077747778200474e-08,
+      "loss": 0.6211,
+      "step": 1500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 7.54887381840752e-08,
+      "loss": 0.5863,
+      "step": 1502
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 7.037838912107298e-08,
+      "loss": 0.6035,
+      "step": 1504
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.544652245020433e-08,
+      "loss": 0.6091,
+      "step": 1506
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.069322682050516e-08,
+      "loss": 0.5979,
+      "step": 1508
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.611858767124001e-08,
+      "loss": 0.6134,
+      "step": 1510
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.1722687230369995e-08,
+      "loss": 0.5743,
+      "step": 1512
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 4.7505604513072845e-08,
+      "loss": 0.5767,
+      "step": 1514
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 4.346741532032628e-08,
+      "loss": 0.5905,
+      "step": 1516
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.96081922375402e-08,
+      "loss": 0.576,
+      "step": 1518
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.592800463325663e-08,
+      "loss": 0.5968,
+      "step": 1520
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.242691865790071e-08,
+      "loss": 0.5451,
+      "step": 1522
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.9104997242590528e-08,
+      "loss": 0.5999,
+      "step": 1524
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.5962300098008042e-08,
+      "loss": 0.5615,
+      "step": 1526
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.2998883713326592e-08,
+      "loss": 0.5677,
+      "step": 1528
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.0214801355192826e-08,
+      "loss": 0.6002,
+      "step": 1530
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.761010306676969e-08,
+      "loss": 0.6138,
+      "step": 1532
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.518483566683826e-08,
+      "loss": 0.6095,
+      "step": 1534
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.2939042748955078e-08,
+      "loss": 0.5596,
+      "step": 1536
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.0872764680671666e-08,
+      "loss": 0.6428,
+      "step": 1538
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 8.986038602802894e-09,
+      "loss": 0.5899,
+      "step": 1540
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 7.278898428764169e-09,
+      "loss": 0.5952,
+      "step": 1542
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.751374843961932e-09,
+      "loss": 0.5526,
+      "step": 1544
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.403495305237426e-09,
+      "loss": 0.5829,
+      "step": 1546
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.2352840403804264e-09,
+      "loss": 0.5848,
+      "step": 1548
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.246762047685147e-09,
+      "loss": 0.5983,
+      "step": 1550
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.437947095582759e-09,
+      "loss": 0.5923,
+      "step": 1552
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 8.088537223116533e-10,
+      "loss": 0.5919,
+      "step": 1554
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 3.594932356654202e-10,
+      "loss": 0.6125,
+      "step": 1556
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.987371278079693e-11,
+      "loss": 0.5734,
+      "step": 1558
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.6057,
+      "step": 1560
+    },
+    {
+      "epoch": 2.0,
+      "step": 1560,
+      "total_flos": 3.6540609644891996e+18,
+      "train_loss": 0.8723082382709552,
+      "train_runtime": 12247.4613,
+      "train_samples_per_second": 8.152,
+      "train_steps_per_second": 0.127
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 780,
+  "total_flos": 3.6540609644891996e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:715a837f4547b5e7a9b74269084fc80bc1b009817e06a0124616fdfbc78a4bf3
+size 5103