just a copy from Alpaca-Mar21 for upload

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "../llama-7b-hf",
+  "architectures": [
+    "LLaMAForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561107a4e6f55d8d45eb47d08b28b65163fe091b27a1f32d95e3759b11f55f64
+size 9878004434

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea857f0a9d72ed274b2b6b39f0ac89e2d44758ac1f8f0719a722c4b896fdcf09
+size 9894799542

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd2a8550323b8672b5936792686353d5d822f46806e3170ef2198c0c32d81ff
+size 7181006073

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953699328
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 512,
+  "padding_side": "right",
+  "special_tokens_map_file": "../llama-7b-hf/special_tokens_map.json",
+  "tokenizer_class": "LLaMATokenizer",
+  "unk_token": ""
+}

trainer_state.json

@@ -0,0 +1,4237 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9984,
+  "global_step": 702,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.9416,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.9482,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.7529,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.7071,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.7033,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.6641,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.6292,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.6257,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.5905,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.6379,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 0.5972,
+      "step": 11
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.6028,
+      "step": 12
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.181818181818182e-05,
+      "loss": 0.5902,
+      "step": 13
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 0.6073,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 0.5989,
+      "step": 15
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.5838,
+      "step": 16
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5454545454545454e-05,
+      "loss": 0.5778,
+      "step": 17
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.6007,
+      "step": 18
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7272727272727274e-05,
+      "loss": 0.5941,
+      "step": 19
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.6026,
+      "step": 20
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9090909090909094e-05,
+      "loss": 0.5882,
+      "step": 21
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 0.5822,
+      "step": 22
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999989327868895e-05,
+      "loss": 0.5918,
+      "step": 23
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999957311703368e-05,
+      "loss": 0.6018,
+      "step": 24
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999903952186781e-05,
+      "loss": 0.5785,
+      "step": 25
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998292504580528e-05,
+      "loss": 0.5757,
+      "step": 26
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9997332081116374e-05,
+      "loss": 0.5742,
+      "step": 27
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9996158271974875e-05,
+      "loss": 0.597,
+      "step": 28
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9994771102210122e-05,
+      "loss": 0.5785,
+      "step": 29
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9993170601430233e-05,
+      "loss": 0.5649,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999135680379671e-05,
+      "loss": 0.5869,
+      "step": 31
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9989329748023728e-05,
+      "loss": 0.5552,
+      "step": 32
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9987089477377293e-05,
+      "loss": 0.5808,
+      "step": 33
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9984636039674342e-05,
+      "loss": 0.6061,
+      "step": 34
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9981969487281678e-05,
+      "loss": 0.5559,
+      "step": 35
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9979089877114905e-05,
+      "loss": 0.5876,
+      "step": 36
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9975997270637172e-05,
+      "loss": 0.5647,
+      "step": 37
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.997269173385788e-05,
+      "loss": 0.5751,
+      "step": 38
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9969173337331283e-05,
+      "loss": 0.5307,
+      "step": 39
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9965442156154947e-05,
+      "loss": 0.5695,
+      "step": 40
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9961498269968187e-05,
+      "loss": 0.5663,
+      "step": 41
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9957341762950346e-05,
+      "loss": 0.5816,
+      "step": 42
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9952972723819e-05,
+      "loss": 0.5434,
+      "step": 43
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.994839124582806e-05,
+      "loss": 0.5448,
+      "step": 44
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9943597426765792e-05,
+      "loss": 0.5671,
+      "step": 45
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.993859136895274e-05,
+      "loss": 0.5817,
+      "step": 46
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.99333731792395e-05,
+      "loss": 0.5839,
+      "step": 47
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9927942969004493e-05,
+      "loss": 0.5718,
+      "step": 48
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.992230085415154e-05,
+      "loss": 0.5695,
+      "step": 49
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.991644695510743e-05,
+      "loss": 0.5453,
+      "step": 50
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9910381396819313e-05,
+      "loss": 0.5722,
+      "step": 51
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9904104308752053e-05,
+      "loss": 0.5952,
+      "step": 52
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.989761582488547e-05,
+      "loss": 0.5541,
+      "step": 53
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9890916083711463e-05,
+      "loss": 0.5696,
+      "step": 54
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.988400522823106e-05,
+      "loss": 0.5503,
+      "step": 55
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.5573,
+      "step": 56
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.986955076888246e-05,
+      "loss": 0.5636,
+      "step": 57
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9862007473534026e-05,
+      "loss": 0.5733,
+      "step": 58
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.985425368091216e-05,
+      "loss": 0.551,
+      "step": 59
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9846289556515835e-05,
+      "loss": 0.5555,
+      "step": 60
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.983811527033342e-05,
+      "loss": 0.5679,
+      "step": 61
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 0.5536,
+      "step": 62
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.982113691498876e-05,
+      "loss": 0.5224,
+      "step": 63
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.981233320821699e-05,
+      "loss": 0.5626,
+      "step": 64
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9803320064432318e-05,
+      "loss": 0.5411,
+      "step": 65
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.979409767601366e-05,
+      "loss": 0.571,
+      "step": 66
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.978466623980609e-05,
+      "loss": 0.5644,
+      "step": 67
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9775025957116657e-05,
+      "loss": 0.5574,
+      "step": 68
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.976517703371008e-05,
+      "loss": 0.5805,
+      "step": 69
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.975511967980437e-05,
+      "loss": 0.5731,
+      "step": 70
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9744854110066313e-05,
+      "loss": 0.5608,
+      "step": 71
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9734380543606932e-05,
+      "loss": 0.5722,
+      "step": 72
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9723699203976768e-05,
+      "loss": 0.5614,
+      "step": 73
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.971281031916114e-05,
+      "loss": 0.555,
+      "step": 74
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.970171412157526e-05,
+      "loss": 0.5342,
+      "step": 75
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9690410848059278e-05,
+      "loss": 0.5622,
+      "step": 76
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.967890073987323e-05,
+      "loss": 0.5656,
+      "step": 77
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9667184042691877e-05,
+      "loss": 0.5773,
+      "step": 78
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9655261006599482e-05,
+      "loss": 0.5609,
+      "step": 79
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.964313188608445e-05,
+      "loss": 0.5235,
+      "step": 80
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9630796940033913e-05,
+      "loss": 0.5379,
+      "step": 81
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.961825643172819e-05,
+      "loss": 0.5545,
+      "step": 82
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9605510628835184e-05,
+      "loss": 0.5572,
+      "step": 83
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9592559803404652e-05,
+      "loss": 0.5723,
+      "step": 84
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9579404231862403e-05,
+      "loss": 0.5617,
+      "step": 85
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.956604419500441e-05,
+      "loss": 0.5522,
+      "step": 86
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9552479977990802e-05,
+      "loss": 0.549,
+      "step": 87
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.953871187033978e-05,
+      "loss": 0.5504,
+      "step": 88
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9524740165921454e-05,
+      "loss": 0.535,
+      "step": 89
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.5456,
+      "step": 90
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9496187163985012e-05,
+      "loss": 0.5638,
+      "step": 91
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.948160647590966e-05,
+      "loss": 0.5411,
+      "step": 92
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.946682340993951e-05,
+      "loss": 0.5658,
+      "step": 93
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.94518382816082e-05,
+      "loss": 0.5675,
+      "step": 94
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.943665141076223e-05,
+      "loss": 0.5581,
+      "step": 95
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9421263121554163e-05,
+      "loss": 0.5541,
+      "step": 96
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9405673742435677e-05,
+      "loss": 0.5561,
+      "step": 97
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.938988360615057e-05,
+      "loss": 0.548,
+      "step": 98
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9373893049727643e-05,
+      "loss": 0.5971,
+      "step": 99
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9357702414473528e-05,
+      "loss": 0.5381,
+      "step": 100
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.934131204596539e-05,
+      "loss": 0.5466,
+      "step": 101
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 0.5573,
+      "step": 102
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.930793351280404e-05,
+      "loss": 0.5586,
+      "step": 103
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9290946060590992e-05,
+      "loss": 0.5656,
+      "step": 104
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9273760299989036e-05,
+      "loss": 0.5665,
+      "step": 105
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9256376597815565e-05,
+      "loss": 0.5537,
+      "step": 106
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 0.5554,
+      "step": 107
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9221016857140244e-05,
+      "loss": 0.5619,
+      "step": 108
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9203041573365978e-05,
+      "loss": 0.5511,
+      "step": 109
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9184869857459233e-05,
+      "loss": 0.5736,
+      "step": 110
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9166502097281882e-05,
+      "loss": 0.5298,
+      "step": 111
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9147938684880213e-05,
+      "loss": 0.5641,
+      "step": 112
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9129180016476568e-05,
+      "loss": 0.5501,
+      "step": 113
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9110226492460886e-05,
+      "loss": 0.5447,
+      "step": 114
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.909107851738215e-05,
+      "loss": 0.5543,
+      "step": 115
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9071736499939765e-05,
+      "loss": 0.557,
+      "step": 116
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.905220085297482e-05,
+      "loss": 0.5593,
+      "step": 117
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.903247199346129e-05,
+      "loss": 0.5433,
+      "step": 118
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.901255034249712e-05,
+      "loss": 0.5823,
+      "step": 119
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8992436325295258e-05,
+      "loss": 0.5636,
+      "step": 120
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8972130371174557e-05,
+      "loss": 0.5546,
+      "step": 121
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8951632913550625e-05,
+      "loss": 0.5701,
+      "step": 122
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8930944389926575e-05,
+      "loss": 0.529,
+      "step": 123
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.5446,
+      "step": 124
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.888899591507195e-05,
+      "loss": 0.5565,
+      "step": 125
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.886773685920062e-05,
+      "loss": 0.5722,
+      "step": 126
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8846288528028555e-05,
+      "loss": 0.5392,
+      "step": 127
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.882465137935456e-05,
+      "loss": 0.5447,
+      "step": 128
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8802825875007604e-05,
+      "loss": 0.521,
+      "step": 129
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.878081248083698e-05,
+      "loss": 0.5412,
+      "step": 130
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8758611666702347e-05,
+      "loss": 0.5437,
+      "step": 131
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8736223906463698e-05,
+      "loss": 0.5677,
+      "step": 132
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.871364967797126e-05,
+      "loss": 0.5413,
+      "step": 133
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8690889463055285e-05,
+      "loss": 0.5573,
+      "step": 134
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.866794374751577e-05,
+      "loss": 0.5483,
+      "step": 135
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.864481302111208e-05,
+      "loss": 0.555,
+      "step": 136
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8621497777552508e-05,
+      "loss": 0.5243,
+      "step": 137
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8597998514483724e-05,
+      "loss": 0.5513,
+      "step": 138
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8574315733480165e-05,
+      "loss": 0.56,
+      "step": 139
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.855044994003331e-05,
+      "loss": 0.5493,
+      "step": 140
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8526401643540924e-05,
+      "loss": 0.5401,
+      "step": 141
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 0.5413,
+      "step": 142
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8477759598476556e-05,
+      "loss": 0.5539,
+      "step": 143
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.845316688813314e-05,
+      "loss": 0.5612,
+      "step": 144
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8428393751179154e-05,
+      "loss": 0.5327,
+      "step": 145
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.840344071637893e-05,
+      "loss": 0.53,
+      "step": 146
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8378308316336585e-05,
+      "loss": 0.551,
+      "step": 147
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8352997087484657e-05,
+      "loss": 0.5491,
+      "step": 148
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8327507570072648e-05,
+      "loss": 0.5721,
+      "step": 149
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8301840308155507e-05,
+      "loss": 0.5472,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8275995849582e-05,
+      "loss": 0.547,
+      "step": 151
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8249974745983023e-05,
+      "loss": 0.5658,
+      "step": 152
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.822377755275984e-05,
+      "loss": 0.5378,
+      "step": 153
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8197404829072214e-05,
+      "loss": 0.5139,
+      "step": 154
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8170857137826465e-05,
+      "loss": 0.5315,
+      "step": 155
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8144135045663486e-05,
+      "loss": 0.5363,
+      "step": 156
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8117239122946615e-05,
+      "loss": 0.5678,
+      "step": 157
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.533,
+      "step": 158
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8062928085843732e-05,
+      "loss": 0.5161,
+      "step": 159
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8035514130686737e-05,
+      "loss": 0.5386,
+      "step": 160
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8007928663409148e-05,
+      "loss": 0.5504,
+      "step": 161
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7980172272802398e-05,
+      "loss": 0.5643,
+      "step": 162
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7952245551306173e-05,
+      "loss": 0.5495,
+      "step": 163
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.792414909499574e-05,
+      "loss": 0.5485,
+      "step": 164
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7895883503569228e-05,
+      "loss": 0.5442,
+      "step": 165
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7867449380334834e-05,
+      "loss": 0.5239,
+      "step": 166
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.783884733219794e-05,
+      "loss": 0.5673,
+      "step": 167
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7810077969648157e-05,
+      "loss": 0.5431,
+      "step": 168
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7781141906746304e-05,
+      "loss": 0.5535,
+      "step": 169
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.77520397611113e-05,
+      "loss": 0.5522,
+      "step": 170
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.772277215390697e-05,
+      "loss": 0.5336,
+      "step": 171
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.769333970982879e-05,
+      "loss": 0.5594,
+      "step": 172
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7663743057090572e-05,
+      "loss": 0.5441,
+      "step": 173
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.763398282741103e-05,
+      "loss": 0.5468,
+      "step": 174
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7604059656000313e-05,
+      "loss": 0.5624,
+      "step": 175
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.757397418154643e-05,
+      "loss": 0.5574,
+      "step": 176
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7543727046201642e-05,
+      "loss": 0.5288,
+      "step": 177
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7513318895568734e-05,
+      "loss": 0.5243,
+      "step": 178
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.748275037868725e-05,
+      "loss": 0.5303,
+      "step": 179
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7452022148019626e-05,
+      "loss": 0.5379,
+      "step": 180
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.742113485943728e-05,
+      "loss": 0.5549,
+      "step": 181
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 0.5797,
+      "step": 182
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7358885748974853e-05,
+      "loss": 0.5449,
+      "step": 183
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7327525255756118e-05,
+      "loss": 0.5135,
+      "step": 184
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.729600836191696e-05,
+      "loss": 0.5091,
+      "step": 185
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7264335740162244e-05,
+      "loss": 0.5595,
+      "step": 186
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7232508066520702e-05,
+      "loss": 0.5471,
+      "step": 187
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.720052602033055e-05,
+      "loss": 0.5352,
+      "step": 188
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7168390284224964e-05,
+      "loss": 0.5773,
+      "step": 189
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7136101544117526e-05,
+      "loss": 0.549,
+      "step": 190
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.710366048918757e-05,
+      "loss": 0.5475,
+      "step": 191
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.5415,
+      "step": 192
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7038324207817902e-05,
+      "loss": 0.576,
+      "step": 193
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.700543037593291e-05,
+      "loss": 0.5513,
+      "step": 194
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.697238701830508e-05,
+      "loss": 0.5276,
+      "step": 195
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6939194840220497e-05,
+      "loss": 0.5532,
+      "step": 196
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6905854550141717e-05,
+      "loss": 0.5214,
+      "step": 197
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.687236685969263e-05,
+      "loss": 0.5288,
+      "step": 198
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.683873248364328e-05,
+      "loss": 0.5464,
+      "step": 199
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6804952139894618e-05,
+      "loss": 0.5326,
+      "step": 200
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6771026549463148e-05,
+      "loss": 0.5424,
+      "step": 201
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6736956436465573e-05,
+      "loss": 0.5409,
+      "step": 202
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6702742528103318e-05,
+      "loss": 0.5317,
+      "step": 203
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6668385554647017e-05,
+      "loss": 0.5474,
+      "step": 204
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6633886249420915e-05,
+      "loss": 0.5521,
+      "step": 205
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.659924534878723e-05,
+      "loss": 0.5564,
+      "step": 206
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.656446359213043e-05,
+      "loss": 0.5636,
+      "step": 207
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6529541721841444e-05,
+      "loss": 0.5271,
+      "step": 208
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6494480483301836e-05,
+      "loss": 0.5573,
+      "step": 209
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6459280624867876e-05,
+      "loss": 0.5698,
+      "step": 210
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.642394289785456e-05,
+      "loss": 0.5302,
+      "step": 211
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.638846805651961e-05,
+      "loss": 0.5482,
+      "step": 212
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6352856858047347e-05,
+      "loss": 0.5426,
+      "step": 213
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.631711006253251e-05,
+      "loss": 0.5608,
+      "step": 214
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6281228432964092e-05,
+      "loss": 0.5331,
+      "step": 215
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6245212735208994e-05,
+      "loss": 0.5287,
+      "step": 216
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6209063737995716e-05,
+      "loss": 0.5517,
+      "step": 217
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.617278221289793e-05,
+      "loss": 0.5694,
+      "step": 218
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6136368934318028e-05,
+      "loss": 0.5162,
+      "step": 219
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.609982467947057e-05,
+      "loss": 0.5519,
+      "step": 220
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6063150228365712e-05,
+      "loss": 0.5254,
+      "step": 221
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6026346363792565e-05,
+      "loss": 0.5543,
+      "step": 222
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5989413871302456e-05,
+      "loss": 0.5382,
+      "step": 223
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.595235353919219e-05,
+      "loss": 0.5457,
+      "step": 224
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5915166158487213e-05,
+      "loss": 0.5254,
+      "step": 225
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.5418,
+      "step": 226
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5840413428936767e-05,
+      "loss": 0.506,
+      "step": 227
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.580284967563316e-05,
+      "loss": 0.5303,
+      "step": 228
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5765162064784504e-05,
+      "loss": 0.5404,
+      "step": 229
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5727351400805054e-05,
+      "loss": 0.5365,
+      "step": 230
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5689418490735533e-05,
+      "loss": 0.5582,
+      "step": 231
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.565136414422592e-05,
+      "loss": 0.5701,
+      "step": 232
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5613189173518167e-05,
+      "loss": 0.5161,
+      "step": 233
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5574894393428856e-05,
+      "loss": 0.5359,
+      "step": 234
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5536480621331818e-05,
+      "loss": 0.5894,
+      "step": 235
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5497948677140673e-05,
+      "loss": 0.3695,
+      "step": 236
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5459299383291347e-05,
+      "loss": 0.3926,
+      "step": 237
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5420533564724495e-05,
+      "loss": 0.3781,
+      "step": 238
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.538165204886792e-05,
+      "loss": 0.3832,
+      "step": 239
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5342655665618885e-05,
+      "loss": 0.3738,
+      "step": 240
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5303545247326424e-05,
+      "loss": 0.3741,
+      "step": 241
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.526432162877356e-05,
+      "loss": 0.3788,
+      "step": 242
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5224985647159489e-05,
+      "loss": 0.3581,
+      "step": 243
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5185538142081721e-05,
+      "loss": 0.3723,
+      "step": 244
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5145979955518147e-05,
+      "loss": 0.3735,
+      "step": 245
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.510631193180907e-05,
+      "loss": 0.3565,
+      "step": 246
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5066534917639195e-05,
+      "loss": 0.3862,
+      "step": 247
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5026649762019539e-05,
+      "loss": 0.3674,
+      "step": 248
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.498665731626932e-05,
+      "loss": 0.3613,
+      "step": 249
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4946558433997792e-05,
+      "loss": 0.3823,
+      "step": 250
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4906353971086004e-05,
+      "loss": 0.3576,
+      "step": 251
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4866044785668563e-05,
+      "loss": 0.3627,
+      "step": 252
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4825631738115289e-05,
+      "loss": 0.3564,
+      "step": 253
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4785115691012866e-05,
+      "loss": 0.3501,
+      "step": 254
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4744497509146427e-05,
+      "loss": 0.3718,
+      "step": 255
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4703778059481096e-05,
+      "loss": 0.3506,
+      "step": 256
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.466295821114348e-05,
+      "loss": 0.3617,
+      "step": 257
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4622038835403135e-05,
+      "loss": 0.3395,
+      "step": 258
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4581020805653934e-05,
+      "loss": 0.3638,
+      "step": 259
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.3685,
+      "step": 260
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.449869228821433e-05,
+      "loss": 0.3566,
+      "step": 261
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 0.3614,
+      "step": 262
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.441597968775301e-05,
+      "loss": 0.3516,
+      "step": 263
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4374481561912266e-05,
+      "loss": 0.356,
+      "step": 264
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4332890065990027e-05,
+      "loss": 0.3582,
+      "step": 265
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.429120608772609e-05,
+      "loss": 0.3485,
+      "step": 266
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4249430516834222e-05,
+      "loss": 0.3578,
+      "step": 267
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4207564244983154e-05,
+      "loss": 0.3367,
+      "step": 268
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4165608165777574e-05,
+      "loss": 0.3614,
+      "step": 269
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4123563174739036e-05,
+      "loss": 0.3734,
+      "step": 270
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4081430169286859e-05,
+      "loss": 0.3608,
+      "step": 271
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.403921004871895e-05,
+      "loss": 0.3453,
+      "step": 272
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3996903714192643e-05,
+      "loss": 0.3493,
+      "step": 273
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3954512068705425e-05,
+      "loss": 0.3603,
+      "step": 274
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3912036017075703e-05,
+      "loss": 0.3483,
+      "step": 275
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.3869476465923455e-05,
+      "loss": 0.3334,
+      "step": 276
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.3466,
+      "step": 277
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3784110500423104e-05,
+      "loss": 0.3654,
+      "step": 278
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3741305908148555e-05,
+      "loss": 0.3377,
+      "step": 279
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3698421460459692e-05,
+      "loss": 0.3522,
+      "step": 280
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3655458072693413e-05,
+      "loss": 0.3414,
+      "step": 281
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3612416661871532e-05,
+      "loss": 0.3751,
+      "step": 282
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3569298146681202e-05,
+      "loss": 0.3613,
+      "step": 283
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3526103447455326e-05,
+      "loss": 0.3503,
+      "step": 284
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3482833486152886e-05,
+      "loss": 0.3773,
+      "step": 285
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3439489186339283e-05,
+      "loss": 0.36,
+      "step": 286
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3396071473166614e-05,
+      "loss": 0.3439,
+      "step": 287
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.335258127335394e-05,
+      "loss": 0.3173,
+      "step": 288
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3309019515167481e-05,
+      "loss": 0.3654,
+      "step": 289
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3265387128400833e-05,
+      "loss": 0.3665,
+      "step": 290
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3221685044355099e-05,
+      "loss": 0.3677,
+      "step": 291
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3177914195819018e-05,
+      "loss": 0.3529,
+      "step": 292
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3134075517049059e-05,
+      "loss": 0.3478,
+      "step": 293
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.3426,
+      "step": 294
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3046198413052337e-05,
+      "loss": 0.3622,
+      "step": 295
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3002161863497529e-05,
+      "loss": 0.3359,
+      "step": 296
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.2958061235012707e-05,
+      "loss": 0.3486,
+      "step": 297
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.2913897468893249e-05,
+      "loss": 0.3775,
+      "step": 298
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.286967150778216e-05,
+      "loss": 0.3654,
+      "step": 299
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2825384295649952e-05,
+      "loss": 0.3525,
+      "step": 300
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2781036777774492e-05,
+      "loss": 0.3499,
+      "step": 301
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2736629900720832e-05,
+      "loss": 0.334,
+      "step": 302
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2692164612320997e-05,
+      "loss": 0.3556,
+      "step": 303
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2647641861653759e-05,
+      "loss": 0.3568,
+      "step": 304
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.260306259902439e-05,
+      "loss": 0.3623,
+      "step": 305
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2558427775944357e-05,
+      "loss": 0.3686,
+      "step": 306
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2513738345111029e-05,
+      "loss": 0.3556,
+      "step": 307
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2468995260387332e-05,
+      "loss": 0.3657,
+      "step": 308
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2424199476781403e-05,
+      "loss": 0.3584,
+      "step": 309
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2379351950426188e-05,
+      "loss": 0.3501,
+      "step": 310
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2334453638559057e-05,
+      "loss": 0.3391,
+      "step": 311
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2289505499501341e-05,
+      "loss": 0.3726,
+      "step": 312
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2244508492637914e-05,
+      "loss": 0.3576,
+      "step": 313
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2199463578396688e-05,
+      "loss": 0.3652,
+      "step": 314
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2154371718228119e-05,
+      "loss": 0.3507,
+      "step": 315
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.21092338745847e-05,
+      "loss": 0.35,
+      "step": 316
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2064051010900397e-05,
+      "loss": 0.3726,
+      "step": 317
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2018824091570103e-05,
+      "loss": 0.3502,
+      "step": 318
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1973554081929042e-05,
+      "loss": 0.3557,
+      "step": 319
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.192824194823217e-05,
+      "loss": 0.3573,
+      "step": 320
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.188288865763355e-05,
+      "loss": 0.3452,
+      "step": 321
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1837495178165706e-05,
+      "loss": 0.357,
+      "step": 322
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.179206247871897e-05,
+      "loss": 0.3538,
+      "step": 323
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1746591529020789e-05,
+      "loss": 0.3784,
+      "step": 324
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.170108329961504e-05,
+      "loss": 0.3513,
+      "step": 325
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.16555387618413e-05,
+      "loss": 0.3761,
+      "step": 326
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.160995888781413e-05,
+      "loss": 0.3459,
+      "step": 327
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.3389,
+      "step": 328
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1518697023208085e-05,
+      "loss": 0.3505,
+      "step": 329
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1473016980546377e-05,
+      "loss": 0.3503,
+      "step": 330
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1427305497423995e-05,
+      "loss": 0.3374,
+      "step": 331
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1381563549518823e-05,
+      "loss": 0.3464,
+      "step": 332
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.133579211315899e-05,
+      "loss": 0.3542,
+      "step": 333
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1289992165302036e-05,
+      "loss": 0.332,
+      "step": 334
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1244164683514055e-05,
+      "loss": 0.3637,
+      "step": 335
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1198310645948833e-05,
+      "loss": 0.3593,
+      "step": 336
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1152431031326978e-05,
+      "loss": 0.3543,
+      "step": 337
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1106526818915008e-05,
+      "loss": 0.3507,
+      "step": 338
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1060598988504476e-05,
+      "loss": 0.356,
+      "step": 339
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1014648520391031e-05,
+      "loss": 0.3703,
+      "step": 340
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0968676395353514e-05,
+      "loss": 0.3566,
+      "step": 341
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 0.3576,
+      "step": 342
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0876671099911947e-05,
+      "loss": 0.3283,
+      "step": 343
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.083063989329304e-05,
+      "loss": 0.3381,
+      "step": 344
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0784590957278452e-05,
+      "loss": 0.3484,
+      "step": 345
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.073852527474874e-05,
+      "loss": 0.3626,
+      "step": 346
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0692443828941918e-05,
+      "loss": 0.3448,
+      "step": 347
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0646347603432443e-05,
+      "loss": 0.3493,
+      "step": 348
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0600237582110244e-05,
+      "loss": 0.3412,
+      "step": 349
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.05541147491597e-05,
+      "loss": 0.3635,
+      "step": 350
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0507980089038659e-05,
+      "loss": 0.37,
+      "step": 351
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0461834586457398e-05,
+      "loss": 0.3623,
+      "step": 352
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0415679226357627e-05,
+      "loss": 0.3632,
+      "step": 353
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0369514993891451e-05,
+      "loss": 0.3418,
+      "step": 354
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0323342874400358e-05,
+      "loss": 0.3623,
+      "step": 355
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0277163853394166e-05,
+      "loss": 0.332,
+      "step": 356
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0230978916530012e-05,
+      "loss": 0.3551,
+      "step": 357
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.01847890495913e-05,
+      "loss": 0.3285,
+      "step": 358
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0138595238466659e-05,
+      "loss": 0.3577,
+      "step": 359
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.009239846912891e-05,
+      "loss": 0.36,
+      "step": 360
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0046199727614005e-05,
+      "loss": 0.3526,
+      "step": 361
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1e-05,
+      "loss": 0.3417,
+      "step": 362
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.953800272385997e-06,
+      "loss": 0.3405,
+      "step": 363
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.907601530871094e-06,
+      "loss": 0.3688,
+      "step": 364
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.861404761533343e-06,
+      "loss": 0.3488,
+      "step": 365
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.815210950408703e-06,
+      "loss": 0.3659,
+      "step": 366
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.769021083469991e-06,
+      "loss": 0.3509,
+      "step": 367
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.722836146605838e-06,
+      "loss": 0.3582,
+      "step": 368
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.676657125599649e-06,
+      "loss": 0.3291,
+      "step": 369
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.630485006108554e-06,
+      "loss": 0.3261,
+      "step": 370
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.58432077364238e-06,
+      "loss": 0.3595,
+      "step": 371
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.538165413542607e-06,
+      "loss": 0.3546,
+      "step": 372
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.492019910961345e-06,
+      "loss": 0.3386,
+      "step": 373
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.445885250840301e-06,
+      "loss": 0.3614,
+      "step": 374
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.39976241788976e-06,
+      "loss": 0.3525,
+      "step": 375
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.353652396567558e-06,
+      "loss": 0.3525,
+      "step": 376
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.307556171058085e-06,
+      "loss": 0.3438,
+      "step": 377
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.261474725251261e-06,
+      "loss": 0.3384,
+      "step": 378
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.215409042721553e-06,
+      "loss": 0.337,
+      "step": 379
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.169360106706962e-06,
+      "loss": 0.3443,
+      "step": 380
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.123328900088058e-06,
+      "loss": 0.3628,
+      "step": 381
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.07731640536698e-06,
+      "loss": 0.3276,
+      "step": 382
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.031323604646488e-06,
+      "loss": 0.3691,
+      "step": 383
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.985351479608972e-06,
+      "loss": 0.3485,
+      "step": 384
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.939401011495527e-06,
+      "loss": 0.3739,
+      "step": 385
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.893473181084993e-06,
+      "loss": 0.339,
+      "step": 386
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.847568968673025e-06,
+      "loss": 0.3763,
+      "step": 387
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.80168935405117e-06,
+      "loss": 0.3365,
+      "step": 388
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.75583531648595e-06,
+      "loss": 0.3568,
+      "step": 389
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.71000783469797e-06,
+      "loss": 0.3614,
+      "step": 390
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.664207886841014e-06,
+      "loss": 0.3539,
+      "step": 391
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.618436450481182e-06,
+      "loss": 0.3189,
+      "step": 392
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.572694502576009e-06,
+      "loss": 0.3642,
+      "step": 393
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.526983019453624e-06,
+      "loss": 0.3292,
+      "step": 394
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.481302976791917e-06,
+      "loss": 0.3552,
+      "step": 395
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.354,
+      "step": 396
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.39004111218587e-06,
+      "loss": 0.3485,
+      "step": 397
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.3444612381587e-06,
+      "loss": 0.3481,
+      "step": 398
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.29891670038496e-06,
+      "loss": 0.3537,
+      "step": 399
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.253408470979212e-06,
+      "loss": 0.367,
+      "step": 400
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.207937521281033e-06,
+      "loss": 0.3631,
+      "step": 401
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.162504821834296e-06,
+      "loss": 0.3509,
+      "step": 402
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.117111342366454e-06,
+      "loss": 0.3435,
+      "step": 403
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.071758051767833e-06,
+      "loss": 0.3386,
+      "step": 404
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.026445918070963e-06,
+      "loss": 0.3549,
+      "step": 405
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.9811759084299e-06,
+      "loss": 0.3458,
+      "step": 406
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.935948989099606e-06,
+      "loss": 0.3439,
+      "step": 407
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.890766125415304e-06,
+      "loss": 0.3684,
+      "step": 408
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.845628281771884e-06,
+      "loss": 0.3487,
+      "step": 409
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.800536421603317e-06,
+      "loss": 0.3532,
+      "step": 410
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.755491507362089e-06,
+      "loss": 0.3537,
+      "step": 411
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.710494500498662e-06,
+      "loss": 0.3464,
+      "step": 412
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.66554636144095e-06,
+      "loss": 0.3602,
+      "step": 413
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.620648049573815e-06,
+      "loss": 0.3486,
+      "step": 414
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.575800523218603e-06,
+      "loss": 0.3649,
+      "step": 415
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.531004739612668e-06,
+      "loss": 0.3409,
+      "step": 416
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.486261654888974e-06,
+      "loss": 0.3496,
+      "step": 417
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.441572224055644e-06,
+      "loss": 0.3395,
+      "step": 418
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.3969374009756104e-06,
+      "loss": 0.3616,
+      "step": 419
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.352358138346241e-06,
+      "loss": 0.3552,
+      "step": 420
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.307835387679007e-06,
+      "loss": 0.3411,
+      "step": 421
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.263370099279173e-06,
+      "loss": 0.3336,
+      "step": 422
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.21896322222551e-06,
+      "loss": 0.3432,
+      "step": 423
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.17461570435005e-06,
+      "loss": 0.3344,
+      "step": 424
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.130328492217841e-06,
+      "loss": 0.3561,
+      "step": 425
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.086102531106755e-06,
+      "loss": 0.3435,
+      "step": 426
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.041938764987297e-06,
+      "loss": 0.3663,
+      "step": 427
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.997838136502474e-06,
+      "loss": 0.3519,
+      "step": 428
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.953801586947664e-06,
+      "loss": 0.347,
+      "step": 429
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.3435,
+      "step": 430
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.8659244829509455e-06,
+      "loss": 0.3568,
+      "step": 431
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.822085804180985e-06,
+      "loss": 0.3534,
+      "step": 432
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.778314955644905e-06,
+      "loss": 0.3466,
+      "step": 433
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.734612871599169e-06,
+      "loss": 0.359,
+      "step": 434
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.690980484832521e-06,
+      "loss": 0.3444,
+      "step": 435
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.647418726646065e-06,
+      "loss": 0.3309,
+      "step": 436
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.603928526833386e-06,
+      "loss": 0.3378,
+      "step": 437
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.560510813660719e-06,
+      "loss": 0.3541,
+      "step": 438
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.517166513847115e-06,
+      "loss": 0.3587,
+      "step": 439
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.473896552544674e-06,
+      "loss": 0.355,
+      "step": 440
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.430701853318797e-06,
+      "loss": 0.3389,
+      "step": 441
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.387583338128471e-06,
+      "loss": 0.3499,
+      "step": 442
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.344541927306589e-06,
+      "loss": 0.3357,
+      "step": 443
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.30157853954031e-06,
+      "loss": 0.3303,
+      "step": 444
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.2586940918514474e-06,
+      "loss": 0.3424,
+      "step": 445
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.215889499576898e-06,
+      "loss": 0.3757,
+      "step": 446
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.3483,
+      "step": 447
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.130523534076549e-06,
+      "loss": 0.3567,
+      "step": 448
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.0879639829243e-06,
+      "loss": 0.3538,
+      "step": 449
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.0454879312945755e-06,
+      "loss": 0.3593,
+      "step": 450
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.0030962858073615e-06,
+      "loss": 0.3575,
+      "step": 451
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.960789951281052e-06,
+      "loss": 0.3382,
+      "step": 452
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.918569830713145e-06,
+      "loss": 0.3507,
+      "step": 453
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.876436825260967e-06,
+      "loss": 0.3509,
+      "step": 454
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.83439183422243e-06,
+      "loss": 0.3473,
+      "step": 455
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.7924357550168534e-06,
+      "loss": 0.3748,
+      "step": 456
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.750569483165785e-06,
+      "loss": 0.3469,
+      "step": 457
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.708793912273911e-06,
+      "loss": 0.3553,
+      "step": 458
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.667109934009973e-06,
+      "loss": 0.3553,
+      "step": 459
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.625518438087738e-06,
+      "loss": 0.357,
+      "step": 460
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.584020312246991e-06,
+      "loss": 0.329,
+      "step": 461
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.542616442234618e-06,
+      "loss": 0.3475,
+      "step": 462
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.501307711785672e-06,
+      "loss": 0.3294,
+      "step": 463
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.3466,
+      "step": 464
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.418979194346065e-06,
+      "loss": 0.3526,
+      "step": 465
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.3779611645968696e-06,
+      "loss": 0.3429,
+      "step": 466
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.337041788856518e-06,
+      "loss": 0.3307,
+      "step": 467
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.296221940518908e-06,
+      "loss": 0.3755,
+      "step": 468
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.255502490853575e-06,
+      "loss": 0.347,
+      "step": 469
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.214884308987136e-06,
+      "loss": 0.2027,
+      "step": 470
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.1743682618847114e-06,
+      "loss": 0.2009,
+      "step": 471
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.133955214331439e-06,
+      "loss": 0.1942,
+      "step": 472
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.093646028913996e-06,
+      "loss": 0.1812,
+      "step": 473
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.053441566002214e-06,
+      "loss": 0.1953,
+      "step": 474
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.013342683730682e-06,
+      "loss": 0.1985,
+      "step": 475
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 4.973350237980466e-06,
+      "loss": 0.185,
+      "step": 476
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.933465082360808e-06,
+      "loss": 0.1864,
+      "step": 477
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.893688068190933e-06,
+      "loss": 0.1846,
+      "step": 478
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.854020044481855e-06,
+      "loss": 0.1827,
+      "step": 479
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.814461857918279e-06,
+      "loss": 0.2007,
+      "step": 480
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.775014352840512e-06,
+      "loss": 0.1921,
+      "step": 481
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.7356783712264405e-06,
+      "loss": 0.1749,
+      "step": 482
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.696454752673578e-06,
+      "loss": 0.182,
+      "step": 483
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.657344334381116e-06,
+      "loss": 0.1766,
+      "step": 484
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.618347951132085e-06,
+      "loss": 0.1804,
+      "step": 485
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.579466435275506e-06,
+      "loss": 0.1736,
+      "step": 486
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.5407006167086575e-06,
+      "loss": 0.1736,
+      "step": 487
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.5020513228593275e-06,
+      "loss": 0.1801,
+      "step": 488
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.463519378668185e-06,
+      "loss": 0.1644,
+      "step": 489
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.425105606571145e-06,
+      "loss": 0.2001,
+      "step": 490
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.3868108264818366e-06,
+      "loss": 0.1953,
+      "step": 491
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.348635855774082e-06,
+      "loss": 0.1765,
+      "step": 492
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.310581509264471e-06,
+      "loss": 0.1856,
+      "step": 493
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.272648599194948e-06,
+      "loss": 0.1897,
+      "step": 494
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.2348379352155e-06,
+      "loss": 0.1889,
+      "step": 495
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.197150324366844e-06,
+      "loss": 0.1848,
+      "step": 496
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.1595865710632366e-06,
+      "loss": 0.1862,
+      "step": 497
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.1758,
+      "step": 498
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.084833841512791e-06,
+      "loss": 0.1712,
+      "step": 499
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.047646460807814e-06,
+      "loss": 0.1835,
+      "step": 500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.010586128697546e-06,
+      "loss": 0.1885,
+      "step": 501
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.973653636207437e-06,
+      "loss": 0.1867,
+      "step": 502
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.936849771634286e-06,
+      "loss": 0.1883,
+      "step": 503
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.9001753205294335e-06,
+      "loss": 0.1921,
+      "step": 504
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.863631065681974e-06,
+      "loss": 0.1733,
+      "step": 505
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.827217787102072e-06,
+      "loss": 0.1736,
+      "step": 506
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.790936262004287e-06,
+      "loss": 0.1792,
+      "step": 507
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.754787264791011e-06,
+      "loss": 0.176,
+      "step": 508
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.7187715670359114e-06,
+      "loss": 0.1631,
+      "step": 509
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.6828899374674933e-06,
+      "loss": 0.1825,
+      "step": 510
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.647143141952657e-06,
+      "loss": 0.1951,
+      "step": 511
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.6115319434803897e-06,
+      "loss": 0.1708,
+      "step": 512
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.5760571021454393e-06,
+      "loss": 0.185,
+      "step": 513
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.540719375132129e-06,
+      "loss": 0.1723,
+      "step": 514
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.505519516698165e-06,
+      "loss": 0.1806,
+      "step": 515
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.4704582781585596e-06,
+      "loss": 0.1641,
+      "step": 516
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.435536407869575e-06,
+      "loss": 0.1694,
+      "step": 517
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.4007546512127764e-06,
+      "loss": 0.1794,
+      "step": 518
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.366113750579091e-06,
+      "loss": 0.1814,
+      "step": 519
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.3316144453529897e-06,
+      "loss": 0.1702,
+      "step": 520
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.2972574718966845e-06,
+      "loss": 0.1755,
+      "step": 521
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.2630435635344283e-06,
+      "loss": 0.1818,
+      "step": 522
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.228973450536852e-06,
+      "loss": 0.1848,
+      "step": 523
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.1950478601053847e-06,
+      "loss": 0.1867,
+      "step": 524
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.1612675163567186e-06,
+      "loss": 0.1659,
+      "step": 525
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.1276331403073733e-06,
+      "loss": 0.1747,
+      "step": 526
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.0941454498582847e-06,
+      "loss": 0.1749,
+      "step": 527
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.0608051597795043e-06,
+      "loss": 0.1675,
+      "step": 528
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.0276129816949207e-06,
+      "loss": 0.1857,
+      "step": 529
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.9945696240670905e-06,
+      "loss": 0.1784,
+      "step": 530
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.9616757921821005e-06,
+      "loss": 0.1873,
+      "step": 531
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.1732,
+      "step": 532
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.896339510812436e-06,
+      "loss": 0.1801,
+      "step": 533
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.8638984558824777e-06,
+      "loss": 0.1822,
+      "step": 534
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.8316097157750422e-06,
+      "loss": 0.1806,
+      "step": 535
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.799473979669456e-06,
+      "loss": 0.18,
+      "step": 536
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.767491933479304e-06,
+      "loss": 0.1652,
+      "step": 537
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.7356642598377604e-06,
+      "loss": 0.1734,
+      "step": 538
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.703991638083042e-06,
+      "loss": 0.1706,
+      "step": 539
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.672474744243888e-06,
+      "loss": 0.1714,
+      "step": 540
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.64111425102515e-06,
+      "loss": 0.1694,
+      "step": 541
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.6099108277934105e-06,
+      "loss": 0.17,
+      "step": 542
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.578865140562722e-06,
+      "loss": 0.1818,
+      "step": 543
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.547977851980373e-06,
+      "loss": 0.1712,
+      "step": 544
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.517249621312752e-06,
+      "loss": 0.1741,
+      "step": 545
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.4866811044312667e-06,
+      "loss": 0.1727,
+      "step": 546
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.456272953798361e-06,
+      "loss": 0.1823,
+      "step": 547
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.426025818453572e-06,
+      "loss": 0.1848,
+      "step": 548
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.395940343999691e-06,
+      "loss": 0.1753,
+      "step": 549
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.3660171725889703e-06,
+      "loss": 0.1766,
+      "step": 550
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.3362569429094295e-06,
+      "loss": 0.1695,
+      "step": 551
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.306660290171211e-06,
+      "loss": 0.1739,
+      "step": 552
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.277227846093035e-06,
+      "loss": 0.1792,
+      "step": 553
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.2479602388887013e-06,
+      "loss": 0.1763,
+      "step": 554
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.2188580932536986e-06,
+      "loss": 0.1742,
+      "step": 555
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.1899220303518465e-06,
+      "loss": 0.1829,
+      "step": 556
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.1611526678020658e-06,
+      "loss": 0.1695,
+      "step": 557
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.132550619665168e-06,
+      "loss": 0.1774,
+      "step": 558
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.1041164964307747e-06,
+      "loss": 0.1811,
+      "step": 559
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.075850905004262e-06,
+      "loss": 0.1923,
+      "step": 560
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0477544486938306e-06,
+      "loss": 0.18,
+      "step": 561
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.019827727197605e-06,
+      "loss": 0.1724,
+      "step": 562
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9920713365908586e-06,
+      "loss": 0.1746,
+      "step": 563
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9644858693132627e-06,
+      "loss": 0.1772,
+      "step": 564
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9370719141562687e-06,
+      "loss": 0.1735,
+      "step": 565
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.1741,
+      "step": 566
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.882760877053388e-06,
+      "loss": 0.1779,
+      "step": 567
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.855864954336517e-06,
+      "loss": 0.1747,
+      "step": 568
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.8291428621735353e-06,
+      "loss": 0.1828,
+      "step": 569
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.80259517092779e-06,
+      "loss": 0.1681,
+      "step": 570
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.776222447240159e-06,
+      "loss": 0.1728,
+      "step": 571
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.7500252540169782e-06,
+      "loss": 0.1818,
+      "step": 572
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.7240041504180016e-06,
+      "loss": 0.1682,
+      "step": 573
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.6981596918444953e-06,
+      "loss": 0.1787,
+      "step": 574
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6724924299273514e-06,
+      "loss": 0.1656,
+      "step": 575
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6470029125153463e-06,
+      "loss": 0.1827,
+      "step": 576
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.6216916836634179e-06,
+      "loss": 0.1862,
+      "step": 577
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.596559283621074e-06,
+      "loss": 0.1778,
+      "step": 578
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.5716062488208494e-06,
+      "loss": 0.1563,
+      "step": 579
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.5468331118668655e-06,
+      "loss": 0.1839,
+      "step": 580
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.5222404015234483e-06,
+      "loss": 0.1741,
+      "step": 581
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4978286427038602e-06,
+      "loss": 0.1768,
+      "step": 582
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4735983564590784e-06,
+      "loss": 0.1781,
+      "step": 583
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.44955005996669e-06,
+      "loss": 0.1709,
+      "step": 584
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.4256842665198377e-06,
+      "loss": 0.1702,
+      "step": 585
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.4020014855162755e-06,
+      "loss": 0.1808,
+      "step": 586
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.3785022224474943e-06,
+      "loss": 0.1762,
+      "step": 587
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.3551869788879213e-06,
+      "loss": 0.1718,
+      "step": 588
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.332056252484234e-06,
+      "loss": 0.1884,
+      "step": 589
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.3091105369447166e-06,
+      "loss": 0.1712,
+      "step": 590
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.2863503220287433e-06,
+      "loss": 0.1712,
+      "step": 591
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.2637760935363053e-06,
+      "loss": 0.1883,
+      "step": 592
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.2413883332976573e-06,
+      "loss": 0.1802,
+      "step": 593
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.2191875191630209e-06,
+      "loss": 0.1671,
+      "step": 594
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.1971741249923985e-06,
+      "loss": 0.1766,
+      "step": 595
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1753486206454433e-06,
+      "loss": 0.1657,
+      "step": 596
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1537114719714482e-06,
+      "loss": 0.1788,
+      "step": 597
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.132263140799381e-06,
+      "loss": 0.1727,
+      "step": 598
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.1110040849280534e-06,
+      "loss": 0.1774,
+      "step": 599
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.1626,
+      "step": 600
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.0690556100734284e-06,
+      "loss": 0.1768,
+      "step": 601
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.0483670864493777e-06,
+      "loss": 0.1763,
+      "step": 602
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.0278696288254475e-06,
+      "loss": 0.1754,
+      "step": 603
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.0075636747047446e-06,
+      "loss": 0.178,
+      "step": 604
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.874496575028814e-07,
+      "loss": 0.1722,
+      "step": 605
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.675280065387117e-07,
+      "loss": 0.1924,
+      "step": 606
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.47799147025179e-07,
+      "loss": 0.1771,
+      "step": 607
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.282635000602346e-07,
+      "loss": 0.1757,
+      "step": 608
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.089214826178505e-07,
+      "loss": 0.1818,
+      "step": 609
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.897735075391156e-07,
+      "loss": 0.1675,
+      "step": 610
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.708199835234343e-07,
+      "loss": 0.1944,
+      "step": 611
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.520613151197899e-07,
+      "loss": 0.1732,
+      "step": 612
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.334979027181222e-07,
+      "loss": 0.1851,
+      "step": 613
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.151301425407699e-07,
+      "loss": 0.1887,
+      "step": 614
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.969584266340258e-07,
+      "loss": 0.164,
+      "step": 615
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.78983142859755e-07,
+      "loss": 0.1876,
+      "step": 616
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.1822,
+      "step": 617
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.43623402184438e-07,
+      "loss": 0.1756,
+      "step": 618
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.262397000109645e-07,
+      "loss": 0.184,
+      "step": 619
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 7.090539394090135e-07,
+      "loss": 0.1827,
+      "step": 620
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.920664871959603e-07,
+      "loss": 0.1669,
+      "step": 621
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.752777059564431e-07,
+      "loss": 0.1723,
+      "step": 622
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.586879540346092e-07,
+      "loss": 0.1719,
+      "step": 623
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.422975855264757e-07,
+      "loss": 0.1745,
+      "step": 624
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.261069502723616e-07,
+      "loss": 0.1715,
+      "step": 625
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.101163938494359e-07,
+      "loss": 0.164,
+      "step": 626
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.943262575643239e-07,
+      "loss": 0.1745,
+      "step": 627
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.78736878445837e-07,
+      "loss": 0.1748,
+      "step": 628
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.633485892377699e-07,
+      "loss": 0.189,
+      "step": 629
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.481617183918053e-07,
+      "loss": 0.1607,
+      "step": 630
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.331765900604913e-07,
+      "loss": 0.1747,
+      "step": 631
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.183935240903415e-07,
+      "loss": 0.1778,
+      "step": 632
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.038128360149885e-07,
+      "loss": 0.1619,
+      "step": 633
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.1868,
+      "step": 634
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.752598340785475e-07,
+      "loss": 0.1749,
+      "step": 635
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.6128812966021894e-07,
+      "loss": 0.1706,
+      "step": 636
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.475200220092002e-07,
+      "loss": 0.1826,
+      "step": 637
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.3395580499559276e-07,
+      "loss": 0.1838,
+      "step": 638
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.205957681375994e-07,
+      "loss": 0.1779,
+      "step": 639
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.0744019659535116e-07,
+      "loss": 0.1745,
+      "step": 640
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.9448937116481676e-07,
+      "loss": 0.1818,
+      "step": 641
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.817435682718096e-07,
+      "loss": 0.1755,
+      "step": 642
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.6920305996608785e-07,
+      "loss": 0.184,
+      "step": 643
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.5686811391555164e-07,
+      "loss": 0.1838,
+      "step": 644
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.4473899340052075e-07,
+      "loss": 0.1831,
+      "step": 645
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.328159573081258e-07,
+      "loss": 0.1767,
+      "step": 646
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.2109926012677484e-07,
+      "loss": 0.1746,
+      "step": 647
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.095891519407246e-07,
+      "loss": 0.1788,
+      "step": 648
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.982858784247422e-07,
+      "loss": 0.1859,
+      "step": 649
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.871896808388608e-07,
+      "loss": 0.1729,
+      "step": 650
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.7630079602323447e-07,
+      "loss": 0.1827,
+      "step": 651
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.656194563930714e-07,
+      "loss": 0.1731,
+      "step": 652
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.5514588993368894e-07,
+      "loss": 0.165,
+      "step": 653
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.44880320195634e-07,
+      "loss": 0.1792,
+      "step": 654
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.348229662899193e-07,
+      "loss": 0.1679,
+      "step": 655
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.2497404288334245e-07,
+      "loss": 0.1816,
+      "step": 656
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.1533376019391095e-07,
+      "loss": 0.1878,
+      "step": 657
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.0590232398634114e-07,
+      "loss": 0.171,
+      "step": 658
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.9667993556768517e-07,
+      "loss": 0.176,
+      "step": 659
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.876667917830155e-07,
+      "loss": 0.1644,
+      "step": 660
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.788630850112405e-07,
+      "loss": 0.1828,
+      "step": 661
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.7026900316098217e-07,
+      "loss": 0.1735,
+      "step": 662
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.6188472966658043e-07,
+      "loss": 0.1623,
+      "step": 663
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.537104434841641e-07,
+      "loss": 0.168,
+      "step": 664
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.4574631908784275e-07,
+      "loss": 0.1736,
+      "step": 665
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.3799252646597428e-07,
+      "loss": 0.1798,
+      "step": 666
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.3044923111754427e-07,
+      "loss": 0.1769,
+      "step": 667
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.1807,
+      "step": 668
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.1599477176894136e-07,
+      "loss": 0.1715,
+      "step": 669
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.0908391628854042e-07,
+      "loss": 0.1717,
+      "step": 670
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.0238417511453158e-07,
+      "loss": 0.1801,
+      "step": 671
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 9.589569124794918e-08,
+      "loss": 0.1793,
+      "step": 672
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 8.961860318069115e-08,
+      "loss": 0.1835,
+      "step": 673
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 8.355304489257254e-08,
+      "loss": 0.1829,
+      "step": 674
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 7.769914584845994e-08,
+      "loss": 0.1702,
+      "step": 675
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.205703099551042e-08,
+      "loss": 0.1595,
+      "step": 676
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 6.662682076050031e-08,
+      "loss": 0.1826,
+      "step": 677
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 6.140863104726391e-08,
+      "loss": 0.1759,
+      "step": 678
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.6402573234207725e-08,
+      "loss": 0.1607,
+      "step": 679
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.1608754171944555e-08,
+      "loss": 0.1817,
+      "step": 680
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.702727618100422e-08,
+      "loss": 0.1885,
+      "step": 681
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.2658237049655325e-08,
+      "loss": 0.1933,
+      "step": 682
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.850173003181357e-08,
+      "loss": 0.1591,
+      "step": 683
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.455784384505445e-08,
+      "loss": 0.1785,
+      "step": 684
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 3.082666266872036e-08,
+      "loss": 0.1668,
+      "step": 685
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.7308266142119788e-08,
+      "loss": 0.17,
+      "step": 686
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.400272936283088e-08,
+      "loss": 0.1752,
+      "step": 687
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 2.0910122885097194e-08,
+      "loss": 0.1747,
+      "step": 688
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.8030512718322235e-08,
+      "loss": 0.1698,
+      "step": 689
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.5363960325660565e-08,
+      "loss": 0.1828,
+      "step": 690
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.2910522622705534e-08,
+      "loss": 0.1781,
+      "step": 691
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.0670251976275803e-08,
+      "loss": 0.1759,
+      "step": 692
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 8.643196203294013e-09,
+      "loss": 0.1688,
+      "step": 693
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 6.82939856977094e-09,
+      "loss": 0.17,
+      "step": 694
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.228897789878451e-09,
+      "loss": 0.1785,
+      "step": 695
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 3.8417280251257235e-09,
+      "loss": 0.1683,
+      "step": 696
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.667918883627607e-09,
+      "loss": 0.1756,
+      "step": 697
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.7074954194729044e-09,
+      "loss": 0.1746,
+      "step": 698
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 9.604781321936875e-10,
+      "loss": 0.1719,
+      "step": 699
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 4.2688296632120705e-10,
+      "loss": 0.1816,
+      "step": 700
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.0672131105282646e-10,
+      "loss": 0.1719,
+      "step": 701
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1783,
+      "step": 702
+    },
+    {
+      "epoch": 3.0,
+      "step": 702,
+      "total_flos": 4.271125352719319e+17,
+      "train_loss": 0.3649357236348666,
+      "train_runtime": 3891.5455,
+      "train_samples_per_second": 23.127,
+      "train_steps_per_second": 0.18
+    }
+  ],
+  "max_steps": 702,
+  "num_train_epochs": 3,
+  "total_flos": 4.271125352719319e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdee6a90df0c48439c002ee726be6e54bbbbb89a97d97ff6449217f11b586fe0
+size 3707