Upload folder using huggingface_hub

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/zk/home/wuqinzhuo/code/BigModel/COT/github/ToolBench/ToolLLaMA-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "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": "4.28.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

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": "4.28.1"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950505467e2b9d61c77085eff53a004a34e6de06f915f0996bf21b5a7e477f85
+size 9877989586

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a1f5d3c29b6f3b69a104bec728bdc826ff491ee2ce141ded9caa252c0c5de5
+size 9894801014

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9511df2400ff968390c9aeef96f8501a18f010bb526849fac3e2dd75c34df7
+size 7180990649

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953670656
+  },
+  "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 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 8192,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,4085 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9992584352984797,
+  "global_step": 674,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 0.9184,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.9226,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.7856,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.7922,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 0.6422,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.5384,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.2962962962962962e-05,
+      "loss": 0.5082,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.5413,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.4565,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.4604,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.037037037037037e-05,
+      "loss": 0.486,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.4797,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.4074074074074074e-05,
+      "loss": 0.4684,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.3826,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.4032,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 0.4024,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.148148148148148e-05,
+      "loss": 0.3624,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3776,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.4135,
+      "step": 19
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.3613,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.3409,
+      "step": 21
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.3493,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.259259259259259e-05,
+      "loss": 0.3327,
+      "step": 23
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.3361,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.363,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.3036,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5e-05,
+      "loss": 0.3057,
+      "step": 27
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.999970528628716e-05,
+      "loss": 0.3926,
+      "step": 28
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.999882115209711e-05,
+      "loss": 0.3045,
+      "step": 29
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.999734761827518e-05,
+      "loss": 0.2907,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9995284719563015e-05,
+      "loss": 0.2982,
+      "step": 31
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.999263250459779e-05,
+      "loss": 0.332,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.998939103591103e-05,
+      "loss": 0.3169,
+      "step": 33
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.998556038992714e-05,
+      "loss": 0.3662,
+      "step": 34
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.9981140656961645e-05,
+      "loss": 0.3214,
+      "step": 35
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.997613194121902e-05,
+      "loss": 0.2994,
+      "step": 36
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.997053436079025e-05,
+      "loss": 0.2729,
+      "step": 37
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.9964348047650004e-05,
+      "loss": 0.2914,
+      "step": 38
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.9957573147653615e-05,
+      "loss": 0.3089,
+      "step": 39
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.995020982053354e-05,
+      "loss": 0.2787,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.994225823989567e-05,
+      "loss": 0.2941,
+      "step": 41
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.993371859321518e-05,
+      "loss": 0.3103,
+      "step": 42
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.992459108183217e-05,
+      "loss": 0.2666,
+      "step": 43
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.9914875920946835e-05,
+      "loss": 0.3063,
+      "step": 44
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.990457333961449e-05,
+      "loss": 0.2899,
+      "step": 45
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.9893683580740066e-05,
+      "loss": 0.3058,
+      "step": 46
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.9882206901072495e-05,
+      "loss": 0.3234,
+      "step": 47
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.9870143571198545e-05,
+      "loss": 0.2889,
+      "step": 48
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.985749387553652e-05,
+      "loss": 0.275,
+      "step": 49
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.984425811232954e-05,
+      "loss": 0.2988,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.9830436593638455e-05,
+      "loss": 0.2436,
+      "step": 51
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.981602964533456e-05,
+      "loss": 0.2999,
+      "step": 52
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.980103760709187e-05,
+      "loss": 0.2922,
+      "step": 53
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.978546083237914e-05,
+      "loss": 0.2753,
+      "step": 54
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.9769299688451475e-05,
+      "loss": 0.2615,
+      "step": 55
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.975255455634176e-05,
+      "loss": 0.269,
+      "step": 56
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.9735225830851575e-05,
+      "loss": 0.292,
+      "step": 57
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.971731392054198e-05,
+      "loss": 0.2871,
+      "step": 58
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.969881924772381e-05,
+      "loss": 0.3152,
+      "step": 59
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.967974224844777e-05,
+      "loss": 0.264,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.966008337249411e-05,
+      "loss": 0.2851,
+      "step": 61
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.963984308336208e-05,
+      "loss": 0.2519,
+      "step": 62
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.961902185825892e-05,
+      "loss": 0.2274,
+      "step": 63
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.9597620188088676e-05,
+      "loss": 0.2706,
+      "step": 64
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.9575638577440606e-05,
+      "loss": 0.2822,
+      "step": 65
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.9553077544577284e-05,
+      "loss": 0.2219,
+      "step": 66
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.952993762142236e-05,
+      "loss": 0.2716,
+      "step": 67
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.9506219353548045e-05,
+      "loss": 0.238,
+      "step": 68
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.948192330016226e-05,
+      "loss": 0.2807,
+      "step": 69
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.9457050034095395e-05,
+      "loss": 0.2397,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.943160014178686e-05,
+      "loss": 0.2662,
+      "step": 71
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.9405574223271246e-05,
+      "loss": 0.3248,
+      "step": 72
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.9378972892164156e-05,
+      "loss": 0.2869,
+      "step": 73
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.935179677564774e-05,
+      "loss": 0.2342,
+      "step": 74
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.932404651445596e-05,
+      "loss": 0.2968,
+      "step": 75
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.9295722762859383e-05,
+      "loss": 0.2189,
+      "step": 76
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.926682618864988e-05,
+      "loss": 0.3025,
+      "step": 77
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.923735747312477e-05,
+      "loss": 0.2458,
+      "step": 78
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.920731731107082e-05,
+      "loss": 0.231,
+      "step": 79
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.917670641074784e-05,
+      "loss": 0.255,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.9145525493872014e-05,
+      "loss": 0.2198,
+      "step": 81
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.911377529559883e-05,
+      "loss": 0.2827,
+      "step": 82
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.908145656450579e-05,
+      "loss": 0.2509,
+      "step": 83
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.9048570062574764e-05,
+      "loss": 0.204,
+      "step": 84
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.901511656517399e-05,
+      "loss": 0.2879,
+      "step": 85
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.898109686103983e-05,
+      "loss": 0.2926,
+      "step": 86
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.894651175225815e-05,
+      "loss": 0.2334,
+      "step": 87
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.8911362054245416e-05,
+      "loss": 0.2381,
+      "step": 88
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.8875648595729454e-05,
+      "loss": 0.233,
+      "step": 89
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.883937221872995e-05,
+      "loss": 0.2768,
+      "step": 90
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.8802533778538566e-05,
+      "loss": 0.2225,
+      "step": 91
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.876513414369878e-05,
+      "loss": 0.2175,
+      "step": 92
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.872717419598541e-05,
+      "loss": 0.2311,
+      "step": 93
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.868865483038383e-05,
+      "loss": 0.2587,
+      "step": 94
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.864957695506885e-05,
+      "loss": 0.3273,
+      "step": 95
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.860994149138335e-05,
+      "loss": 0.2918,
+      "step": 96
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.856974937381648e-05,
+      "loss": 0.2508,
+      "step": 97
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.85290015499817e-05,
+      "loss": 0.2777,
+      "step": 98
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.848769898059442e-05,
+      "loss": 0.2597,
+      "step": 99
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.8445842639449313e-05,
+      "loss": 0.294,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.84034335133974e-05,
+      "loss": 0.2387,
+      "step": 101
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.836047260232276e-05,
+      "loss": 0.2745,
+      "step": 102
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.831696091911895e-05,
+      "loss": 0.2732,
+      "step": 103
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.8272899489665167e-05,
+      "loss": 0.2347,
+      "step": 104
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.8228289352802006e-05,
+      "loss": 0.2397,
+      "step": 105
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.8183131560306976e-05,
+      "loss": 0.2591,
+      "step": 106
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.813742717686974e-05,
+      "loss": 0.2281,
+      "step": 107
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.809117728006699e-05,
+      "loss": 0.2228,
+      "step": 108
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.804438296033702e-05,
+      "loss": 0.2303,
+      "step": 109
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.7997045320954056e-05,
+      "loss": 0.2742,
+      "step": 110
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.79491654780022e-05,
+      "loss": 0.2369,
+      "step": 111
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.790074456034918e-05,
+      "loss": 0.2551,
+      "step": 112
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.7851783709619634e-05,
+      "loss": 0.2613,
+      "step": 113
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.780228408016831e-05,
+      "loss": 0.2337,
+      "step": 114
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.7752246839052785e-05,
+      "loss": 0.2112,
+      "step": 115
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.770167316600593e-05,
+      "loss": 0.2248,
+      "step": 116
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.765056425340815e-05,
+      "loss": 0.2563,
+      "step": 117
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.7598921306259236e-05,
+      "loss": 0.2603,
+      "step": 118
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.754674554214996e-05,
+      "loss": 0.2199,
+      "step": 119
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.749403819123338e-05,
+      "loss": 0.2052,
+      "step": 120
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.744080049619582e-05,
+      "loss": 0.2565,
+      "step": 121
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.738703371222758e-05,
+      "loss": 0.2796,
+      "step": 122
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.733273910699334e-05,
+      "loss": 0.259,
+      "step": 123
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.727791796060229e-05,
+      "loss": 0.257,
+      "step": 124
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.72225715655779e-05,
+      "loss": 0.2393,
+      "step": 125
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.7166701226827495e-05,
+      "loss": 0.2474,
+      "step": 126
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.711030826161149e-05,
+      "loss": 0.2596,
+      "step": 127
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.705339399951229e-05,
+      "loss": 0.2681,
+      "step": 128
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.699595978240297e-05,
+      "loss": 0.2652,
+      "step": 129
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.693800696441564e-05,
+      "loss": 0.2259,
+      "step": 130
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.6879536911909514e-05,
+      "loss": 0.2608,
+      "step": 131
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.682055100343869e-05,
+      "loss": 0.241,
+      "step": 132
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.676105062971967e-05,
+      "loss": 0.2579,
+      "step": 133
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.6701037193598515e-05,
+      "loss": 0.3111,
+      "step": 134
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.664051211001786e-05,
+      "loss": 0.1979,
+      "step": 135
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.6579476805983445e-05,
+      "loss": 0.316,
+      "step": 136
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.6517932720530574e-05,
+      "loss": 0.2279,
+      "step": 137
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.6455881304690116e-05,
+      "loss": 0.2519,
+      "step": 138
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.639332402145432e-05,
+      "loss": 0.2608,
+      "step": 139
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.633026234574232e-05,
+      "loss": 0.2132,
+      "step": 140
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.626669776436537e-05,
+      "loss": 0.2364,
+      "step": 141
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.620263177599177e-05,
+      "loss": 0.2387,
+      "step": 142
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.613806589111155e-05,
+      "loss": 0.2326,
+      "step": 143
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.607300163200083e-05,
+      "loss": 0.2564,
+      "step": 144
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.600744053268596e-05,
+      "loss": 0.2605,
+      "step": 145
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.594138413890736e-05,
+      "loss": 0.231,
+      "step": 146
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.5874834008083015e-05,
+      "loss": 0.2,
+      "step": 147
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.580779170927183e-05,
+      "loss": 0.2298,
+      "step": 148
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.5740258823136574e-05,
+      "loss": 0.2075,
+      "step": 149
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.567223694190667e-05,
+      "loss": 0.2771,
+      "step": 150
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.5603727669340606e-05,
+      "loss": 0.2017,
+      "step": 151
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.553473262068815e-05,
+      "loss": 0.2085,
+      "step": 152
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.5465253422652254e-05,
+      "loss": 0.2166,
+      "step": 153
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.5395291713350715e-05,
+      "loss": 0.1932,
+      "step": 154
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.5324849142277545e-05,
+      "loss": 0.2219,
+      "step": 155
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.525392737026407e-05,
+      "loss": 0.2358,
+      "step": 156
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.51825280694398e-05,
+      "loss": 0.2272,
+      "step": 157
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.511065292319296e-05,
+      "loss": 0.2991,
+      "step": 158
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.5038303626130875e-05,
+      "loss": 0.211,
+      "step": 159
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.4965481884039915e-05,
+      "loss": 0.213,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.489218941384537e-05,
+      "loss": 0.1961,
+      "step": 161
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.4818427943570924e-05,
+      "loss": 0.2265,
+      "step": 162
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.4744199212297914e-05,
+      "loss": 0.2022,
+      "step": 163
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.466950497012434e-05,
+      "loss": 0.2501,
+      "step": 164
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.4594346978123595e-05,
+      "loss": 0.2537,
+      "step": 165
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.4518727008302954e-05,
+      "loss": 0.2576,
+      "step": 166
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.4442646843561785e-05,
+      "loss": 0.2679,
+      "step": 167
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.436610827764951e-05,
+      "loss": 0.1983,
+      "step": 168
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.4289113115123316e-05,
+      "loss": 0.2703,
+      "step": 169
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.421166317130563e-05,
+      "loss": 0.2199,
+      "step": 170
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.413376027224129e-05,
+      "loss": 0.2305,
+      "step": 171
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.405540625465451e-05,
+      "loss": 0.225,
+      "step": 172
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.397660296590556e-05,
+      "loss": 0.2591,
+      "step": 173
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.389735226394722e-05,
+      "loss": 0.2271,
+      "step": 174
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.3817656017280995e-05,
+      "loss": 0.2396,
+      "step": 175
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.373751610491301e-05,
+      "loss": 0.2561,
+      "step": 176
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.365693441630976e-05,
+      "loss": 0.2433,
+      "step": 177
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.357591285135354e-05,
+      "loss": 0.2337,
+      "step": 178
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.349445332029765e-05,
+      "loss": 0.215,
+      "step": 179
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.3412557743721336e-05,
+      "loss": 0.2186,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.333022805248458e-05,
+      "loss": 0.2591,
+      "step": 181
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.324746618768249e-05,
+      "loss": 0.2667,
+      "step": 182
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.316427410059959e-05,
+      "loss": 0.2198,
+      "step": 183
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.308065375266377e-05,
+      "loss": 0.2171,
+      "step": 184
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.29966071154001e-05,
+      "loss": 0.2264,
+      "step": 185
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.2912136170384307e-05,
+      "loss": 0.2725,
+      "step": 186
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.282724290919605e-05,
+      "loss": 0.2265,
+      "step": 187
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.2741929333371986e-05,
+      "loss": 0.2887,
+      "step": 188
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.265619745435856e-05,
+      "loss": 0.2413,
+      "step": 189
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.257004929346462e-05,
+      "loss": 0.2571,
+      "step": 190
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.248348688181371e-05,
+      "loss": 0.2317,
+      "step": 191
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.239651226029619e-05,
+      "loss": 0.2089,
+      "step": 192
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.230912747952118e-05,
+      "loss": 0.2081,
+      "step": 193
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.2221334599768114e-05,
+      "loss": 0.2045,
+      "step": 194
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.213313569093824e-05,
+      "loss": 0.2263,
+      "step": 195
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.20445328325058e-05,
+      "loss": 0.196,
+      "step": 196
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.1955528113468966e-05,
+      "loss": 0.1844,
+      "step": 197
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.186612363230065e-05,
+      "loss": 0.234,
+      "step": 198
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.177632149689897e-05,
+      "loss": 0.2112,
+      "step": 199
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.168612382453759e-05,
+      "loss": 0.2052,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.159553274181578e-05,
+      "loss": 0.2232,
+      "step": 201
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.15045503846083e-05,
+      "loss": 0.1687,
+      "step": 202
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.141317889801499e-05,
+      "loss": 0.1874,
+      "step": 203
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.132142043631028e-05,
+      "loss": 0.2434,
+      "step": 204
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.12292771628923e-05,
+      "loss": 0.2531,
+      "step": 205
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.1136751250231966e-05,
+      "loss": 0.2449,
+      "step": 206
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.104384487982169e-05,
+      "loss": 0.2521,
+      "step": 207
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.095056024212399e-05,
+      "loss": 0.2189,
+      "step": 208
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.085689953651982e-05,
+      "loss": 0.2032,
+      "step": 209
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.076286497125671e-05,
+      "loss": 0.247,
+      "step": 210
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.0668458763396735e-05,
+      "loss": 0.239,
+      "step": 211
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.057368313876423e-05,
+      "loss": 0.1929,
+      "step": 212
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.0478540331893263e-05,
+      "loss": 0.1898,
+      "step": 213
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.0383032585975066e-05,
+      "loss": 0.2054,
+      "step": 214
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.0287162152805e-05,
+      "loss": 0.2121,
+      "step": 215
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.019093129272958e-05,
+      "loss": 0.2278,
+      "step": 216
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.0094342274593135e-05,
+      "loss": 0.2454,
+      "step": 217
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.9997397375684295e-05,
+      "loss": 0.225,
+      "step": 218
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.990009888168238e-05,
+      "loss": 0.2471,
+      "step": 219
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.980244908660341e-05,
+      "loss": 0.1954,
+      "step": 220
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.970445029274607e-05,
+      "loss": 0.2089,
+      "step": 221
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.960610481063744e-05,
+      "loss": 0.2453,
+      "step": 222
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.9507414958978494e-05,
+      "loss": 0.1901,
+      "step": 223
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.940838306458944e-05,
+      "loss": 0.2113,
+      "step": 224
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.930901146235485e-05,
+      "loss": 0.1836,
+      "step": 225
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.9209302495168654e-05,
+      "loss": 0.2376,
+      "step": 226
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.910925851387882e-05,
+      "loss": 0.2262,
+      "step": 227
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.900888187723203e-05,
+      "loss": 0.1913,
+      "step": 228
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.890817495181795e-05,
+      "loss": 0.1979,
+      "step": 229
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.8807140112013574e-05,
+      "loss": 0.2066,
+      "step": 230
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.8705779739927095e-05,
+      "loss": 0.2521,
+      "step": 231
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.860409622534184e-05,
+      "loss": 0.2169,
+      "step": 232
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.850209196565991e-05,
+      "loss": 0.2584,
+      "step": 233
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.8399769365845625e-05,
+      "loss": 0.213,
+      "step": 234
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.829713083836886e-05,
+      "loss": 0.2185,
+      "step": 235
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.819417880314813e-05,
+      "loss": 0.2325,
+      "step": 236
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.8090915687493545e-05,
+      "loss": 0.2231,
+      "step": 237
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.798734392604962e-05,
+      "loss": 0.183,
+      "step": 238
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.788346596073782e-05,
+      "loss": 0.2298,
+      "step": 239
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.7779284240699003e-05,
+      "loss": 0.2299,
+      "step": 240
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.7674801222235706e-05,
+      "loss": 0.2235,
+      "step": 241
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.757001936875418e-05,
+      "loss": 0.1848,
+      "step": 242
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.746494115070636e-05,
+      "loss": 0.2397,
+      "step": 243
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.735956904553158e-05,
+      "loss": 0.1875,
+      "step": 244
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.72539055375982e-05,
+      "loss": 0.1987,
+      "step": 245
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.714795311814499e-05,
+      "loss": 0.2212,
+      "step": 246
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.704171428522242e-05,
+      "loss": 0.2174,
+      "step": 247
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.6935191543633776e-05,
+      "loss": 0.2165,
+      "step": 248
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.6828387404876056e-05,
+      "loss": 0.2094,
+      "step": 249
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.6721304387080804e-05,
+      "loss": 0.1776,
+      "step": 250
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.661394501495474e-05,
+      "loss": 0.1595,
+      "step": 251
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.650631181972018e-05,
+      "loss": 0.2081,
+      "step": 252
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.639840733905541e-05,
+      "loss": 0.2008,
+      "step": 253
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.629023411703484e-05,
+      "loss": 0.2133,
+      "step": 254
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.6181794704069036e-05,
+      "loss": 0.1909,
+      "step": 255
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.607309165684455e-05,
+      "loss": 0.1886,
+      "step": 256
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.596412753826367e-05,
+      "loss": 0.1778,
+      "step": 257
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.5854904917384e-05,
+      "loss": 0.2146,
+      "step": 258
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.574542636935786e-05,
+      "loss": 0.1899,
+      "step": 259
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.563569447537161e-05,
+      "loss": 0.2459,
+      "step": 260
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.552571182258476e-05,
+      "loss": 0.2508,
+      "step": 261
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.541548100406897e-05,
+      "loss": 0.1831,
+      "step": 262
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.5305004618746976e-05,
+      "loss": 0.2369,
+      "step": 263
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.5194285271331204e-05,
+      "loss": 0.2135,
+      "step": 264
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.508332557226246e-05,
+      "loss": 0.2163,
+      "step": 265
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.497212813764833e-05,
+      "loss": 0.2167,
+      "step": 266
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.4860695589201535e-05,
+      "loss": 0.2048,
+      "step": 267
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.474903055417807e-05,
+      "loss": 0.1896,
+      "step": 268
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.4637135665315306e-05,
+      "loss": 0.2422,
+      "step": 269
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.45250135607699e-05,
+      "loss": 0.2465,
+      "step": 270
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.441266688405556e-05,
+      "loss": 0.2143,
+      "step": 271
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.4300098283980814e-05,
+      "loss": 0.2149,
+      "step": 272
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.4187310414586474e-05,
+      "loss": 0.2376,
+      "step": 273
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.407430593508304e-05,
+      "loss": 0.2277,
+      "step": 274
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.396108750978813e-05,
+      "loss": 0.2359,
+      "step": 275
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.384765780806353e-05,
+      "loss": 0.2482,
+      "step": 276
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.373401950425231e-05,
+      "loss": 0.2342,
+      "step": 277
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.3620175277615806e-05,
+      "loss": 0.2281,
+      "step": 278
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.3506127812270385e-05,
+      "loss": 0.1932,
+      "step": 279
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.33918797971242e-05,
+      "loss": 0.2035,
+      "step": 280
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.327743392581379e-05,
+      "loss": 0.2329,
+      "step": 281
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.316279289664057e-05,
+      "loss": 0.1897,
+      "step": 282
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.304795941250722e-05,
+      "loss": 0.2026,
+      "step": 283
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.293293618085392e-05,
+      "loss": 0.186,
+      "step": 284
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.281772591359457e-05,
+      "loss": 0.2262,
+      "step": 285
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.2702331327052816e-05,
+      "loss": 0.1735,
+      "step": 286
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.258675514189802e-05,
+      "loss": 0.1621,
+      "step": 287
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.2471000083081126e-05,
+      "loss": 0.206,
+      "step": 288
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.235506887977038e-05,
+      "loss": 0.2173,
+      "step": 289
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.223896426528701e-05,
+      "loss": 0.1933,
+      "step": 290
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.2122688977040765e-05,
+      "loss": 0.181,
+      "step": 291
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.200624575646542e-05,
+      "loss": 0.2182,
+      "step": 292
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.1889637348954076e-05,
+      "loss": 0.1973,
+      "step": 293
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.1772866503794464e-05,
+      "loss": 0.2129,
+      "step": 294
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.165593597410414e-05,
+      "loss": 0.2149,
+      "step": 295
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.1538848516765546e-05,
+      "loss": 0.2395,
+      "step": 296
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.142160689236102e-05,
+      "loss": 0.1873,
+      "step": 297
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.1304213865107715e-05,
+      "loss": 0.1967,
+      "step": 298
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.1186672202792435e-05,
+      "loss": 0.2074,
+      "step": 299
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.1068984676706344e-05,
+      "loss": 0.2306,
+      "step": 300
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.095115406157968e-05,
+      "loss": 0.2121,
+      "step": 301
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.083318313551628e-05,
+      "loss": 0.2234,
+      "step": 302
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.07150746799281e-05,
+      "loss": 0.2329,
+      "step": 303
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.059683147946968e-05,
+      "loss": 0.1665,
+      "step": 304
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.0478456321972422e-05,
+      "loss": 0.2467,
+      "step": 305
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.0359951998378894e-05,
+      "loss": 0.1902,
+      "step": 306
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.0241321302677038e-05,
+      "loss": 0.1981,
+      "step": 307
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.0122567031834275e-05,
+      "loss": 0.2039,
+      "step": 308
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.0003691985731574e-05,
+      "loss": 0.2224,
+      "step": 309
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.9884698967097425e-05,
+      "loss": 0.1845,
+      "step": 310
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.9765590781441776e-05,
+      "loss": 0.1746,
+      "step": 311
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.9646370236989884e-05,
+      "loss": 0.1793,
+      "step": 312
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.952704014461608e-05,
+      "loss": 0.1622,
+      "step": 313
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.9407603317777544e-05,
+      "loss": 0.2037,
+      "step": 314
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.9288062572447926e-05,
+      "loss": 0.2136,
+      "step": 315
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.9168420727050972e-05,
+      "loss": 0.1836,
+      "step": 316
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.9048680602394085e-05,
+      "loss": 0.2239,
+      "step": 317
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.892884502160181e-05,
+      "loss": 0.168,
+      "step": 318
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.8808916810049248e-05,
+      "loss": 0.1927,
+      "step": 319
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.8688898795295477e-05,
+      "loss": 0.2387,
+      "step": 320
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.8568793807016892e-05,
+      "loss": 0.2304,
+      "step": 321
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.8448604676940442e-05,
+      "loss": 0.2212,
+      "step": 322
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.8328334238776915e-05,
+      "loss": 0.1887,
+      "step": 323
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.8207985328154107e-05,
+      "loss": 0.2298,
+      "step": 324
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.8087560782549944e-05,
+      "loss": 0.214,
+      "step": 325
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.7967063441225633e-05,
+      "loss": 0.2337,
+      "step": 326
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.7846496145158683e-05,
+      "loss": 0.1779,
+      "step": 327
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.772586173697593e-05,
+      "loss": 0.1806,
+      "step": 328
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.7605163060886517e-05,
+      "loss": 0.1935,
+      "step": 329
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.748440296261485e-05,
+      "loss": 0.2478,
+      "step": 330
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.7363584289333478e-05,
+      "loss": 0.2177,
+      "step": 331
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.7242709889595974e-05,
+      "loss": 0.1898,
+      "step": 332
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.7121782613269807e-05,
+      "loss": 0.2004,
+      "step": 333
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.7000805311469096e-05,
+      "loss": 0.1983,
+      "step": 334
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.6879780836487412e-05,
+      "loss": 0.1708,
+      "step": 335
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.6758712041730567e-05,
+      "loss": 0.2253,
+      "step": 336
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.6637601781649264e-05,
+      "loss": 0.2016,
+      "step": 337
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1552647203207016,
+      "eval_runtime": 29.6391,
+      "eval_samples_per_second": 10.122,
+      "eval_steps_per_second": 0.641,
+      "step": 337
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.651645291167186e-05,
+      "loss": 0.1531,
+      "step": 338
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.6395268288137028e-05,
+      "loss": 0.1604,
+      "step": 339
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.6274050768226384e-05,
+      "loss": 0.1236,
+      "step": 340
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.6152803209897153e-05,
+      "loss": 0.131,
+      "step": 341
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.6031528471814793e-05,
+      "loss": 0.1197,
+      "step": 342
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.5910229413285563e-05,
+      "loss": 0.1108,
+      "step": 343
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.5788908894189147e-05,
+      "loss": 0.1381,
+      "step": 344
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.5667569774911175e-05,
+      "loss": 0.0951,
+      "step": 345
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.5546214916275856e-05,
+      "loss": 0.1315,
+      "step": 346
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.5424847179478454e-05,
+      "loss": 0.0849,
+      "step": 347
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.5303469426017878e-05,
+      "loss": 0.1023,
+      "step": 348
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.5182084517629207e-05,
+      "loss": 0.1193,
+      "step": 349
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.5060695316216188e-05,
+      "loss": 0.1124,
+      "step": 350
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.493930468378381e-05,
+      "loss": 0.1223,
+      "step": 351
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.4817915482370796e-05,
+      "loss": 0.1042,
+      "step": 352
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.469653057398213e-05,
+      "loss": 0.1197,
+      "step": 353
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.4575152820521548e-05,
+      "loss": 0.1124,
+      "step": 354
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.4453785083724147e-05,
+      "loss": 0.1163,
+      "step": 355
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.433243022508883e-05,
+      "loss": 0.1016,
+      "step": 356
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.421109110581087e-05,
+      "loss": 0.1389,
+      "step": 357
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.4089770586714436e-05,
+      "loss": 0.0931,
+      "step": 358
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.3968471528185216e-05,
+      "loss": 0.0836,
+      "step": 359
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.3847196790102853e-05,
+      "loss": 0.1015,
+      "step": 360
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.372594923177362e-05,
+      "loss": 0.1123,
+      "step": 361
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.360473171186298e-05,
+      "loss": 0.1288,
+      "step": 362
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.3483547088328143e-05,
+      "loss": 0.1124,
+      "step": 363
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.3362398218350748e-05,
+      "loss": 0.1059,
+      "step": 364
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.3241287958269442e-05,
+      "loss": 0.1091,
+      "step": 365
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.3120219163512593e-05,
+      "loss": 0.0985,
+      "step": 366
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.2999194688530916e-05,
+      "loss": 0.1278,
+      "step": 367
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.2878217386730196e-05,
+      "loss": 0.1055,
+      "step": 368
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.275729011040403e-05,
+      "loss": 0.1438,
+      "step": 369
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.263641571066653e-05,
+      "loss": 0.1171,
+      "step": 370
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.251559703738515e-05,
+      "loss": 0.1256,
+      "step": 371
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.2394836939113485e-05,
+      "loss": 0.1213,
+      "step": 372
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.2274138263024074e-05,
+      "loss": 0.1141,
+      "step": 373
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.2153503854841323e-05,
+      "loss": 0.0943,
+      "step": 374
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.203293655877437e-05,
+      "loss": 0.1215,
+      "step": 375
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.191243921745006e-05,
+      "loss": 0.1263,
+      "step": 376
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.1792014671845902e-05,
+      "loss": 0.12,
+      "step": 377
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.1671665761223087e-05,
+      "loss": 0.1333,
+      "step": 378
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.155139532305956e-05,
+      "loss": 0.1214,
+      "step": 379
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.1431206192983117e-05,
+      "loss": 0.1127,
+      "step": 380
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.1311101204704525e-05,
+      "loss": 0.1074,
+      "step": 381
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.119108318995076e-05,
+      "loss": 0.1221,
+      "step": 382
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.10711549783982e-05,
+      "loss": 0.1177,
+      "step": 383
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.0951319397605918e-05,
+      "loss": 0.1174,
+      "step": 384
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.0831579272949027e-05,
+      "loss": 0.12,
+      "step": 385
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.071193742755208e-05,
+      "loss": 0.0972,
+      "step": 386
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.059239668222246e-05,
+      "loss": 0.1164,
+      "step": 387
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.0472959855383916e-05,
+      "loss": 0.1132,
+      "step": 388
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.0353629763010122e-05,
+      "loss": 0.0955,
+      "step": 389
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.0234409218558226e-05,
+      "loss": 0.1076,
+      "step": 390
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.0115301032902588e-05,
+      "loss": 0.1091,
+      "step": 391
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.999630801426843e-05,
+      "loss": 0.1199,
+      "step": 392
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.9877432968165728e-05,
+      "loss": 0.1271,
+      "step": 393
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.975867869732297e-05,
+      "loss": 0.1321,
+      "step": 394
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.964004800162111e-05,
+      "loss": 0.0906,
+      "step": 395
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.952154367802758e-05,
+      "loss": 0.1322,
+      "step": 396
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.940316852053033e-05,
+      "loss": 0.0955,
+      "step": 397
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.9284925320071898e-05,
+      "loss": 0.1225,
+      "step": 398
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.9166816864483728e-05,
+      "loss": 0.0912,
+      "step": 399
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.9048845938420327e-05,
+      "loss": 0.1114,
+      "step": 400
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.893101532329366e-05,
+      "loss": 0.1174,
+      "step": 401
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.8813327797207564e-05,
+      "loss": 0.109,
+      "step": 402
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.869578613489229e-05,
+      "loss": 0.1087,
+      "step": 403
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.857839310763899e-05,
+      "loss": 0.0838,
+      "step": 404
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.8461151483234456e-05,
+      "loss": 0.099,
+      "step": 405
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.8344064025895865e-05,
+      "loss": 0.0959,
+      "step": 406
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.8227133496205542e-05,
+      "loss": 0.1059,
+      "step": 407
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.8110362651045933e-05,
+      "loss": 0.1108,
+      "step": 408
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.7993754243534584e-05,
+      "loss": 0.097,
+      "step": 409
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.787731102295924e-05,
+      "loss": 0.1031,
+      "step": 410
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.7761035734713004e-05,
+      "loss": 0.1264,
+      "step": 411
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.7644931120229628e-05,
+      "loss": 0.1294,
+      "step": 412
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.752899991691888e-05,
+      "loss": 0.1205,
+      "step": 413
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.7413244858101986e-05,
+      "loss": 0.1169,
+      "step": 414
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.729766867294719e-05,
+      "loss": 0.1174,
+      "step": 415
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.718227408640544e-05,
+      "loss": 0.1262,
+      "step": 416
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.706706381914609e-05,
+      "loss": 0.1296,
+      "step": 417
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.695204058749279e-05,
+      "loss": 0.1035,
+      "step": 418
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.6837207103359427e-05,
+      "loss": 0.1095,
+      "step": 419
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.6722566074186214e-05,
+      "loss": 0.0955,
+      "step": 420
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.660812020287581e-05,
+      "loss": 0.1107,
+      "step": 421
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.649387218772962e-05,
+      "loss": 0.1071,
+      "step": 422
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.6379824722384203e-05,
+      "loss": 0.1265,
+      "step": 423
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.6265980495747694e-05,
+      "loss": 0.123,
+      "step": 424
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.6152342191936483e-05,
+      "loss": 0.1028,
+      "step": 425
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.603891249021187e-05,
+      "loss": 0.1132,
+      "step": 426
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.5925694064916963e-05,
+      "loss": 0.1174,
+      "step": 427
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.5812689585413542e-05,
+      "loss": 0.1007,
+      "step": 428
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.5699901716019185e-05,
+      "loss": 0.112,
+      "step": 429
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.558733311594444e-05,
+      "loss": 0.1171,
+      "step": 430
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.5474986439230116e-05,
+      "loss": 0.1075,
+      "step": 431
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.5362864334684696e-05,
+      "loss": 0.1193,
+      "step": 432
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.5250969445821928e-05,
+      "loss": 0.0886,
+      "step": 433
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5139304410798466e-05,
+      "loss": 0.1177,
+      "step": 434
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5027871862351671e-05,
+      "loss": 0.1221,
+      "step": 435
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.4916674427737548e-05,
+      "loss": 0.0932,
+      "step": 436
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.4805714728668807e-05,
+      "loss": 0.1025,
+      "step": 437
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.4694995381253035e-05,
+      "loss": 0.1175,
+      "step": 438
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.4584518995931026e-05,
+      "loss": 0.0964,
+      "step": 439
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4474288177415245e-05,
+      "loss": 0.0868,
+      "step": 440
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4364305524628397e-05,
+      "loss": 0.1059,
+      "step": 441
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4254573630642143e-05,
+      "loss": 0.0952,
+      "step": 442
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4145095082616012e-05,
+      "loss": 0.1004,
+      "step": 443
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4035872461736337e-05,
+      "loss": 0.114,
+      "step": 444
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.3926908343155462e-05,
+      "loss": 0.1222,
+      "step": 445
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.3818205295930963e-05,
+      "loss": 0.112,
+      "step": 446
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.3709765882965162e-05,
+      "loss": 0.1132,
+      "step": 447
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.3601592660944601e-05,
+      "loss": 0.0825,
+      "step": 448
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.3493688180279834e-05,
+      "loss": 0.1177,
+      "step": 449
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.3386054985045271e-05,
+      "loss": 0.1071,
+      "step": 450
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.32786956129192e-05,
+      "loss": 0.118,
+      "step": 451
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3171612595123955e-05,
+      "loss": 0.1109,
+      "step": 452
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3064808456366228e-05,
+      "loss": 0.1077,
+      "step": 453
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2958285714777579e-05,
+      "loss": 0.1028,
+      "step": 454
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2852046881855015e-05,
+      "loss": 0.1125,
+      "step": 455
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2746094462401803e-05,
+      "loss": 0.1333,
+      "step": 456
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2640430954468421e-05,
+      "loss": 0.0936,
+      "step": 457
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2535058849293646e-05,
+      "loss": 0.106,
+      "step": 458
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2429980631245817e-05,
+      "loss": 0.0832,
+      "step": 459
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2325198777764297e-05,
+      "loss": 0.1026,
+      "step": 460
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2220715759300996e-05,
+      "loss": 0.1141,
+      "step": 461
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2116534039262187e-05,
+      "loss": 0.1126,
+      "step": 462
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2012656073950385e-05,
+      "loss": 0.1186,
+      "step": 463
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.190908431250646e-05,
+      "loss": 0.1037,
+      "step": 464
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1805821196851886e-05,
+      "loss": 0.1098,
+      "step": 465
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1702869161631138e-05,
+      "loss": 0.1061,
+      "step": 466
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1600230634154372e-05,
+      "loss": 0.104,
+      "step": 467
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.149790803434009e-05,
+      "loss": 0.1127,
+      "step": 468
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.139590377465817e-05,
+      "loss": 0.1063,
+      "step": 469
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1294220260072912e-05,
+      "loss": 0.0888,
+      "step": 470
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1192859887986432e-05,
+      "loss": 0.1036,
+      "step": 471
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1091825048182047e-05,
+      "loss": 0.1079,
+      "step": 472
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.0991118122767974e-05,
+      "loss": 0.121,
+      "step": 473
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0890741486121176e-05,
+      "loss": 0.0883,
+      "step": 474
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.079069750483136e-05,
+      "loss": 0.1045,
+      "step": 475
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.069098853764515e-05,
+      "loss": 0.0918,
+      "step": 476
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.059161693541057e-05,
+      "loss": 0.0882,
+      "step": 477
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.0492585041021513e-05,
+      "loss": 0.1058,
+      "step": 478
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.0393895189362567e-05,
+      "loss": 0.0978,
+      "step": 479
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.029554970725393e-05,
+      "loss": 0.1099,
+      "step": 480
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.0197550913396603e-05,
+      "loss": 0.1193,
+      "step": 481
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.0099901118317629e-05,
+      "loss": 0.1021,
+      "step": 482
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.0002602624315702e-05,
+      "loss": 0.1176,
+      "step": 483
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.905657725406875e-06,
+      "loss": 0.102,
+      "step": 484
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.809068707270425e-06,
+      "loss": 0.1045,
+      "step": 485
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.712837847194997e-06,
+      "loss": 0.0926,
+      "step": 486
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.616967414024942e-06,
+      "loss": 0.0955,
+      "step": 487
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 9.521459668106736e-06,
+      "loss": 0.1278,
+      "step": 488
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 9.426316861235784e-06,
+      "loss": 0.1142,
+      "step": 489
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 9.331541236603267e-06,
+      "loss": 0.0999,
+      "step": 490
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 9.237135028743296e-06,
+      "loss": 0.1076,
+      "step": 491
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 9.14310046348019e-06,
+      "loss": 0.0926,
+      "step": 492
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 9.049439757876013e-06,
+      "loss": 0.0965,
+      "step": 493
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.956155120178315e-06,
+      "loss": 0.1235,
+      "step": 494
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.863248749768042e-06,
+      "loss": 0.1035,
+      "step": 495
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.770722837107709e-06,
+      "loss": 0.0934,
+      "step": 496
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.67857956368973e-06,
+      "loss": 0.0782,
+      "step": 497
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.586821101985013e-06,
+      "loss": 0.1026,
+      "step": 498
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.495449615391709e-06,
+      "loss": 0.1067,
+      "step": 499
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.404467258184223e-06,
+      "loss": 0.0963,
+      "step": 500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 8.313876175462415e-06,
+      "loss": 0.0956,
+      "step": 501
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 8.223678503101037e-06,
+      "loss": 0.086,
+      "step": 502
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 8.133876367699353e-06,
+      "loss": 0.0977,
+      "step": 503
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 8.044471886531035e-06,
+      "loss": 0.1167,
+      "step": 504
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.955467167494208e-06,
+      "loss": 0.11,
+      "step": 505
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.86686430906176e-06,
+      "loss": 0.1086,
+      "step": 506
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.77866540023189e-06,
+      "loss": 0.1028,
+      "step": 507
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.690872520478825e-06,
+      "loss": 0.0911,
+      "step": 508
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.603487739703813e-06,
+      "loss": 0.1183,
+      "step": 509
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.516513118186294e-06,
+      "loss": 0.1078,
+      "step": 510
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.42995070653538e-06,
+      "loss": 0.1059,
+      "step": 511
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.34380254564144e-06,
+      "loss": 0.1088,
+      "step": 512
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.258070666628031e-06,
+      "loss": 0.0993,
+      "step": 513
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.172757090803958e-06,
+      "loss": 0.0848,
+      "step": 514
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 7.087863829615698e-06,
+      "loss": 0.1038,
+      "step": 515
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 7.003392884599905e-06,
+      "loss": 0.0919,
+      "step": 516
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 6.919346247336231e-06,
+      "loss": 0.1145,
+      "step": 517
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.835725899400417e-06,
+      "loss": 0.097,
+      "step": 518
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.752533812317516e-06,
+      "loss": 0.1123,
+      "step": 519
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.669771947515421e-06,
+      "loss": 0.0854,
+      "step": 520
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.587442256278664e-06,
+      "loss": 0.1041,
+      "step": 521
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.5055466797023625e-06,
+      "loss": 0.0976,
+      "step": 522
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.424087148646468e-06,
+      "loss": 0.0858,
+      "step": 523
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.343065583690238e-06,
+      "loss": 0.1024,
+      "step": 524
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 6.262483895087002e-06,
+      "loss": 0.1019,
+      "step": 525
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 6.182343982719016e-06,
+      "loss": 0.1148,
+      "step": 526
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 6.10264773605278e-06,
+      "loss": 0.0975,
+      "step": 527
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 6.0233970340944465e-06,
+      "loss": 0.0922,
+      "step": 528
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.944593745345495e-06,
+      "loss": 0.1272,
+      "step": 529
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.8662397277587125e-06,
+      "loss": 0.1057,
+      "step": 530
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.788336828694377e-06,
+      "loss": 0.108,
+      "step": 531
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.710886884876693e-06,
+      "loss": 0.104,
+      "step": 532
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.633891722350504e-06,
+      "loss": 0.083,
+      "step": 533
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.557353156438216e-06,
+      "loss": 0.0925,
+      "step": 534
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.481272991697045e-06,
+      "loss": 0.0979,
+      "step": 535
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.405653021876406e-06,
+      "loss": 0.0912,
+      "step": 536
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.33049502987566e-06,
+      "loss": 0.0936,
+      "step": 537
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 5.255800787702095e-06,
+      "loss": 0.0883,
+      "step": 538
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 5.181572056429085e-06,
+      "loss": 0.1172,
+      "step": 539
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 5.107810586154637e-06,
+      "loss": 0.0856,
+      "step": 540
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 5.034518115960088e-06,
+      "loss": 0.0862,
+      "step": 541
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.961696373869132e-06,
+      "loss": 0.0853,
+      "step": 542
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.889347076807038e-06,
+      "loss": 0.1029,
+      "step": 543
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.817471930560205e-06,
+      "loss": 0.1053,
+      "step": 544
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.746072629735932e-06,
+      "loss": 0.0912,
+      "step": 545
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.67515085772246e-06,
+      "loss": 0.1101,
+      "step": 546
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.604708286649284e-06,
+      "loss": 0.1056,
+      "step": 547
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.534746577347748e-06,
+      "loss": 0.1,
+      "step": 548
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.465267379311855e-06,
+      "loss": 0.0986,
+      "step": 549
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.396272330659398e-06,
+      "loss": 0.0882,
+      "step": 550
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.3277630580933345e-06,
+      "loss": 0.0824,
+      "step": 551
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.25974117686343e-06,
+      "loss": 0.1173,
+      "step": 552
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.192208290728178e-06,
+      "loss": 0.1181,
+      "step": 553
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.125165991916985e-06,
+      "loss": 0.0811,
+      "step": 554
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.05861586109264e-06,
+      "loss": 0.1078,
+      "step": 555
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.992559467314036e-06,
+      "loss": 0.0869,
+      "step": 556
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.9269983679991765e-06,
+      "loss": 0.1021,
+      "step": 557
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.8619341088884595e-06,
+      "loss": 0.097,
+      "step": 558
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.7973682240082355e-06,
+      "loss": 0.0765,
+      "step": 559
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.7333022356346365e-06,
+      "loss": 0.0985,
+      "step": 560
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.669737654257682e-06,
+      "loss": 0.1096,
+      "step": 561
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.6066759785456845e-06,
+      "loss": 0.0999,
+      "step": 562
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.5441186953098894e-06,
+      "loss": 0.1117,
+      "step": 563
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.4820672794694283e-06,
+      "loss": 0.1047,
+      "step": 564
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.420523194016556e-06,
+      "loss": 0.0866,
+      "step": 565
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.3594878899821463e-06,
+      "loss": 0.0899,
+      "step": 566
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.2989628064014844e-06,
+      "loss": 0.0758,
+      "step": 567
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.238949370280331e-06,
+      "loss": 0.0988,
+      "step": 568
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.1794489965613074e-06,
+      "loss": 0.1039,
+      "step": 569
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.1204630880904944e-06,
+      "loss": 0.0993,
+      "step": 570
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.061993035584368e-06,
+      "loss": 0.0883,
+      "step": 571
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 3.004040217597037e-06,
+      "loss": 0.1288,
+      "step": 572
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.9466060004877174e-06,
+      "loss": 0.0823,
+      "step": 573
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.889691738388514e-06,
+      "loss": 0.0922,
+      "step": 574
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.833298773172502e-06,
+      "loss": 0.085,
+      "step": 575
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.7774284344221107e-06,
+      "loss": 0.1106,
+      "step": 576
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.722082039397722e-06,
+      "loss": 0.104,
+      "step": 577
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.6672608930066596e-06,
+      "loss": 0.0941,
+      "step": 578
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.6129662877724225e-06,
+      "loss": 0.0982,
+      "step": 579
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.559199503804183e-06,
+      "loss": 0.0915,
+      "step": 580
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.5059618087666188e-06,
+      "loss": 0.1199,
+      "step": 581
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.4532544578500405e-06,
+      "loss": 0.1053,
+      "step": 582
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.4010786937407687e-06,
+      "loss": 0.1014,
+      "step": 583
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.349435746591852e-06,
+      "loss": 0.1064,
+      "step": 584
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.298326833994069e-06,
+      "loss": 0.104,
+      "step": 585
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.247753160947219e-06,
+      "loss": 0.1083,
+      "step": 586
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.197715919831689e-06,
+      "loss": 0.105,
+      "step": 587
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.1482162903803725e-06,
+      "loss": 0.1065,
+      "step": 588
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.0992554396508324e-06,
+      "loss": 0.0975,
+      "step": 589
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.050834521997802e-06,
+      "loss": 0.1091,
+      "step": 590
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.0029546790459513e-06,
+      "loss": 0.0923,
+      "step": 591
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.955617039662977e-06,
+      "loss": 0.0832,
+      "step": 592
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.9088227199330095e-06,
+      "loss": 0.121,
+      "step": 593
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8625728231302569e-06,
+      "loss": 0.1117,
+      "step": 594
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8168684396930285e-06,
+      "loss": 0.0856,
+      "step": 595
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.771710647198002e-06,
+      "loss": 0.0983,
+      "step": 596
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.7271005103348337e-06,
+      "loss": 0.1149,
+      "step": 597
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.6830390808810465e-06,
+      "loss": 0.113,
+      "step": 598
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.6395273976772457e-06,
+      "loss": 0.1107,
+      "step": 599
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.5965664866026047e-06,
+      "loss": 0.0808,
+      "step": 600
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.5541573605506898e-06,
+      "loss": 0.0986,
+      "step": 601
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.512301019405582e-06,
+      "loss": 0.0926,
+      "step": 602
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.4709984500182987e-06,
+      "loss": 0.0827,
+      "step": 603
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.4302506261835242e-06,
+      "loss": 0.0906,
+      "step": 604
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.3900585086166513e-06,
+      "loss": 0.1106,
+      "step": 605
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.3504230449311456e-06,
+      "loss": 0.0952,
+      "step": 606
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.311345169616171e-06,
+      "loss": 0.0928,
+      "step": 607
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.2728258040145907e-06,
+      "loss": 0.0832,
+      "step": 608
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.2348658563012234e-06,
+      "loss": 0.1077,
+      "step": 609
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1974662214614379e-06,
+      "loss": 0.0862,
+      "step": 610
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1606277812700572e-06,
+      "loss": 0.0982,
+      "step": 611
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.1243514042705517e-06,
+      "loss": 0.0853,
+      "step": 612
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.088637945754592e-06,
+      "loss": 0.0878,
+      "step": 613
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.053488247741849e-06,
+      "loss": 0.1042,
+      "step": 614
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.0189031389601672e-06,
+      "loss": 0.0876,
+      "step": 615
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 9.848834348260089e-07,
+      "loss": 0.0917,
+      "step": 616
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 9.514299374252384e-07,
+      "loss": 0.0891,
+      "step": 617
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 9.185434354942124e-07,
+      "loss": 0.0963,
+      "step": 618
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.862247044011757e-07,
+      "loss": 0.1108,
+      "step": 619
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.544745061279891e-07,
+      "loss": 0.0963,
+      "step": 620
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.232935892521609e-07,
+      "loss": 0.0857,
+      "step": 621
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.926826889291833e-07,
+      "loss": 0.0937,
+      "step": 622
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.626425268752318e-07,
+      "loss": 0.086,
+      "step": 623
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.331738113501213e-07,
+      "loss": 0.1044,
+      "step": 624
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.042772371406131e-07,
+      "loss": 0.0957,
+      "step": 625
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.75953485544048e-07,
+      "loss": 0.0953,
+      "step": 626
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.482032243522618e-07,
+      "loss": 0.1037,
+      "step": 627
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.210271078358503e-07,
+      "loss": 0.0994,
+      "step": 628
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.944257767287547e-07,
+      "loss": 0.0905,
+      "step": 629
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.683998582131395e-07,
+      "loss": 0.098,
+      "step": 630
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.4294996590461e-07,
+      "loss": 0.1063,
+      "step": 631
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.18076699837744e-07,
+      "loss": 0.0814,
+      "step": 632
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.937806464519551e-07,
+      "loss": 0.115,
+      "step": 633
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.700623785776487e-07,
+      "loss": 0.0718,
+      "step": 634
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.4692245542272417e-07,
+      "loss": 0.0908,
+      "step": 635
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.2436142255939394e-07,
+      "loss": 0.0937,
+      "step": 636
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.02379811911327e-07,
+      "loss": 0.0825,
+      "step": 637
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.809781417410868e-07,
+      "loss": 0.0936,
+      "step": 638
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.601569166379243e-07,
+      "loss": 0.0978,
+      "step": 639
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.399166275058874e-07,
+      "loss": 0.097,
+      "step": 640
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.202577515522359e-07,
+      "loss": 0.0879,
+      "step": 641
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.011807522761922e-07,
+      "loss": 0.1055,
+      "step": 642
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.8268607945802493e-07,
+      "loss": 0.0835,
+      "step": 643
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.647741691484268e-07,
+      "loss": 0.0908,
+      "step": 644
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.4744544365824793e-07,
+      "loss": 0.0873,
+      "step": 645
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.3070031154852624e-07,
+      "loss": 0.0731,
+      "step": 646
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.145391676208669e-07,
+      "loss": 0.0942,
+      "step": 647
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.9896239290813078e-07,
+      "loss": 0.0919,
+      "step": 648
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.839703546654442e-07,
+      "loss": 0.0911,
+      "step": 649
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.6956340636155033e-07,
+      "loss": 0.0975,
+      "step": 650
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.557418876704658e-07,
+      "loss": 0.094,
+      "step": 651
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.4250612446347622e-07,
+      "loss": 0.1044,
+      "step": 652
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.2985642880145864e-07,
+      "loss": 0.1112,
+      "step": 653
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.1779309892751001e-07,
+      "loss": 0.076,
+      "step": 654
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.0631641925993307e-07,
+      "loss": 0.1133,
+      "step": 655
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 9.542666038551696e-08,
+      "loss": 0.0841,
+      "step": 656
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 8.512407905316432e-08,
+      "loss": 0.1208,
+      "step": 657
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.540891816783246e-08,
+      "loss": 0.0944,
+      "step": 658
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 6.628140678481553e-08,
+      "loss": 0.0934,
+      "step": 659
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.774176010432952e-08,
+      "loss": 0.1169,
+      "step": 660
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 4.979017946645792e-08,
+      "loss": 0.0911,
+      "step": 661
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 4.242685234638888e-08,
+      "loss": 0.0939,
+      "step": 662
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.565195234999652e-08,
+      "loss": 0.0955,
+      "step": 663
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.946563920975809e-08,
+      "loss": 0.1027,
+      "step": 664
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.3868058780979198e-08,
+      "loss": 0.1165,
+      "step": 665
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.8859343038354903e-08,
+      "loss": 0.0972,
+      "step": 666
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.4439610072863874e-08,
+      "loss": 0.0917,
+      "step": 667
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.0608964088978934e-08,
+      "loss": 0.0978,
+      "step": 668
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 7.367495402210711e-09,
+      "loss": 0.0905,
+      "step": 669
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 4.715280436981551e-09,
+      "loss": 0.0925,
+      "step": 670
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.6523817248214068e-09,
+      "loss": 0.078,
+      "step": 671
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.1788479028940203e-09,
+      "loss": 0.1115,
+      "step": 672
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.9471371284783834e-10,
+      "loss": 0.0883,
+      "step": 673
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.0878,
+      "step": 674
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.14739708602428436,
+      "eval_runtime": 29.6104,
+      "eval_samples_per_second": 10.132,
+      "eval_steps_per_second": 0.642,
+      "step": 674
+    },
+    {
+      "epoch": 2.0,
+      "step": 674,
+      "total_flos": 3.571400814654128e+18,
+      "train_loss": 0.179449640932971,
+      "train_runtime": 40133.1208,
+      "train_samples_per_second": 2.15,
+      "train_steps_per_second": 0.017
+    }
+  ],
+  "max_steps": 674,
+  "num_train_epochs": 2,
+  "total_flos": 3.571400814654128e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7de310354babff9d7c569929eea15b784d9ac5e2c1c8577970344c0da50a312
+size 3835