upload

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "eachadea/vicuna-7b-1.1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "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": 1,
+  "eos_token_id": 2,
+  "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 sha256:2ed3c9589a782c9b32ac7643133b647b42a5fe6afdc7550884bbe4b588205bbd
+size 9877991826

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3b3accf6016b2377c5732a99edf000c60f5547e50701a4e691f5347c97282ce
+size 9894803382

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db494b5ad0c303b26f2520c953594a3ab6855576009642d303fb3878e037ece
+size 7180992377

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": 2048,
+  "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 +1,4765 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9993674889310563,
+  "global_step": 790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.25e-07,
+      "loss": 1.4706,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.25e-06,
+      "loss": 1.4961,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.4356,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.5e-06,
+      "loss": 1.4061,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.125e-06,
+      "loss": 1.3136,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.3813,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 1.353,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-06,
+      "loss": 1.2831,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.625e-06,
+      "loss": 1.3101,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.25e-06,
+      "loss": 1.2627,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.875e-06,
+      "loss": 1.2808,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.247,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 1.2448,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.2534,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 1.2163,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 1.1997,
+      "step": 16
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0625e-05,
+      "loss": 1.2006,
+      "step": 17
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.125e-05,
+      "loss": 1.1916,
+      "step": 18
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1875e-05,
+      "loss": 1.1942,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.25e-05,
+      "loss": 1.1869,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3125e-05,
+      "loss": 1.1935,
+      "step": 21
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.375e-05,
+      "loss": 1.1551,
+      "step": 22
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.4375e-05,
+      "loss": 1.1497,
+      "step": 23
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.1367,
+      "step": 24
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.5625e-05,
+      "loss": 1.1488,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 1.1392,
+      "step": 26
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.6875e-05,
+      "loss": 1.136,
+      "step": 27
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.0938,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.8125e-05,
+      "loss": 1.1511,
+      "step": 29
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 1.1279,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9375e-05,
+      "loss": 1.1147,
+      "step": 31
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2e-05,
+      "loss": 1.0939,
+      "step": 32
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9999914112350643e-05,
+      "loss": 1.0959,
+      "step": 33
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999965645087791e-05,
+      "loss": 1.1042,
+      "step": 34
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9999227020007783e-05,
+      "loss": 1.0922,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9998625827116828e-05,
+      "loss": 1.1033,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9997852882532053e-05,
+      "loss": 1.1146,
+      "step": 37
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9996908199530737e-05,
+      "loss": 1.091,
+      "step": 38
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.99957917943402e-05,
+      "loss": 1.0667,
+      "step": 39
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9994503686137526e-05,
+      "loss": 1.0897,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.999304389704923e-05,
+      "loss": 1.0777,
+      "step": 41
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.999141245215089e-05,
+      "loss": 1.0726,
+      "step": 42
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9989609379466688e-05,
+      "loss": 1.0602,
+      "step": 43
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.998763470996897e-05,
+      "loss": 1.0607,
+      "step": 44
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.998548847757767e-05,
+      "loss": 1.0432,
+      "step": 45
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.998317071915977e-05,
+      "loss": 1.0637,
+      "step": 46
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9980681474528624e-05,
+      "loss": 1.0461,
+      "step": 47
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9978020786443314e-05,
+      "loss": 1.0603,
+      "step": 48
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9975188700607885e-05,
+      "loss": 1.0505,
+      "step": 49
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9972185265670573e-05,
+      "loss": 1.0306,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.996901053322298e-05,
+      "loss": 1.0448,
+      "step": 51
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9965664557799164e-05,
+      "loss": 1.0256,
+      "step": 52
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.996214739687471e-05,
+      "loss": 1.0354,
+      "step": 53
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9958459110865767e-05,
+      "loss": 1.065,
+      "step": 54
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.995459976312797e-05,
+      "loss": 1.0457,
+      "step": 55
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.995056941995538e-05,
+      "loss": 1.0467,
+      "step": 56
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9946368150579343e-05,
+      "loss": 1.0676,
+      "step": 57
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9941996027167286e-05,
+      "loss": 1.0477,
+      "step": 58
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9937453124821487e-05,
+      "loss": 1.0331,
+      "step": 59
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.993273952157779e-05,
+      "loss": 1.0291,
+      "step": 60
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9927855298404255e-05,
+      "loss": 1.0386,
+      "step": 61
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.992280053919977e-05,
+      "loss": 1.0411,
+      "step": 62
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9917575330792616e-05,
+      "loss": 1.015,
+      "step": 63
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9912179762938962e-05,
+      "loss": 1.0149,
+      "step": 64
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.990661392832134e-05,
+      "loss": 1.0227,
+      "step": 65
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9900877922547034e-05,
+      "loss": 1.0225,
+      "step": 66
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.989497184414646e-05,
+      "loss": 1.0574,
+      "step": 67
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.988889579457146e-05,
+      "loss": 1.0261,
+      "step": 68
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9882649878193544e-05,
+      "loss": 1.0438,
+      "step": 69
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.987623420230214e-05,
+      "loss": 1.0487,
+      "step": 70
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9869648877102707e-05,
+      "loss": 1.0169,
+      "step": 71
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9862894015714866e-05,
+      "loss": 1.0207,
+      "step": 72
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9855969734170448e-05,
+      "loss": 1.0012,
+      "step": 73
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.984887615141151e-05,
+      "loss": 1.0013,
+      "step": 74
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9841613389288278e-05,
+      "loss": 1.0199,
+      "step": 75
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9834181572557066e-05,
+      "loss": 0.9873,
+      "step": 76
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9826580828878134e-05,
+      "loss": 1.0116,
+      "step": 77
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9818811288813475e-05,
+      "loss": 0.9813,
+      "step": 78
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9810873085824604e-05,
+      "loss": 0.9811,
+      "step": 79
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9802766356270226e-05,
+      "loss": 1.0188,
+      "step": 80
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9794491239403946e-05,
+      "loss": 1.0195,
+      "step": 81
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9786047877371823e-05,
+      "loss": 1.0168,
+      "step": 82
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.977743641520996e-05,
+      "loss": 0.9916,
+      "step": 83
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.976865700084201e-05,
+      "loss": 1.025,
+      "step": 84
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9759709785076622e-05,
+      "loss": 1.0009,
+      "step": 85
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.975059492160486e-05,
+      "loss": 1.0116,
+      "step": 86
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9741312566997573e-05,
+      "loss": 1.0108,
+      "step": 87
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9731862880702676e-05,
+      "loss": 1.0065,
+      "step": 88
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.972224602504244e-05,
+      "loss": 1.0041,
+      "step": 89
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9712462165210687e-05,
+      "loss": 1.0068,
+      "step": 90
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9702511469269964e-05,
+      "loss": 1.0045,
+      "step": 91
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.969239410814865e-05,
+      "loss": 1.0246,
+      "step": 92
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.968211025563802e-05,
+      "loss": 1.0156,
+      "step": 93
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.967166008838925e-05,
+      "loss": 0.978,
+      "step": 94
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9661043785910404e-05,
+      "loss": 0.9861,
+      "step": 95
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9650261530563336e-05,
+      "loss": 0.9811,
+      "step": 96
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.963931350756056e-05,
+      "loss": 1.0103,
+      "step": 97
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9628199904962063e-05,
+      "loss": 1.0095,
+      "step": 98
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9616920913672092e-05,
+      "loss": 0.9938,
+      "step": 99
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9605476727435854e-05,
+      "loss": 0.9795,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9593867542836198e-05,
+      "loss": 0.9685,
+      "step": 101
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9582093559290242e-05,
+      "loss": 0.9953,
+      "step": 102
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9570154979045938e-05,
+      "loss": 1.0191,
+      "step": 103
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9558052007178608e-05,
+      "loss": 1.0097,
+      "step": 104
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.954578485158741e-05,
+      "loss": 0.9908,
+      "step": 105
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9533353722991775e-05,
+      "loss": 0.9716,
+      "step": 106
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.952075883492779e-05,
+      "loss": 0.9779,
+      "step": 107
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9508000403744516e-05,
+      "loss": 0.9853,
+      "step": 108
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9495078648600286e-05,
+      "loss": 0.995,
+      "step": 109
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.948199379145894e-05,
+      "loss": 0.976,
+      "step": 110
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9468746057086e-05,
+      "loss": 0.9898,
+      "step": 111
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9455335673044817e-05,
+      "loss": 0.9726,
+      "step": 112
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9441762869692664e-05,
+      "loss": 0.9815,
+      "step": 113
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9428027880176775e-05,
+      "loss": 0.9554,
+      "step": 114
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9414130940430347e-05,
+      "loss": 0.9766,
+      "step": 115
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9400072289168474e-05,
+      "loss": 0.9792,
+      "step": 116
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9385852167884057e-05,
+      "loss": 0.9699,
+      "step": 117
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.937147082084366e-05,
+      "loss": 0.9519,
+      "step": 118
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9356928495083295e-05,
+      "loss": 0.9658,
+      "step": 119
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.93422254404042e-05,
+      "loss": 0.9649,
+      "step": 120
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9327361909368535e-05,
+      "loss": 0.9557,
+      "step": 121
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.931233815729505e-05,
+      "loss": 1.0064,
+      "step": 122
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9297154442254692e-05,
+      "loss": 0.9695,
+      "step": 123
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9281811025066184e-05,
+      "loss": 0.9815,
+      "step": 124
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9266308169291533e-05,
+      "loss": 1.0004,
+      "step": 125
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9250646141231503e-05,
+      "loss": 0.9569,
+      "step": 126
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9234825209921045e-05,
+      "loss": 0.9619,
+      "step": 127
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.921884564712469e-05,
+      "loss": 0.9828,
+      "step": 128
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.920270772733185e-05,
+      "loss": 0.9856,
+      "step": 129
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9186411727752124e-05,
+      "loss": 0.9548,
+      "step": 130
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9169957928310533e-05,
+      "loss": 0.974,
+      "step": 131
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9153346611642706e-05,
+      "loss": 0.9748,
+      "step": 132
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9136578063090035e-05,
+      "loss": 0.9616,
+      "step": 133
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.911965257069476e-05,
+      "loss": 0.9627,
+      "step": 134
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9102570425195032e-05,
+      "loss": 0.976,
+      "step": 135
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.908533192001992e-05,
+      "loss": 0.9474,
+      "step": 136
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9067937351284355e-05,
+      "loss": 0.9484,
+      "step": 137
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9050387017784067e-05,
+      "loss": 0.9563,
+      "step": 138
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.903268122099043e-05,
+      "loss": 0.9419,
+      "step": 139
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9014820265045304e-05,
+      "loss": 0.9765,
+      "step": 140
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8996804456755783e-05,
+      "loss": 0.9695,
+      "step": 141
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8978634105588963e-05,
+      "loss": 0.9607,
+      "step": 142
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8960309523666583e-05,
+      "loss": 0.9382,
+      "step": 143
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8941831025759705e-05,
+      "loss": 0.9672,
+      "step": 144
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8923198929283275e-05,
+      "loss": 0.9347,
+      "step": 145
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8904413554290687e-05,
+      "loss": 0.9662,
+      "step": 146
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.888547522346828e-05,
+      "loss": 0.9695,
+      "step": 147
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.88663842621298e-05,
+      "loss": 0.9532,
+      "step": 148
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8847140998210806e-05,
+      "loss": 0.9486,
+      "step": 149
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8827745762263038e-05,
+      "loss": 0.9802,
+      "step": 150
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8808198887448737e-05,
+      "loss": 0.9734,
+      "step": 151
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8788500709534934e-05,
+      "loss": 0.9552,
+      "step": 152
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8768651566887667e-05,
+      "loss": 0.9708,
+      "step": 153
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8748651800466174e-05,
+      "loss": 0.9705,
+      "step": 154
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8728501753817044e-05,
+      "loss": 0.9525,
+      "step": 155
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8708201773068303e-05,
+      "loss": 0.9753,
+      "step": 156
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.868775220692348e-05,
+      "loss": 0.939,
+      "step": 157
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8667153406655606e-05,
+      "loss": 0.9641,
+      "step": 158
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.864640572610118e-05,
+      "loss": 0.9256,
+      "step": 159
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8625509521654122e-05,
+      "loss": 0.9258,
+      "step": 160
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8604465152259595e-05,
+      "loss": 0.9847,
+      "step": 161
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8583272979407885e-05,
+      "loss": 0.9285,
+      "step": 162
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8561933367128175e-05,
+      "loss": 0.9397,
+      "step": 163
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8540446681982295e-05,
+      "loss": 0.9488,
+      "step": 164
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.851881329305842e-05,
+      "loss": 0.9441,
+      "step": 165
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.849703357196473e-05,
+      "loss": 0.9147,
+      "step": 166
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8475107892823038e-05,
+      "loss": 0.9195,
+      "step": 167
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8453036632262352e-05,
+      "loss": 0.9266,
+      "step": 168
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8430820169412415e-05,
+      "loss": 0.9241,
+      "step": 169
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.840845888589717e-05,
+      "loss": 0.9499,
+      "step": 170
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8385953165828242e-05,
+      "loss": 0.9473,
+      "step": 171
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8363303395798305e-05,
+      "loss": 0.9455,
+      "step": 172
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.834050996487446e-05,
+      "loss": 0.9623,
+      "step": 173
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8317573264591553e-05,
+      "loss": 0.9292,
+      "step": 174
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8294493688945435e-05,
+      "loss": 0.9203,
+      "step": 175
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.82712716343862e-05,
+      "loss": 0.9387,
+      "step": 176
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8247907499811395e-05,
+      "loss": 0.9346,
+      "step": 177
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.822440168655913e-05,
+      "loss": 0.967,
+      "step": 178
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8200754598401223e-05,
+      "loss": 0.9292,
+      "step": 179
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8176966641536228e-05,
+      "loss": 0.9368,
+      "step": 180
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8153038224582493e-05,
+      "loss": 0.935,
+      "step": 181
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.812896975857111e-05,
+      "loss": 0.908,
+      "step": 182
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8104761656938872e-05,
+      "loss": 0.9569,
+      "step": 183
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8080414335521174e-05,
+      "loss": 0.9307,
+      "step": 184
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.805592821254485e-05,
+      "loss": 0.9604,
+      "step": 185
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.803130370862101e-05,
+      "loss": 0.9504,
+      "step": 186
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.800654124673781e-05,
+      "loss": 0.9181,
+      "step": 187
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.798164125225318e-05,
+      "loss": 0.9367,
+      "step": 188
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.795660415288751e-05,
+      "loss": 0.923,
+      "step": 189
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.793143037871633e-05,
+      "loss": 0.9509,
+      "step": 190
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7906120362162895e-05,
+      "loss": 0.9353,
+      "step": 191
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.788067453799077e-05,
+      "loss": 0.8999,
+      "step": 192
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.785509334329636e-05,
+      "loss": 0.944,
+      "step": 193
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.78293772175014e-05,
+      "loss": 0.9048,
+      "step": 194
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7803526602345415e-05,
+      "loss": 0.9412,
+      "step": 195
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7777541941878116e-05,
+      "loss": 0.96,
+      "step": 196
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.775142368245178e-05,
+      "loss": 0.9282,
+      "step": 197
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.772517227271359e-05,
+      "loss": 0.9237,
+      "step": 198
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7698788163597923e-05,
+      "loss": 0.9288,
+      "step": 199
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7672271808318603e-05,
+      "loss": 0.9451,
+      "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7645623662361112e-05,
+      "loss": 0.9433,
+      "step": 201
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7618844183474775e-05,
+      "loss": 0.9517,
+      "step": 202
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7591933831664887e-05,
+      "loss": 0.9347,
+      "step": 203
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7564893069184824e-05,
+      "loss": 0.9193,
+      "step": 204
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.753772236052809e-05,
+      "loss": 0.945,
+      "step": 205
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7510422172420344e-05,
+      "loss": 0.9152,
+      "step": 206
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7482992973811384e-05,
+      "loss": 0.9065,
+      "step": 207
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.745543523586709e-05,
+      "loss": 0.9389,
+      "step": 208
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7427749431961324e-05,
+      "loss": 0.9464,
+      "step": 209
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7399936037667807e-05,
+      "loss": 0.9359,
+      "step": 210
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.737199553075196e-05,
+      "loss": 0.9283,
+      "step": 211
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7343928391162673e-05,
+      "loss": 0.9618,
+      "step": 212
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7315735101024068e-05,
+      "loss": 0.8981,
+      "step": 213
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7287416144627237e-05,
+      "loss": 0.9407,
+      "step": 214
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.725897200842189e-05,
+      "loss": 0.9403,
+      "step": 215
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7230403181008032e-05,
+      "loss": 0.9103,
+      "step": 216
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7201710153127554e-05,
+      "loss": 0.9198,
+      "step": 217
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.7172893417655792e-05,
+      "loss": 0.9324,
+      "step": 218
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.714395346959308e-05,
+      "loss": 0.9175,
+      "step": 219
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.7114890806056245e-05,
+      "loss": 0.9181,
+      "step": 220
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.708570592627006e-05,
+      "loss": 0.8913,
+      "step": 221
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.705639933155866e-05,
+      "loss": 0.929,
+      "step": 222
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.702697152533695e-05,
+      "loss": 0.9049,
+      "step": 223
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6997423013101967e-05,
+      "loss": 0.9145,
+      "step": 224
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6967754302424153e-05,
+      "loss": 0.9276,
+      "step": 225
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6937965902938667e-05,
+      "loss": 0.8991,
+      "step": 226
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6908058326336634e-05,
+      "loss": 0.9193,
+      "step": 227
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.687803208635635e-05,
+      "loss": 0.9094,
+      "step": 228
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6847887698774446e-05,
+      "loss": 0.9389,
+      "step": 229
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6817625681397035e-05,
+      "loss": 0.9386,
+      "step": 230
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.678724655405083e-05,
+      "loss": 0.8991,
+      "step": 231
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6756750838574197e-05,
+      "loss": 0.906,
+      "step": 232
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6726139058808206e-05,
+      "loss": 0.9433,
+      "step": 233
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.66954117405876e-05,
+      "loss": 0.9031,
+      "step": 234
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6664569411731828e-05,
+      "loss": 0.9276,
+      "step": 235
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.66336126020359e-05,
+      "loss": 0.9083,
+      "step": 236
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6602541843261345e-05,
+      "loss": 0.9047,
+      "step": 237
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6571357669127047e-05,
+      "loss": 0.9254,
+      "step": 238
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6540060615300096e-05,
+      "loss": 0.9163,
+      "step": 239
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.650865121938656e-05,
+      "loss": 0.9153,
+      "step": 240
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6477130020922277e-05,
+      "loss": 0.9229,
+      "step": 241
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.644549756136358e-05,
+      "loss": 0.8953,
+      "step": 242
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6413754384077992e-05,
+      "loss": 0.906,
+      "step": 243
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6381901034334876e-05,
+      "loss": 0.8999,
+      "step": 244
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6349938059296106e-05,
+      "loss": 0.9403,
+      "step": 245
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.631786600800664e-05,
+      "loss": 0.9033,
+      "step": 246
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6285685431385096e-05,
+      "loss": 0.9203,
+      "step": 247
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6253396882214293e-05,
+      "loss": 0.9212,
+      "step": 248
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6221000915131746e-05,
+      "loss": 0.9282,
+      "step": 249
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6188498086620148e-05,
+      "loss": 0.9073,
+      "step": 250
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.615588895499781e-05,
+      "loss": 0.9156,
+      "step": 251
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6123174080409055e-05,
+      "loss": 0.8987,
+      "step": 252
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.609035402481463e-05,
+      "loss": 0.9173,
+      "step": 253
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6057429351982016e-05,
+      "loss": 0.91,
+      "step": 254
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.602440062747576e-05,
+      "loss": 0.9052,
+      "step": 255
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5991268418647772e-05,
+      "loss": 0.919,
+      "step": 256
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.595803329462755e-05,
+      "loss": 0.9068,
+      "step": 257
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5924695826312434e-05,
+      "loss": 0.9054,
+      "step": 258
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5891256586357783e-05,
+      "loss": 0.917,
+      "step": 259
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.585771614916714e-05,
+      "loss": 0.8738,
+      "step": 260
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5824075090882364e-05,
+      "loss": 0.9232,
+      "step": 261
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5790333989373738e-05,
+      "loss": 0.915,
+      "step": 262
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5756493424230046e-05,
+      "loss": 0.9317,
+      "step": 263
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5722553976748605e-05,
+      "loss": 0.8937,
+      "step": 264
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5688516229925282e-05,
+      "loss": 0.9021,
+      "step": 265
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5654380768444498e-05,
+      "loss": 0.9139,
+      "step": 266
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.562014817866916e-05,
+      "loss": 0.8888,
+      "step": 267
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.55858190486306e-05,
+      "loss": 0.8966,
+      "step": 268
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.555139396801847e-05,
+      "loss": 0.9331,
+      "step": 269
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.551687352817063e-05,
+      "loss": 0.8848,
+      "step": 270
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.548225832206296e-05,
+      "loss": 0.9018,
+      "step": 271
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5447548944299203e-05,
+      "loss": 0.91,
+      "step": 272
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5412745991100724e-05,
+      "loss": 0.8796,
+      "step": 273
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.53778500602963e-05,
+      "loss": 0.8965,
+      "step": 274
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5342861751311816e-05,
+      "loss": 0.9017,
+      "step": 275
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5307781665160005e-05,
+      "loss": 0.9004,
+      "step": 276
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.527261040443008e-05,
+      "loss": 0.8986,
+      "step": 277
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.523734857327744e-05,
+      "loss": 0.9089,
+      "step": 278
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5201996777413231e-05,
+      "loss": 0.9409,
+      "step": 279
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5166555624093986e-05,
+      "loss": 0.8904,
+      "step": 280
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.5131025722111176e-05,
+      "loss": 0.9151,
+      "step": 281
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.5095407681780753e-05,
+      "loss": 0.9176,
+      "step": 282
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.505970211493267e-05,
+      "loss": 0.8897,
+      "step": 283
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.5023909634900362e-05,
+      "loss": 0.9039,
+      "step": 284
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4988030856510231e-05,
+      "loss": 0.9399,
+      "step": 285
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4952066396071064e-05,
+      "loss": 0.9093,
+      "step": 286
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.491601687136345e-05,
+      "loss": 0.9042,
+      "step": 287
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4879882901629181e-05,
+      "loss": 0.9184,
+      "step": 288
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4843665107560596e-05,
+      "loss": 0.8836,
+      "step": 289
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4807364111289941e-05,
+      "loss": 0.8907,
+      "step": 290
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.477098053637866e-05,
+      "loss": 0.91,
+      "step": 291
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4734515007806698e-05,
+      "loss": 0.9095,
+      "step": 292
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4697968151961763e-05,
+      "loss": 0.8937,
+      "step": 293
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4661340596628564e-05,
+      "loss": 0.8775,
+      "step": 294
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4624632970978021e-05,
+      "loss": 0.8971,
+      "step": 295
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4587845905556477e-05,
+      "loss": 0.9108,
+      "step": 296
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4550980032274842e-05,
+      "loss": 0.8934,
+      "step": 297
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4514035984397759e-05,
+      "loss": 0.9082,
+      "step": 298
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4477014396532711e-05,
+      "loss": 0.9129,
+      "step": 299
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4439915904619136e-05,
+      "loss": 0.9151,
+      "step": 300
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4402741145917475e-05,
+      "loss": 0.8944,
+      "step": 301
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4365490758998268e-05,
+      "loss": 0.9149,
+      "step": 302
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4328165383731145e-05,
+      "loss": 0.8942,
+      "step": 303
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.429076566127385e-05,
+      "loss": 0.893,
+      "step": 304
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4253292234061237e-05,
+      "loss": 0.925,
+      "step": 305
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4215745745794224e-05,
+      "loss": 0.9179,
+      "step": 306
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4178126841428732e-05,
+      "loss": 0.9189,
+      "step": 307
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4140436167164611e-05,
+      "loss": 0.8805,
+      "step": 308
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4102674370434549e-05,
+      "loss": 0.896,
+      "step": 309
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4064842099892934e-05,
+      "loss": 0.8998,
+      "step": 310
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4026940005404726e-05,
+      "loss": 0.907,
+      "step": 311
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3988968738034285e-05,
+      "loss": 0.9157,
+      "step": 312
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3950928950034189e-05,
+      "loss": 0.8885,
+      "step": 313
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3912821294834033e-05,
+      "loss": 0.8706,
+      "step": 314
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3874646427029204e-05,
+      "loss": 0.92,
+      "step": 315
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3836405002369631e-05,
+      "loss": 0.9096,
+      "step": 316
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3798097677748535e-05,
+      "loss": 0.8924,
+      "step": 317
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3759725111191118e-05,
+      "loss": 0.8932,
+      "step": 318
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3721287961843298e-05,
+      "loss": 0.8898,
+      "step": 319
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3682786889960354e-05,
+      "loss": 0.876,
+      "step": 320
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3644222556895591e-05,
+      "loss": 0.9011,
+      "step": 321
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3605595625089006e-05,
+      "loss": 0.9199,
+      "step": 322
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3566906758055862e-05,
+      "loss": 0.8982,
+      "step": 323
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3528156620375335e-05,
+      "loss": 0.8794,
+      "step": 324
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3489345877679068e-05,
+      "loss": 0.8905,
+      "step": 325
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3450475196639753e-05,
+      "loss": 0.8824,
+      "step": 326
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.341154524495968e-05,
+      "loss": 0.891,
+      "step": 327
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3372556691359251e-05,
+      "loss": 0.8762,
+      "step": 328
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3333510205565516e-05,
+      "loss": 0.8887,
+      "step": 329
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3294406458300646e-05,
+      "loss": 0.9018,
+      "step": 330
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.325524612127043e-05,
+      "loss": 0.8953,
+      "step": 331
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3216029867152724e-05,
+      "loss": 0.9105,
+      "step": 332
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3176758369585909e-05,
+      "loss": 0.8775,
+      "step": 333
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3137432303157306e-05,
+      "loss": 0.8913,
+      "step": 334
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3098052343391596e-05,
+      "loss": 0.907,
+      "step": 335
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.3058619166739212e-05,
+      "loss": 0.8817,
+      "step": 336
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.3019133450564725e-05,
+      "loss": 0.883,
+      "step": 337
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2979595873135208e-05,
+      "loss": 0.8846,
+      "step": 338
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2940007113608572e-05,
+      "loss": 0.8963,
+      "step": 339
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.290036785202192e-05,
+      "loss": 0.8842,
+      "step": 340
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2860678769279855e-05,
+      "loss": 0.912,
+      "step": 341
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2820940547142773e-05,
+      "loss": 0.8968,
+      "step": 342
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.278115386821518e-05,
+      "loss": 0.9003,
+      "step": 343
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2741319415933934e-05,
+      "loss": 0.8967,
+      "step": 344
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2701437874556537e-05,
+      "loss": 0.885,
+      "step": 345
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2661509929149351e-05,
+      "loss": 0.8893,
+      "step": 346
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2621536265575855e-05,
+      "loss": 0.8762,
+      "step": 347
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.258151757048485e-05,
+      "loss": 0.9144,
+      "step": 348
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2541454531298661e-05,
+      "loss": 0.8839,
+      "step": 349
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2501347836201343e-05,
+      "loss": 0.8945,
+      "step": 350
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2461198174126851e-05,
+      "loss": 0.8976,
+      "step": 351
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2421006234747202e-05,
+      "loss": 0.8802,
+      "step": 352
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.238077270846064e-05,
+      "loss": 0.8809,
+      "step": 353
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2340498286379757e-05,
+      "loss": 0.8865,
+      "step": 354
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2300183660319647e-05,
+      "loss": 0.9058,
+      "step": 355
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2259829522786003e-05,
+      "loss": 0.8816,
+      "step": 356
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2219436566963221e-05,
+      "loss": 0.8943,
+      "step": 357
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2179005486702518e-05,
+      "loss": 0.8743,
+      "step": 358
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2138536976509974e-05,
+      "loss": 0.8897,
+      "step": 359
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.2098031731534636e-05,
+      "loss": 0.8818,
+      "step": 360
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.2057490447556556e-05,
+      "loss": 0.8753,
+      "step": 361
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.2016913820974855e-05,
+      "loss": 0.8811,
+      "step": 362
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1976302548795746e-05,
+      "loss": 0.8934,
+      "step": 363
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1935657328620566e-05,
+      "loss": 0.863,
+      "step": 364
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1894978858633807e-05,
+      "loss": 0.8772,
+      "step": 365
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1854267837591095e-05,
+      "loss": 0.8851,
+      "step": 366
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1813524964807216e-05,
+      "loss": 0.872,
+      "step": 367
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1772750940144079e-05,
+      "loss": 0.8881,
+      "step": 368
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1731946463998712e-05,
+      "loss": 0.8906,
+      "step": 369
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1691112237291225e-05,
+      "loss": 0.8896,
+      "step": 370
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1650248961452765e-05,
+      "loss": 0.8831,
+      "step": 371
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1609357338413476e-05,
+      "loss": 0.8707,
+      "step": 372
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1568438070590428e-05,
+      "loss": 0.8799,
+      "step": 373
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1527491860875574e-05,
+      "loss": 0.8755,
+      "step": 374
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1486519412623653e-05,
+      "loss": 0.8774,
+      "step": 375
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1445521429640113e-05,
+      "loss": 0.8707,
+      "step": 376
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1404498616169039e-05,
+      "loss": 0.8799,
+      "step": 377
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.136345167688103e-05,
+      "loss": 0.8746,
+      "step": 378
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1322381316861114e-05,
+      "loss": 0.8743,
+      "step": 379
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1281288241596624e-05,
+      "loss": 0.8907,
+      "step": 380
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1240173156965089e-05,
+      "loss": 0.8848,
+      "step": 381
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1199036769222104e-05,
+      "loss": 0.8921,
+      "step": 382
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1157879784989203e-05,
+      "loss": 0.8826,
+      "step": 383
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.1116702911241704e-05,
+      "loss": 0.8808,
+      "step": 384
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.107550685529659e-05,
+      "loss": 0.9054,
+      "step": 385
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.1034292324800342e-05,
+      "loss": 0.8663,
+      "step": 386
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.099306002771679e-05,
+      "loss": 0.891,
+      "step": 387
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0951810672314946e-05,
+      "loss": 0.8589,
+      "step": 388
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.091054496715685e-05,
+      "loss": 0.8628,
+      "step": 389
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0869263621085375e-05,
+      "loss": 0.8802,
+      "step": 390
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0827967343212087e-05,
+      "loss": 0.9108,
+      "step": 391
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0786656842905028e-05,
+      "loss": 0.9063,
+      "step": 392
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.074533282977655e-05,
+      "loss": 0.8907,
+      "step": 393
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0703996013671126e-05,
+      "loss": 0.8816,
+      "step": 394
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0662647104653145e-05,
+      "loss": 0.8967,
+      "step": 395
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0621286812994733e-05,
+      "loss": 0.8887,
+      "step": 396
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.057991584916353e-05,
+      "loss": 0.9037,
+      "step": 397
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0538534923810506e-05,
+      "loss": 0.8606,
+      "step": 398
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.049714474775774e-05,
+      "loss": 0.8656,
+      "step": 399
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0455746031986215e-05,
+      "loss": 0.8822,
+      "step": 400
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.041433948762362e-05,
+      "loss": 0.8783,
+      "step": 401
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0372925825932095e-05,
+      "loss": 0.905,
+      "step": 402
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0331505758296054e-05,
+      "loss": 0.8988,
+      "step": 403
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.029007999620995e-05,
+      "loss": 0.8752,
+      "step": 404
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0248649251266043e-05,
+      "loss": 0.8709,
+      "step": 405
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0207214235142197e-05,
+      "loss": 0.8838,
+      "step": 406
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0165775659589638e-05,
+      "loss": 0.8821,
+      "step": 407
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.0124334236420735e-05,
+      "loss": 0.8806,
+      "step": 408
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.0082890677496766e-05,
+      "loss": 0.8709,
+      "step": 409
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.0041445694715717e-05,
+      "loss": 0.8995,
+      "step": 410
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.8796,
+      "step": 411
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.95855430528429e-06,
+      "loss": 0.8517,
+      "step": 412
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.917109322503234e-06,
+      "loss": 0.8865,
+      "step": 413
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.87566576357927e-06,
+      "loss": 0.8784,
+      "step": 414
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.834224340410367e-06,
+      "loss": 0.8748,
+      "step": 415
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.792785764857803e-06,
+      "loss": 0.8717,
+      "step": 416
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.751350748733958e-06,
+      "loss": 0.8667,
+      "step": 417
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.709920003790054e-06,
+      "loss": 0.8941,
+      "step": 418
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.668494241703946e-06,
+      "loss": 0.8664,
+      "step": 419
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.627074174067909e-06,
+      "loss": 0.887,
+      "step": 420
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.585660512376385e-06,
+      "loss": 0.9037,
+      "step": 421
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.544253968013785e-06,
+      "loss": 0.8717,
+      "step": 422
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.502855252242265e-06,
+      "loss": 0.8549,
+      "step": 423
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.461465076189499e-06,
+      "loss": 0.8705,
+      "step": 424
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.420084150836472e-06,
+      "loss": 0.8821,
+      "step": 425
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.37871318700527e-06,
+      "loss": 0.8682,
+      "step": 426
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.337352895346858e-06,
+      "loss": 0.8666,
+      "step": 427
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.296003986328876e-06,
+      "loss": 0.871,
+      "step": 428
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.254667170223454e-06,
+      "loss": 0.8787,
+      "step": 429
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.213343157094975e-06,
+      "loss": 0.8943,
+      "step": 430
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.172032656787913e-06,
+      "loss": 0.8697,
+      "step": 431
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.130736378914626e-06,
+      "loss": 0.8811,
+      "step": 432
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.089455032843156e-06,
+      "loss": 0.89,
+      "step": 433
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.048189327685056e-06,
+      "loss": 0.858,
+      "step": 434
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.006939972283213e-06,
+      "loss": 0.8751,
+      "step": 435
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.965707675199661e-06,
+      "loss": 0.8815,
+      "step": 436
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.92449314470341e-06,
+      "loss": 0.8948,
+      "step": 437
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.883297088758298e-06,
+      "loss": 0.8701,
+      "step": 438
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.842120215010804e-06,
+      "loss": 0.8785,
+      "step": 439
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.800963230777895e-06,
+      "loss": 0.8837,
+      "step": 440
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.759826843034916e-06,
+      "loss": 0.8375,
+      "step": 441
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.718711758403382e-06,
+      "loss": 0.879,
+      "step": 442
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.677618683138888e-06,
+      "loss": 0.8892,
+      "step": 443
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.636548323118974e-06,
+      "loss": 0.8715,
+      "step": 444
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.595501383830964e-06,
+      "loss": 0.8806,
+      "step": 445
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.554478570359888e-06,
+      "loss": 0.8707,
+      "step": 446
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.51348058737635e-06,
+      "loss": 0.8647,
+      "step": 447
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.472508139124427e-06,
+      "loss": 0.8591,
+      "step": 448
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.431561929409572e-06,
+      "loss": 0.8762,
+      "step": 449
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.390642661586527e-06,
+      "loss": 0.8617,
+      "step": 450
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.34975103854724e-06,
+      "loss": 0.8602,
+      "step": 451
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.308887762708776e-06,
+      "loss": 0.8611,
+      "step": 452
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.268053536001291e-06,
+      "loss": 0.8763,
+      "step": 453
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.227249059855926e-06,
+      "loss": 0.8944,
+      "step": 454
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.186475035192788e-06,
+      "loss": 0.8466,
+      "step": 455
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.145732162408906e-06,
+      "loss": 0.8645,
+      "step": 456
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.105021141366196e-06,
+      "loss": 0.8578,
+      "step": 457
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.064342671379436e-06,
+      "loss": 0.867,
+      "step": 458
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.023697451204257e-06,
+      "loss": 0.8888,
+      "step": 459
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.983086179025148e-06,
+      "loss": 0.8779,
+      "step": 460
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.942509552443445e-06,
+      "loss": 0.8693,
+      "step": 461
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.901968268465367e-06,
+      "loss": 0.8792,
+      "step": 462
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.86146302349003e-06,
+      "loss": 0.854,
+      "step": 463
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.820994513297484e-06,
+      "loss": 0.8493,
+      "step": 464
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.78056343303678e-06,
+      "loss": 0.8713,
+      "step": 465
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.740170477214004e-06,
+      "loss": 0.8658,
+      "step": 466
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.699816339680357e-06,
+      "loss": 0.8607,
+      "step": 467
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.659501713620247e-06,
+      "loss": 0.8655,
+      "step": 468
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.619227291539365e-06,
+      "loss": 0.8668,
+      "step": 469
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.578993765252799e-06,
+      "loss": 0.8502,
+      "step": 470
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.538801825873151e-06,
+      "loss": 0.8296,
+      "step": 471
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.498652163798659e-06,
+      "loss": 0.8555,
+      "step": 472
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.458545468701342e-06,
+      "loss": 0.8672,
+      "step": 473
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.418482429515153e-06,
+      "loss": 0.8702,
+      "step": 474
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.378463734424148e-06,
+      "loss": 0.8605,
+      "step": 475
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.338490070850649e-06,
+      "loss": 0.8688,
+      "step": 476
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.298562125443467e-06,
+      "loss": 0.8531,
+      "step": 477
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.258680584066069e-06,
+      "loss": 0.8874,
+      "step": 478
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.218846131784824e-06,
+      "loss": 0.856,
+      "step": 479
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.17905945285723e-06,
+      "loss": 0.8589,
+      "step": 480
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.139321230720151e-06,
+      "loss": 0.8673,
+      "step": 481
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.09963214797808e-06,
+      "loss": 0.8407,
+      "step": 482
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.059992886391429e-06,
+      "loss": 0.8798,
+      "step": 483
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.020404126864795e-06,
+      "loss": 0.8772,
+      "step": 484
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.980866549435274e-06,
+      "loss": 0.862,
+      "step": 485
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.94138083326079e-06,
+      "loss": 0.8774,
+      "step": 486
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.90194765660841e-06,
+      "loss": 0.8396,
+      "step": 487
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.862567696842694e-06,
+      "loss": 0.8882,
+      "step": 488
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.823241630414095e-06,
+      "loss": 0.8572,
+      "step": 489
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.78397013284728e-06,
+      "loss": 0.8621,
+      "step": 490
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.744753878729574e-06,
+      "loss": 0.84,
+      "step": 491
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.705593541699358e-06,
+      "loss": 0.8677,
+      "step": 492
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.666489794434488e-06,
+      "loss": 0.8505,
+      "step": 493
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.627443308640749e-06,
+      "loss": 0.8615,
+      "step": 494
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.588454755040322e-06,
+      "loss": 0.8436,
+      "step": 495
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.549524803360249e-06,
+      "loss": 0.8763,
+      "step": 496
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.5106541223209344e-06,
+      "loss": 0.8867,
+      "step": 497
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.4718433796246685e-06,
+      "loss": 0.8531,
+      "step": 498
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.433093241944142e-06,
+      "loss": 0.8534,
+      "step": 499
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.394404374910996e-06,
+      "loss": 0.8517,
+      "step": 500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.355777443104409e-06,
+      "loss": 0.8695,
+      "step": 501
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.317213110039652e-06,
+      "loss": 0.8474,
+      "step": 502
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.278712038156705e-06,
+      "loss": 0.8822,
+      "step": 503
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.240274888808884e-06,
+      "loss": 0.8891,
+      "step": 504
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.201902322251471e-06,
+      "loss": 0.8608,
+      "step": 505
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.16359499763037e-06,
+      "loss": 0.8491,
+      "step": 506
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.125353572970798e-06,
+      "loss": 0.8381,
+      "step": 507
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.087178705165969e-06,
+      "loss": 0.8669,
+      "step": 508
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.049071049965811e-06,
+      "loss": 0.8557,
+      "step": 509
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.011031261965716e-06,
+      "loss": 0.8314,
+      "step": 510
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.973059994595277e-06,
+      "loss": 0.8644,
+      "step": 511
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.9351579001070655e-06,
+      "loss": 0.8396,
+      "step": 512
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.897325629565455e-06,
+      "loss": 0.8654,
+      "step": 513
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.859563832835393e-06,
+      "loss": 0.8396,
+      "step": 514
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.8218731585712716e-06,
+      "loss": 0.8474,
+      "step": 515
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.784254254205779e-06,
+      "loss": 0.8702,
+      "step": 516
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.746707765938764e-06,
+      "loss": 0.8629,
+      "step": 517
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.70923433872615e-06,
+      "loss": 0.8847,
+      "step": 518
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.671834616268861e-06,
+      "loss": 0.8668,
+      "step": 519
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.634509241001736e-06,
+      "loss": 0.8734,
+      "step": 520
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.5972588540825245e-06,
+      "loss": 0.8714,
+      "step": 521
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.5600840953808675e-06,
+      "loss": 0.8733,
+      "step": 522
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.52298560346729e-06,
+      "loss": 0.8634,
+      "step": 523
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.485964015602243e-06,
+      "loss": 0.8628,
+      "step": 524
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.449019967725161e-06,
+      "loss": 0.856,
+      "step": 525
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.412154094443527e-06,
+      "loss": 0.8537,
+      "step": 526
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.375367029021979e-06,
+      "loss": 0.8582,
+      "step": 527
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.338659403371438e-06,
+      "loss": 0.8694,
+      "step": 528
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.302031848038241e-06,
+      "loss": 0.8593,
+      "step": 529
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.265484992193302e-06,
+      "loss": 0.8589,
+      "step": 530
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.229019463621341e-06,
+      "loss": 0.8558,
+      "step": 531
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.19263588871006e-06,
+      "loss": 0.8586,
+      "step": 532
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.156334892439405e-06,
+      "loss": 0.8491,
+      "step": 533
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.120117098370824e-06,
+      "loss": 0.8599,
+      "step": 534
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.0839831286365535e-06,
+      "loss": 0.8451,
+      "step": 535
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.047933603928936e-06,
+      "loss": 0.8696,
+      "step": 536
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.011969143489769e-06,
+      "loss": 0.859,
+      "step": 537
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.976090365099638e-06,
+      "loss": 0.8269,
+      "step": 538
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.940297885067333e-06,
+      "loss": 0.846,
+      "step": 539
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.904592318219249e-06,
+      "loss": 0.8647,
+      "step": 540
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.868974277888826e-06,
+      "loss": 0.8594,
+      "step": 541
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.833444375906013e-06,
+      "loss": 0.8841,
+      "step": 542
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.798003222586773e-06,
+      "loss": 0.8398,
+      "step": 543
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.762651426722566e-06,
+      "loss": 0.8672,
+      "step": 544
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.727389595569919e-06,
+      "loss": 0.8701,
+      "step": 545
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.6922183348399996e-06,
+      "loss": 0.8465,
+      "step": 546
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.657138248688185e-06,
+      "loss": 0.8475,
+      "step": 547
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.622149939703704e-06,
+      "loss": 0.8407,
+      "step": 548
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.587254008899278e-06,
+      "loss": 0.8472,
+      "step": 549
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.552451055700802e-06,
+      "loss": 0.8934,
+      "step": 550
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.517741677937039e-06,
+      "loss": 0.8593,
+      "step": 551
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.483126471829371e-06,
+      "loss": 0.8583,
+      "step": 552
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.448606031981534e-06,
+      "loss": 0.8629,
+      "step": 553
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.414180951369405e-06,
+      "loss": 0.8616,
+      "step": 554
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.379851821330842e-06,
+      "loss": 0.8403,
+      "step": 555
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.345619231555503e-06,
+      "loss": 0.8722,
+      "step": 556
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.3114837700747205e-06,
+      "loss": 0.8547,
+      "step": 557
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.277446023251401e-06,
+      "loss": 0.8707,
+      "step": 558
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.243506575769958e-06,
+      "loss": 0.8577,
+      "step": 559
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.209666010626262e-06,
+      "loss": 0.8703,
+      "step": 560
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.175924909117638e-06,
+      "loss": 0.8435,
+      "step": 561
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.142283850832862e-06,
+      "loss": 0.8532,
+      "step": 562
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.108743413642219e-06,
+      "loss": 0.8323,
+      "step": 563
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.0753041736875675e-06,
+      "loss": 0.8386,
+      "step": 564
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.041966705372453e-06,
+      "loss": 0.8464,
+      "step": 565
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.008731581352229e-06,
+      "loss": 0.8522,
+      "step": 566
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.975599372524242e-06,
+      "loss": 0.8652,
+      "step": 567
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.942570648017988e-06,
+      "loss": 0.8546,
+      "step": 568
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.90964597518537e-06,
+      "loss": 0.8384,
+      "step": 569
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.876825919590944e-06,
+      "loss": 0.87,
+      "step": 570
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.844111045002193e-06,
+      "loss": 0.8583,
+      "step": 571
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8115019133798535e-06,
+      "loss": 0.8478,
+      "step": 572
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.778999084868257e-06,
+      "loss": 0.836,
+      "step": 573
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.74660311778571e-06,
+      "loss": 0.8649,
+      "step": 574
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.714314568614904e-06,
+      "loss": 0.8296,
+      "step": 575
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.682133991993361e-06,
+      "loss": 0.8423,
+      "step": 576
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6500619407038996e-06,
+      "loss": 0.8792,
+      "step": 577
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6180989656651268e-06,
+      "loss": 0.8276,
+      "step": 578
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5862456159220115e-06,
+      "loss": 0.8689,
+      "step": 579
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5545024386364192e-06,
+      "loss": 0.8288,
+      "step": 580
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.522869979077723e-06,
+      "loss": 0.859,
+      "step": 581
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.491348780613444e-06,
+      "loss": 0.8618,
+      "step": 582
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.4599393846999087e-06,
+      "loss": 0.8486,
+      "step": 583
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.4286423308729523e-06,
+      "loss": 0.8542,
+      "step": 584
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3974581567386567e-06,
+      "loss": 0.8623,
+      "step": 585
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3663873979641014e-06,
+      "loss": 0.849,
+      "step": 586
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3354305882681747e-06,
+      "loss": 0.8552,
+      "step": 587
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.304588259412399e-06,
+      "loss": 0.856,
+      "step": 588
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.2738609411918e-06,
+      "loss": 0.8358,
+      "step": 589
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.243249161425801e-06,
+      "loss": 0.8496,
+      "step": 590
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.2127534459491715e-06,
+      "loss": 0.8537,
+      "step": 591
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1823743186029676e-06,
+      "loss": 0.8509,
+      "step": 592
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1521123012255563e-06,
+      "loss": 0.8627,
+      "step": 593
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1219679136436496e-06,
+      "loss": 0.844,
+      "step": 594
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0919416736633643e-06,
+      "loss": 0.8494,
+      "step": 595
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.062034097061335e-06,
+      "loss": 0.8493,
+      "step": 596
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.0322456975758507e-06,
+      "loss": 0.8583,
+      "step": 597
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.0025769868980337e-06,
+      "loss": 0.8651,
+      "step": 598
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9730284746630454e-06,
+      "loss": 0.8272,
+      "step": 599
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9436006684413444e-06,
+      "loss": 0.8509,
+      "step": 600
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9142940737299486e-06,
+      "loss": 0.8276,
+      "step": 601
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.88510919394376e-06,
+      "loss": 0.8171,
+      "step": 602
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8560465304069217e-06,
+      "loss": 0.8472,
+      "step": 603
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.827106582344212e-06,
+      "loss": 0.8311,
+      "step": 604
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7982898468724496e-06,
+      "loss": 0.8329,
+      "step": 605
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7695968189919686e-06,
+      "loss": 0.8376,
+      "step": 606
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7410279915781124e-06,
+      "loss": 0.8334,
+      "step": 607
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.712583855372769e-06,
+      "loss": 0.8472,
+      "step": 608
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6842648989759325e-06,
+      "loss": 0.8533,
+      "step": 609
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6560716088373295e-06,
+      "loss": 0.835,
+      "step": 610
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.628004469248043e-06,
+      "loss": 0.8364,
+      "step": 611
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6000639623321934e-06,
+      "loss": 0.87,
+      "step": 612
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.572250568038681e-06,
+      "loss": 0.8392,
+      "step": 613
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.5445647641329154e-06,
+      "loss": 0.8465,
+      "step": 614
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.517007026188619e-06,
+      "loss": 0.8504,
+      "step": 615
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.489577827579659e-06,
+      "loss": 0.8492,
+      "step": 616
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.462277639471914e-06,
+      "loss": 0.827,
+      "step": 617
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4351069308151774e-06,
+      "loss": 0.8499,
+      "step": 618
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4080661683351146e-06,
+      "loss": 0.8471,
+      "step": 619
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.381155816525228e-06,
+      "loss": 0.8504,
+      "step": 620
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.3543763376388906e-06,
+      "loss": 0.843,
+      "step": 621
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.3277281916814e-06,
+      "loss": 0.8753,
+      "step": 622
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.3012118364020787e-06,
+      "loss": 0.8318,
+      "step": 623
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2748277272864108e-06,
+      "loss": 0.849,
+      "step": 624
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2485763175482255e-06,
+      "loss": 0.8595,
+      "step": 625
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.222458058121889e-06,
+      "loss": 0.8723,
+      "step": 626
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.196473397654585e-06,
+      "loss": 0.834,
+      "step": 627
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.170622782498598e-06,
+      "loss": 0.8592,
+      "step": 628
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.1449066567036413e-06,
+      "loss": 0.8483,
+      "step": 629
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.119325462009233e-06,
+      "loss": 0.8498,
+      "step": 630
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0938796378371084e-06,
+      "loss": 0.8357,
+      "step": 631
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0685696212836737e-06,
+      "loss": 0.8732,
+      "step": 632
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0433958471124903e-06,
+      "loss": 0.847,
+      "step": 633
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0183587477468226e-06,
+      "loss": 0.8515,
+      "step": 634
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9934587532621917e-06,
+      "loss": 0.8563,
+      "step": 635
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9686962913789897e-06,
+      "loss": 0.8604,
+      "step": 636
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9440717874551527e-06,
+      "loss": 0.8334,
+      "step": 637
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.91958566447883e-06,
+      "loss": 0.8616,
+      "step": 638
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8952383430611299e-06,
+      "loss": 0.8746,
+      "step": 639
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.871030241428894e-06,
+      "loss": 0.8409,
+      "step": 640
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8469617754175106e-06,
+      "loss": 0.8256,
+      "step": 641
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8230333584637715e-06,
+      "loss": 0.8314,
+      "step": 642
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7992454015987791e-06,
+      "loss": 0.8429,
+      "step": 643
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7755983134408706e-06,
+      "loss": 0.8658,
+      "step": 644
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.752092500188608e-06,
+      "loss": 0.8247,
+      "step": 645
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7287283656138009e-06,
+      "loss": 0.866,
+      "step": 646
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.70550631105457e-06,
+      "loss": 0.8494,
+      "step": 647
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6824267354084478e-06,
+      "loss": 0.832,
+      "step": 648
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6594900351255427e-06,
+      "loss": 0.8418,
+      "step": 649
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6366966042016996e-06,
+      "loss": 0.8149,
+      "step": 650
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6140468341717607e-06,
+      "loss": 0.8161,
+      "step": 651
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5915411141028325e-06,
+      "loss": 0.8528,
+      "step": 652
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5691798305875893e-06,
+      "loss": 0.8487,
+      "step": 653
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5469633677376494e-06,
+      "loss": 0.874,
+      "step": 654
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.524892107176964e-06,
+      "loss": 0.8438,
+      "step": 655
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.502966428035274e-06,
+      "loss": 0.8513,
+      "step": 656
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4811867069415832e-06,
+      "loss": 0.8251,
+      "step": 657
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4595533180177058e-06,
+      "loss": 0.8478,
+      "step": 658
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4380666328718274e-06,
+      "loss": 0.8564,
+      "step": 659
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4167270205921168e-06,
+      "loss": 0.8771,
+      "step": 660
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3955348477404073e-06,
+      "loss": 0.8277,
+      "step": 661
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.37449047834588e-06,
+      "loss": 0.8363,
+      "step": 662
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3535942738988194e-06,
+      "loss": 0.848,
+      "step": 663
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.332846593344399e-06,
+      "loss": 0.8757,
+      "step": 664
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3122477930765243e-06,
+      "loss": 0.853,
+      "step": 665
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2917982269316975e-06,
+      "loss": 0.8361,
+      "step": 666
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2714982461829572e-06,
+      "loss": 0.8305,
+      "step": 667
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2513481995338284e-06,
+      "loss": 0.8379,
+      "step": 668
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2313484331123371e-06,
+      "loss": 0.8535,
+      "step": 669
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.211499290465069e-06,
+      "loss": 0.8233,
+      "step": 670
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1918011125512651e-06,
+      "loss": 0.8559,
+      "step": 671
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1722542377369639e-06,
+      "loss": 0.8392,
+      "step": 672
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.152859001789196e-06,
+      "loss": 0.8377,
+      "step": 673
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1336157378702017e-06,
+      "loss": 0.8806,
+      "step": 674
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1145247765317192e-06,
+      "loss": 0.8436,
+      "step": 675
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0955864457093147e-06,
+      "loss": 0.8664,
+      "step": 676
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0768010707167265e-06,
+      "loss": 0.8457,
+      "step": 677
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0581689742402967e-06,
+      "loss": 0.8403,
+      "step": 678
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0396904763334182e-06,
+      "loss": 0.8364,
+      "step": 679
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0213658944110406e-06,
+      "loss": 0.8323,
+      "step": 680
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0031955432442153e-06,
+      "loss": 0.8344,
+      "step": 681
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.851797349546977e-07,
+      "loss": 0.851,
+      "step": 682
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.673187790095707e-07,
+      "loss": 0.8379,
+      "step": 683
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.496129822159339e-07,
+      "loss": 0.8569,
+      "step": 684
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.320626487156459e-07,
+      "loss": 0.8463,
+      "step": 685
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.146680799800833e-07,
+      "loss": 0.8349,
+      "step": 686
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.974295748049711e-07,
+      "loss": 0.836,
+      "step": 687
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.803474293052438e-07,
+      "loss": 0.8636,
+      "step": 688
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.634219369099694e-07,
+      "loss": 0.8414,
+      "step": 689
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.466533883572947e-07,
+      "loss": 0.8452,
+      "step": 690
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.300420716894685e-07,
+      "loss": 0.8305,
+      "step": 691
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.135882722478772e-07,
+      "loss": 0.8307,
+      "step": 692
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.972922726681509e-07,
+      "loss": 0.8345,
+      "step": 693
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.811543528753108e-07,
+      "loss": 0.8272,
+      "step": 694
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.651747900789552e-07,
+      "loss": 0.8493,
+      "step": 695
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.493538587685012e-07,
+      "loss": 0.8597,
+      "step": 696
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.336918307084718e-07,
+      "loss": 0.8397,
+      "step": 697
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.181889749338178e-07,
+      "loss": 0.8216,
+      "step": 698
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.028455577453075e-07,
+      "loss": 0.863,
+      "step": 699
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.876618427049509e-07,
+      "loss": 0.8604,
+      "step": 700
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.726380906314655e-07,
+      "loss": 0.8451,
+      "step": 701
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.577745595958018e-07,
+      "loss": 0.8485,
+      "step": 702
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.430715049167069e-07,
+      "loss": 0.8662,
+      "step": 703
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.285291791563431e-07,
+      "loss": 0.8402,
+      "step": 704
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.141478321159422e-07,
+      "loss": 0.8302,
+      "step": 705
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.999277108315272e-07,
+      "loss": 0.8606,
+      "step": 706
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.858690595696559e-07,
+      "loss": 0.8566,
+      "step": 707
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.719721198232254e-07,
+      "loss": 0.839,
+      "step": 708
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.582371303073386e-07,
+      "loss": 0.8464,
+      "step": 709
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.446643269551854e-07,
+      "loss": 0.8271,
+      "step": 710
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.312539429140018e-07,
+      "loss": 0.8371,
+      "step": 711
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.180062085410609e-07,
+      "loss": 0.865,
+      "step": 712
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.049213513997142e-07,
+      "loss": 0.8687,
+      "step": 713
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.919995962554846e-07,
+      "loss": 0.8563,
+      "step": 714
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.792411650722117e-07,
+      "loss": 0.8756,
+      "step": 715
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.6664627700822475e-07,
+      "loss": 0.8311,
+      "step": 716
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.5421514841259115e-07,
+      "loss": 0.8479,
+      "step": 717
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.4194799282139324e-07,
+      "loss": 0.8535,
+      "step": 718
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.298450209540628e-07,
+      "loss": 0.8282,
+      "step": 719
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.1790644070975884e-07,
+      "loss": 0.8294,
+      "step": 720
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.061324571638048e-07,
+      "loss": 0.8249,
+      "step": 721
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.94523272564149e-07,
+      "loss": 0.8428,
+      "step": 722
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.830790863279088e-07,
+      "loss": 0.8353,
+      "step": 723
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.7180009503793745e-07,
+      "loss": 0.8406,
+      "step": 724
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.6068649243944267e-07,
+      "loss": 0.8286,
+      "step": 725
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.4973846943666567e-07,
+      "loss": 0.8555,
+      "step": 726
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.3895621408959744e-07,
+      "loss": 0.8495,
+      "step": 727
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.283399116107533e-07,
+      "loss": 0.8678,
+      "step": 728
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.1788974436198326e-07,
+      "loss": 0.8589,
+      "step": 729
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.076058918513503e-07,
+      "loss": 0.829,
+      "step": 730
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.974885307300379e-07,
+      "loss": 0.8294,
+      "step": 731
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.875378347893165e-07,
+      "loss": 0.839,
+      "step": 732
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7775397495756527e-07,
+      "loss": 0.8421,
+      "step": 733
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.681371192973281e-07,
+      "loss": 0.836,
+      "step": 734
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.5868743300242913e-07,
+      "loss": 0.8508,
+      "step": 735
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.494050783951396e-07,
+      "loss": 0.8354,
+      "step": 736
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.402902149233799e-07,
+      "loss": 0.8255,
+      "step": 737
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.3134299915799185e-07,
+      "loss": 0.8669,
+      "step": 738
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.2256358479004092e-07,
+      "loss": 0.8533,
+      "step": 739
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1395212262817933e-07,
+      "loss": 0.818,
+      "step": 740
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0550876059605597e-07,
+      "loss": 0.8321,
+      "step": 741
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9723364372977395e-07,
+      "loss": 0.8606,
+      "step": 742
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8912691417540152e-07,
+      "loss": 0.8534,
+      "step": 743
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8118871118652516e-07,
+      "loss": 0.8382,
+      "step": 744
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7341917112186801e-07,
+      "loss": 0.8366,
+      "step": 745
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6581842744293309e-07,
+      "loss": 0.8548,
+      "step": 746
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5838661071172268e-07,
+      "loss": 0.8433,
+      "step": 747
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.511238485884914e-07,
+      "loss": 0.8256,
+      "step": 748
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4403026582955337e-07,
+      "loss": 0.8429,
+      "step": 749
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3710598428513634e-07,
+      "loss": 0.834,
+      "step": 750
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3035112289729423e-07,
+      "loss": 0.8536,
+      "step": 751
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2376579769786124e-07,
+      "loss": 0.8414,
+      "step": 752
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1735012180645544e-07,
+      "loss": 0.8436,
+      "step": 753
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1110420542854383e-07,
+      "loss": 0.8288,
+      "step": 754
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0502815585354042e-07,
+      "loss": 0.8275,
+      "step": 755
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.912207745296665e-08,
+      "loss": 0.814,
+      "step": 756
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.338607167866276e-08,
+      "loss": 0.8567,
+      "step": 757
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.782023706103926e-08,
+      "loss": 0.8112,
+      "step": 758
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.242466920738601e-08,
+      "loss": 0.8295,
+      "step": 759
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.719946080023022e-08,
+      "loss": 0.863,
+      "step": 760
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.21447015957466e-08,
+      "loss": 0.8459,
+      "step": 761
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.726047842221083e-08,
+      "loss": 0.8252,
+      "step": 762
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.25468751785141e-08,
+      "loss": 0.842,
+      "step": 763
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.800397283271753e-08,
+      "loss": 0.7975,
+      "step": 764
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.363184942065891e-08,
+      "loss": 0.8427,
+      "step": 765
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.9430580044620425e-08,
+      "loss": 0.8291,
+      "step": 766
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.540023687203299e-08,
+      "loss": 0.8459,
+      "step": 767
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.154088913423615e-08,
+      "loss": 0.8397,
+      "step": 768
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.7852603125291265e-08,
+      "loss": 0.845,
+      "step": 769
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.433544220084017e-08,
+      "loss": 0.853,
+      "step": 770
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.0989466777021634e-08,
+      "loss": 0.8381,
+      "step": 771
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.7814734329426607e-08,
+      "loss": 0.8597,
+      "step": 772
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.4811299392117904e-08,
+      "loss": 0.8479,
+      "step": 773
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.197921355668875e-08,
+      "loss": 0.847,
+      "step": 774
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.9318525471376803e-08,
+      "loss": 0.8322,
+      "step": 775
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.682928084023261e-08,
+      "loss": 0.8577,
+      "step": 776
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.4511522422330226e-08,
+      "loss": 0.8392,
+      "step": 777
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.2365290031032261e-08,
+      "loss": 0.8336,
+      "step": 778
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0390620533312635e-08,
+      "loss": 0.844,
+      "step": 779
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 8.587547849112643e-09,
+      "loss": 0.8479,
+      "step": 780
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.956102950770316e-09,
+      "loss": 0.8538,
+      "step": 781
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.496313862476399e-09,
+      "loss": 0.8424,
+      "step": 782
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.208205659802511e-09,
+      "loss": 0.8559,
+      "step": 783
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.0918004692648273e-09,
+      "loss": 0.8246,
+      "step": 784
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.147117467949933e-09,
+      "loss": 0.8294,
+      "step": 785
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3741728831750956e-09,
+      "loss": 0.8419,
+      "step": 786
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.729799922195913e-10,
+      "loss": 0.8301,
+      "step": 787
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.435491220937781e-10,
+      "loss": 0.853,
+      "step": 788
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.588764935812955e-11,
+      "loss": 0.862,
+      "step": 789
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.8478,
+      "step": 790
+    },
+    {
+      "epoch": 1.0,
+      "step": 790,
+      "total_flos": 2.0932257395402342e+18,
+      "train_loss": 0.9096447054343888,
+      "train_runtime": 30006.5259,
+      "train_samples_per_second": 3.37,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "max_steps": 790,
+  "num_train_epochs": 1,
+  "total_flos": 2.0932257395402342e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731fcddac33d3b6ae6eb7451011aac9268ccc1a3aea00be489f220f8d669a727
+size 3771