add model

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<point_end>": 32002,
+  "<point_patch>": 32000,
+  "<point_start>": 32001
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "DEFAULT_POINT_END_TOKEN": "<point_end>",
+  "DEFAULT_POINT_PATCH_TOKEN": "<point_patch>",
+  "DEFAULT_POINT_START_TOKEN": "<point_start>",
+  "_name_or_path": "/code/syr/PointLLM/checkpoints/PointLLM_7B_v1.2",
+  "architectures": [
+    "PointLLMLlamaForCausalLM"
+  ],
+  "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,
+  "mm_use_point_start_end": true,
+  "model_type": "pointllm",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "point_backbone": "PointBERT",
+  "point_backbone_ckpt": "",
+  "point_backbone_config_name": "PointTransformer_8192point_2layer",
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": false,
+  "use_color": true,
+  "vocab_size": 32003
+}

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": "4.28.0.dev0"
+}

point_bert_v1.2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6e2160e27526abac9f11ec822fdea1ead6fcb87085108ba92c3063ce0b10b0
+size 87494929

point_proj.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c06b38bbcba1acc5d5e14aa1e027dbebcb07cab92388c0b0a2c218eba26abcf
+size 567884645

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8db1aa66e449394b9f51216f8a6887eb5d0cca0c57307bfa1c227918e452760
+size 9878039225

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b65bd1237f17ab93d996ca3427a4fb2b316a816a991684d9bf63881b8359535
+size 9894801501

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df935c1b1f7f80c2e4e85bf6b74b608e3e5b4df7cafea1614e2c2ec72e72e87
+size 7312084483

pytorch_model.bin.index.json

@@ -0,0 +1,496 @@
+{
+  "metadata": {
+    "total_size": 27084755472
+  },
+  "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",
+    "model.point_backbone.blocks.blocks.0.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.0.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.0.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.0.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.0.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.0.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.0.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.1.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.10.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.11.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.2.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.3.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.4.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.5.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.6.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.7.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.8.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.norm1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.norm1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.norm2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.blocks.blocks.9.norm2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.cls_pos": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.cls_token": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.first_conv.0.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.first_conv.0.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.first_conv.1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.first_conv.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.first_conv.1.running_mean": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.first_conv.1.running_var": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.first_conv.1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.first_conv.3.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.first_conv.3.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.second_conv.0.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.second_conv.0.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.second_conv.1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.second_conv.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.second_conv.1.running_mean": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.second_conv.1.running_var": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.second_conv.1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.second_conv.3.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.encoder.second_conv.3.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.pos_embed.0.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.pos_embed.0.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.pos_embed.2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.pos_embed.2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.reduce_dim.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_backbone.reduce_dim.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_proj.0.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_proj.0.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_proj.2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_proj.2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.point_proj.4.bias": "pytorch_model-00003-of-00003.bin",
+    "model.point_proj.4.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 +1,32 @@
+{
+  "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",
+  "special_tokens_map_file": "/mnt/afs/xurunsen/projects/datasets/LLaMA/ChatPoint-7b-v1.1_init_color/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,3751 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984926138076575,
+  "global_step": 621,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 2.6289,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 2.6619,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 2.2648,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.31578947368421e-06,
+      "loss": 1.8016,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.894736842105263e-06,
+      "loss": 1.5006,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.473684210526315e-06,
+      "loss": 1.2957,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1052631578947368e-05,
+      "loss": 1.1769,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.263157894736842e-05,
+      "loss": 1.0785,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4210526315789473e-05,
+      "loss": 1.0298,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5789473684210526e-05,
+      "loss": 0.9725,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.736842105263158e-05,
+      "loss": 0.9271,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.894736842105263e-05,
+      "loss": 0.9122,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.0526315789473685e-05,
+      "loss": 0.887,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.2105263157894736e-05,
+      "loss": 0.8558,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 0.8786,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.526315789473684e-05,
+      "loss": 0.8406,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.6842105263157896e-05,
+      "loss": 0.8047,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.8421052631578946e-05,
+      "loss": 0.8004,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3e-05,
+      "loss": 0.7882,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.9999795747660024e-05,
+      "loss": 0.8009,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.9999182996202625e-05,
+      "loss": 0.8061,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.999816176231527e-05,
+      "loss": 0.7763,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9996732073809866e-05,
+      "loss": 0.7949,
+      "step": 23
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9994893969622058e-05,
+      "loss": 0.7974,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.999264749981011e-05,
+      "loss": 0.7833,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.998999272555359e-05,
+      "loss": 0.7655,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9986929719151682e-05,
+      "loss": 0.7665,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.998345856402121e-05,
+      "loss": 0.7666,
+      "step": 28
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9979579354694385e-05,
+      "loss": 0.7497,
+      "step": 29
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9975292196816215e-05,
+      "loss": 0.7739,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9970597207141642e-05,
+      "loss": 0.7741,
+      "step": 31
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.996549451353235e-05,
+      "loss": 0.7744,
+      "step": 32
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9959984254953276e-05,
+      "loss": 0.7812,
+      "step": 33
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.995406658146886e-05,
+      "loss": 0.7558,
+      "step": 34
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.9947741654238918e-05,
+      "loss": 0.7499,
+      "step": 35
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.9941009645514273e-05,
+      "loss": 0.759,
+      "step": 36
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.993387073863207e-05,
+      "loss": 0.7595,
+      "step": 37
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.992632512801076e-05,
+      "loss": 0.7622,
+      "step": 38
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.991837301914483e-05,
+      "loss": 0.7367,
+      "step": 39
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.9910014628599188e-05,
+      "loss": 0.7679,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.9901250184003286e-05,
+      "loss": 0.7414,
+      "step": 41
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.9892079924044892e-05,
+      "loss": 0.7491,
+      "step": 42
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.9882504098463614e-05,
+      "loss": 0.7704,
+      "step": 43
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.98725229680441e-05,
+      "loss": 0.7218,
+      "step": 44
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.9862136804608897e-05,
+      "loss": 0.723,
+      "step": 45
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.985134589101111e-05,
+      "loss": 0.7511,
+      "step": 46
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9840150521126656e-05,
+      "loss": 0.7258,
+      "step": 47
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9828550999846257e-05,
+      "loss": 0.7263,
+      "step": 48
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9816547643067163e-05,
+      "loss": 0.7348,
+      "step": 49
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9804140777684538e-05,
+      "loss": 0.7454,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.979133074158256e-05,
+      "loss": 0.7683,
+      "step": 51
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9778117883625196e-05,
+      "loss": 0.7351,
+      "step": 52
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.9764502563646746e-05,
+      "loss": 0.7302,
+      "step": 53
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.975048515244199e-05,
+      "loss": 0.7243,
+      "step": 54
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.973606603175615e-05,
+      "loss": 0.7189,
+      "step": 55
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.9721245594274435e-05,
+      "loss": 0.7269,
+      "step": 56
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.9706024243611384e-05,
+      "loss": 0.7288,
+      "step": 57
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.969040239429987e-05,
+      "loss": 0.7303,
+      "step": 58
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.9674380471779784e-05,
+      "loss": 0.6944,
+      "step": 59
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.9657958912386487e-05,
+      "loss": 0.7537,
+      "step": 60
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.964113816333891e-05,
+      "loss": 0.7305,
+      "step": 61
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.9623918682727355e-05,
+      "loss": 0.7183,
+      "step": 62
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.9606300939501055e-05,
+      "loss": 0.7353,
+      "step": 63
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.9588285413455384e-05,
+      "loss": 0.7355,
+      "step": 64
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.9569872595218786e-05,
+      "loss": 0.724,
+      "step": 65
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9551062986239422e-05,
+      "loss": 0.7374,
+      "step": 66
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.953185709877151e-05,
+      "loss": 0.7322,
+      "step": 67
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9512255455861378e-05,
+      "loss": 0.7321,
+      "step": 68
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9492258591333224e-05,
+      "loss": 0.728,
+      "step": 69
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9471867049774554e-05,
+      "loss": 0.7536,
+      "step": 70
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9451081386521383e-05,
+      "loss": 0.7061,
+      "step": 71
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.9429902167643094e-05,
+      "loss": 0.7217,
+      "step": 72
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.940832996992702e-05,
+      "loss": 0.7466,
+      "step": 73
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.9386365380862742e-05,
+      "loss": 0.7249,
+      "step": 74
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.936400899862609e-05,
+      "loss": 0.7365,
+      "step": 75
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.934126143206285e-05,
+      "loss": 0.7209,
+      "step": 76
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.9318123300672176e-05,
+      "loss": 0.7399,
+      "step": 77
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.929459523458974e-05,
+      "loss": 0.7155,
+      "step": 78
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9270677874570545e-05,
+      "loss": 0.7405,
+      "step": 79
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9246371871971487e-05,
+      "loss": 0.7201,
+      "step": 80
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9221677888733628e-05,
+      "loss": 0.7325,
+      "step": 81
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.919659659736414e-05,
+      "loss": 0.7072,
+      "step": 82
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9171128680918025e-05,
+      "loss": 0.7461,
+      "step": 83
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9145274832979487e-05,
+      "loss": 0.729,
+      "step": 84
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9119035757643046e-05,
+      "loss": 0.7236,
+      "step": 85
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9092412169494375e-05,
+      "loss": 0.7501,
+      "step": 86
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9065404793590832e-05,
+      "loss": 0.726,
+      "step": 87
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.903801436544171e-05,
+      "loss": 0.7212,
+      "step": 88
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.901024163098822e-05,
+      "loss": 0.6973,
+      "step": 89
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.898208734658316e-05,
+      "loss": 0.721,
+      "step": 90
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.8953552278970327e-05,
+      "loss": 0.721,
+      "step": 91
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.892463720526363e-05,
+      "loss": 0.7359,
+      "step": 92
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.889534291292593e-05,
+      "loss": 0.7043,
+      "step": 93
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.88656701997476e-05,
+      "loss": 0.7423,
+      "step": 94
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.883561987382478e-05,
+      "loss": 0.7247,
+      "step": 95
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.880519275353739e-05,
+      "loss": 0.7506,
+      "step": 96
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.877438966752684e-05,
+      "loss": 0.7028,
+      "step": 97
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.874321145467344e-05,
+      "loss": 0.7118,
+      "step": 98
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.871165896407358e-05,
+      "loss": 0.7215,
+      "step": 99
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.867973305501661e-05,
+      "loss": 0.7214,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.8647434596961397e-05,
+      "loss": 0.737,
+      "step": 101
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.8614764469512708e-05,
+      "loss": 0.7213,
+      "step": 102
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.8581723562397203e-05,
+      "loss": 0.7328,
+      "step": 103
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.854831277543922e-05,
+      "loss": 0.7207,
+      "step": 104
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.8514533018536286e-05,
+      "loss": 0.7463,
+      "step": 105
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.8480385211634324e-05,
+      "loss": 0.713,
+      "step": 106
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.8445870284702593e-05,
+      "loss": 0.6953,
+      "step": 107
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.841098917770837e-05,
+      "loss": 0.7047,
+      "step": 108
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.837574284059135e-05,
+      "loss": 0.6912,
+      "step": 109
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.8340132233237784e-05,
+      "loss": 0.7134,
+      "step": 110
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.8304158325454318e-05,
+      "loss": 0.7308,
+      "step": 111
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.8267822096941597e-05,
+      "loss": 0.724,
+      "step": 112
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.823112453726758e-05,
+      "loss": 0.7111,
+      "step": 113
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.8194066645840598e-05,
+      "loss": 0.7095,
+      "step": 114
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.8156649431882118e-05,
+      "loss": 0.7052,
+      "step": 115
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.8118873914399276e-05,
+      "loss": 0.7306,
+      "step": 116
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.8080741122157116e-05,
+      "loss": 0.7132,
+      "step": 117
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.8042252093650578e-05,
+      "loss": 0.711,
+      "step": 118
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.800340787707621e-05,
+      "loss": 0.7274,
+      "step": 119
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.7964209530303632e-05,
+      "loss": 0.7188,
+      "step": 120
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.792465812084672e-05,
+      "loss": 0.7034,
+      "step": 121
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.788475472583453e-05,
+      "loss": 0.7269,
+      "step": 122
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.784450043198197e-05,
+      "loss": 0.7135,
+      "step": 123
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.78038963355602e-05,
+      "loss": 0.7152,
+      "step": 124
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.776294354236678e-05,
+      "loss": 0.7174,
+      "step": 125
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.7721643167695552e-05,
+      "loss": 0.7204,
+      "step": 126
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.767999633630628e-05,
+      "loss": 0.706,
+      "step": 127
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.7638004182394e-05,
+      "loss": 0.6973,
+      "step": 128
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.759566784955813e-05,
+      "loss": 0.7048,
+      "step": 129
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.7552988490771346e-05,
+      "loss": 0.6984,
+      "step": 130
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.7509967268348168e-05,
+      "loss": 0.6926,
+      "step": 131
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.7466605353913312e-05,
+      "loss": 0.6848,
+      "step": 132
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.7422903928369777e-05,
+      "loss": 0.6812,
+      "step": 133
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.7378864181866683e-05,
+      "loss": 0.7051,
+      "step": 134
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.7334487313766867e-05,
+      "loss": 0.6966,
+      "step": 135
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.7289774532614215e-05,
+      "loss": 0.6857,
+      "step": 136
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.7244727056100755e-05,
+      "loss": 0.7081,
+      "step": 137
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.719934611103348e-05,
+      "loss": 0.6819,
+      "step": 138
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.7153632933300957e-05,
+      "loss": 0.6823,
+      "step": 139
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.7107588767839654e-05,
+      "loss": 0.7421,
+      "step": 140
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.7061214868600045e-05,
+      "loss": 0.7034,
+      "step": 141
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.7014512498512452e-05,
+      "loss": 0.7123,
+      "step": 142
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.696748292945265e-05,
+      "loss": 0.6947,
+      "step": 143
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.6920127442207262e-05,
+      "loss": 0.7064,
+      "step": 144
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.6872447326438813e-05,
+      "loss": 0.7085,
+      "step": 145
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.6824443880650673e-05,
+      "loss": 0.6998,
+      "step": 146
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.6776118412151662e-05,
+      "loss": 0.6983,
+      "step": 147
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.672747223702045e-05,
+      "loss": 0.6932,
+      "step": 148
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.6678506680069708e-05,
+      "loss": 0.6901,
+      "step": 149
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.6629223074810057e-05,
+      "loss": 0.7058,
+      "step": 150
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.6579622763413718e-05,
+      "loss": 0.683,
+      "step": 151
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.652970709667798e-05,
+      "loss": 0.7158,
+      "step": 152
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.6479477433988413e-05,
+      "loss": 0.6693,
+      "step": 153
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.642893514328183e-05,
+      "loss": 0.6994,
+      "step": 154
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.637808160100905e-05,
+      "loss": 0.7029,
+      "step": 155
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.632691819209741e-05,
+      "loss": 0.7294,
+      "step": 156
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.627544630991304e-05,
+      "loss": 0.7046,
+      "step": 157
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.6223667356222925e-05,
+      "loss": 0.6985,
+      "step": 158
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.617158274115673e-05,
+      "loss": 0.6882,
+      "step": 159
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.611919388316838e-05,
+      "loss": 0.7089,
+      "step": 160
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.6066502208997456e-05,
+      "loss": 0.7028,
+      "step": 161
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.601350915363033e-05,
+      "loss": 0.71,
+      "step": 162
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.5960216160261063e-05,
+      "loss": 0.6834,
+      "step": 163
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.5906624680252152e-05,
+      "loss": 0.7107,
+      "step": 164
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.585273617309495e-05,
+      "loss": 0.6981,
+      "step": 165
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.579855210636994e-05,
+      "loss": 0.7053,
+      "step": 166
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5744073955706786e-05,
+      "loss": 0.702,
+      "step": 167
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5689303204744123e-05,
+      "loss": 0.7044,
+      "step": 168
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.563424134508915e-05,
+      "loss": 0.6947,
+      "step": 169
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5578889876277027e-05,
+      "loss": 0.7189,
+      "step": 170
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.552325030573003e-05,
+      "loss": 0.6952,
+      "step": 171
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.5467324148716483e-05,
+      "loss": 0.6598,
+      "step": 172
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.541111292830951e-05,
+      "loss": 0.694,
+      "step": 173
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.5354618175345553e-05,
+      "loss": 0.6709,
+      "step": 174
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.529784142838268e-05,
+      "loss": 0.6707,
+      "step": 175
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.524078423365868e-05,
+      "loss": 0.675,
+      "step": 176
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.5183448145048956e-05,
+      "loss": 0.7101,
+      "step": 177
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.512583472402421e-05,
+      "loss": 0.7034,
+      "step": 178
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.5067945539607913e-05,
+      "loss": 0.6958,
+      "step": 179
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.500978216833359e-05,
+      "loss": 0.6806,
+      "step": 180
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.495134619420186e-05,
+      "loss": 0.7301,
+      "step": 181
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.4892639208637316e-05,
+      "loss": 0.7204,
+      "step": 182
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.4833662810445188e-05,
+      "loss": 0.6885,
+      "step": 183
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.477441860576778e-05,
+      "loss": 0.7118,
+      "step": 184
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.4714908208040756e-05,
+      "loss": 0.7006,
+      "step": 185
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.465513323794917e-05,
+      "loss": 0.7017,
+      "step": 186
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.459509532338337e-05,
+      "loss": 0.6917,
+      "step": 187
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.4534796099394624e-05,
+      "loss": 0.6804,
+      "step": 188
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.4474237208150606e-05,
+      "loss": 0.7019,
+      "step": 189
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.4413420298890687e-05,
+      "loss": 0.6755,
+      "step": 190
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.4352347027881003e-05,
+      "loss": 0.692,
+      "step": 191
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.429101905836936e-05,
+      "loss": 0.718,
+      "step": 192
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.4229438060539917e-05,
+      "loss": 0.7089,
+      "step": 193
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.416760571146774e-05,
+      "loss": 0.6916,
+      "step": 194
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.4105523695073086e-05,
+      "loss": 0.6847,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.4043193702075576e-05,
+      "loss": 0.6764,
+      "step": 196
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.3980617429948132e-05,
+      "loss": 0.7085,
+      "step": 197
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.391779658287075e-05,
+      "loss": 0.7112,
+      "step": 198
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.3854732871684104e-05,
+      "loss": 0.6706,
+      "step": 199
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.3791428013842935e-05,
+      "loss": 0.6831,
+      "step": 200
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.3727883733369295e-05,
+      "loss": 0.6848,
+      "step": 201
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.366410176080557e-05,
+      "loss": 0.6828,
+      "step": 202
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.360008383316739e-05,
+      "loss": 0.6917,
+      "step": 203
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.3535831693896283e-05,
+      "loss": 0.6664,
+      "step": 204
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.3471347092812224e-05,
+      "loss": 0.6732,
+      "step": 205
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.3406631786065977e-05,
+      "loss": 0.7021,
+      "step": 206
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.334168753609124e-05,
+      "loss": 0.6986,
+      "step": 207
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.327651611155669e-05,
+      "loss": 0.6899,
+      "step": 208
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.3211119287317785e-05,
+      "loss": 0.6732,
+      "step": 209
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.3145498844368448e-05,
+      "loss": 0.7044,
+      "step": 210
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.3079656569792543e-05,
+      "loss": 0.6834,
+      "step": 211
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.3013594256715232e-05,
+      "loss": 0.6906,
+      "step": 212
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.2947313704254104e-05,
+      "loss": 0.6995,
+      "step": 213
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.2880816717470225e-05,
+      "loss": 0.6925,
+      "step": 214
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.2814105107318955e-05,
+      "loss": 0.695,
+      "step": 215
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.274718069060062e-05,
+      "loss": 0.7041,
+      "step": 216
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.2680045289911042e-05,
+      "loss": 0.6718,
+      "step": 217
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.261270073359192e-05,
+      "loss": 0.6794,
+      "step": 218
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.254514885568101e-05,
+      "loss": 0.7014,
+      "step": 219
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.2477391495862206e-05,
+      "loss": 0.6996,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.2409430499415408e-05,
+      "loss": 0.6992,
+      "step": 221
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.2341267717166285e-05,
+      "loss": 0.6909,
+      "step": 222
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.2272905005435876e-05,
+      "loss": 0.6922,
+      "step": 223
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.220434422599003e-05,
+      "loss": 0.6909,
+      "step": 224
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.2135587245988698e-05,
+      "loss": 0.696,
+      "step": 225
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.2066635937935085e-05,
+      "loss": 0.7072,
+      "step": 226
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.1997492179624662e-05,
+      "loss": 0.6845,
+      "step": 227
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.1928157854094014e-05,
+      "loss": 0.6987,
+      "step": 228
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.1858634849569578e-05,
+      "loss": 0.7064,
+      "step": 229
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.17889250594162e-05,
+      "loss": 0.7079,
+      "step": 230
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.1719030382085577e-05,
+      "loss": 0.6718,
+      "step": 231
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.1648952721064563e-05,
+      "loss": 0.6888,
+      "step": 232
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.157869398482333e-05,
+      "loss": 0.6822,
+      "step": 233
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.1508256086763372e-05,
+      "loss": 0.6774,
+      "step": 234
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.1437640945165433e-05,
+      "loss": 0.6815,
+      "step": 235
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.136685048313723e-05,
+      "loss": 0.6718,
+      "step": 236
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.1295886628561092e-05,
+      "loss": 0.688,
+      "step": 237
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.122475131404148e-05,
+      "loss": 0.6881,
+      "step": 238
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.1153446476852304e-05,
+      "loss": 0.6833,
+      "step": 239
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.108197405888422e-05,
+      "loss": 0.6988,
+      "step": 240
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.1010336006591715e-05,
+      "loss": 0.6775,
+      "step": 241
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.093853427094009e-05,
+      "loss": 0.6972,
+      "step": 242
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.086657080735234e-05,
+      "loss": 0.7003,
+      "step": 243
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.0794447575655924e-05,
+      "loss": 0.6803,
+      "step": 244
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.072216654002935e-05,
+      "loss": 0.7042,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.0649729668948694e-05,
+      "loss": 0.69,
+      "step": 246
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.057713893513403e-05,
+      "loss": 0.6948,
+      "step": 247
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.0504396315495645e-05,
+      "loss": 0.6927,
+      "step": 248
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.043150379108025e-05,
+      "loss": 0.672,
+      "step": 249
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.035846334701699e-05,
+      "loss": 0.6971,
+      "step": 250
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.028527697246343e-05,
+      "loss": 0.6847,
+      "step": 251
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.0211946660551327e-05,
+      "loss": 0.6994,
+      "step": 252
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.013847440833239e-05,
+      "loss": 0.6754,
+      "step": 253
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.006486221672388e-05,
+      "loss": 0.6815,
+      "step": 254
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9991112090454108e-05,
+      "loss": 0.6744,
+      "step": 255
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9917226038007863e-05,
+      "loss": 0.7123,
+      "step": 256
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9843206071571692e-05,
+      "loss": 0.6813,
+      "step": 257
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.976905420697911e-05,
+      "loss": 0.6852,
+      "step": 258
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9694772463655684e-05,
+      "loss": 0.7095,
+      "step": 259
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9620362864564082e-05,
+      "loss": 0.706,
+      "step": 260
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9545827436148932e-05,
+      "loss": 0.7002,
+      "step": 261
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9471168208281648e-05,
+      "loss": 0.6605,
+      "step": 262
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9396387214205173e-05,
+      "loss": 0.6623,
+      "step": 263
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9321486490478565e-05,
+      "loss": 0.6849,
+      "step": 264
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9246468076921578e-05,
+      "loss": 0.6969,
+      "step": 265
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9171334016559078e-05,
+      "loss": 0.6717,
+      "step": 266
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.909608635556542e-05,
+      "loss": 0.6954,
+      "step": 267
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.902072714320871e-05,
+      "loss": 0.6696,
+      "step": 268
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.894525843179501e-05,
+      "loss": 0.6826,
+      "step": 269
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.886968227661244e-05,
+      "loss": 0.6849,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.879400073587521e-05,
+      "loss": 0.6561,
+      "step": 271
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.871821587066756e-05,
+      "loss": 0.7054,
+      "step": 272
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8642329744887623e-05,
+      "loss": 0.6526,
+      "step": 273
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.856634442519124e-05,
+      "loss": 0.7006,
+      "step": 274
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.849026198093565e-05,
+      "loss": 0.6897,
+      "step": 275
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.841408448412317e-05,
+      "loss": 0.6461,
+      "step": 276
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8337814009344716e-05,
+      "loss": 0.6909,
+      "step": 277
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8261452633723356e-05,
+      "loss": 0.6816,
+      "step": 278
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.818500243685771e-05,
+      "loss": 0.6701,
+      "step": 279
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8108465500765315e-05,
+      "loss": 0.7011,
+      "step": 280
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8031843909825953e-05,
+      "loss": 0.69,
+      "step": 281
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.7955139750724858e-05,
+      "loss": 0.6694,
+      "step": 282
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7878355112395887e-05,
+      "loss": 0.6827,
+      "step": 283
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.780149208596465e-05,
+      "loss": 0.6671,
+      "step": 284
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7724552764691545e-05,
+      "loss": 0.6945,
+      "step": 285
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.764753924391477e-05,
+      "loss": 0.68,
+      "step": 286
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7570453620993225e-05,
+      "loss": 0.6665,
+      "step": 287
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7493297995249428e-05,
+      "loss": 0.6869,
+      "step": 288
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7416074467912323e-05,
+      "loss": 0.6758,
+      "step": 289
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.733878514206007e-05,
+      "loss": 0.6896,
+      "step": 290
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7261432122562755e-05,
+      "loss": 0.6797,
+      "step": 291
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7184017516025072e-05,
+      "loss": 0.6884,
+      "step": 292
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7106543430728967e-05,
+      "loss": 0.6531,
+      "step": 293
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7029011976576193e-05,
+      "loss": 0.6692,
+      "step": 294
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.6951425265030883e-05,
+      "loss": 0.6663,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6873785409062012e-05,
+      "loss": 0.6817,
+      "step": 296
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6796094523085885e-05,
+      "loss": 0.6876,
+      "step": 297
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6718354722908543e-05,
+      "loss": 0.6817,
+      "step": 298
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.664056812566812e-05,
+      "loss": 0.6826,
+      "step": 299
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.656273684977722e-05,
+      "loss": 0.6892,
+      "step": 300
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6484863014865212e-05,
+      "loss": 0.6857,
+      "step": 301
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.6406948741720492e-05,
+      "loss": 0.6776,
+      "step": 302
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.6328996152232747e-05,
+      "loss": 0.6547,
+      "step": 303
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.6251007369335137e-05,
+      "loss": 0.6742,
+      "step": 304
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.617298451694653e-05,
+      "loss": 0.6719,
+      "step": 305
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.6094929719913614e-05,
+      "loss": 0.6797,
+      "step": 306
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.601684510395304e-05,
+      "loss": 0.6846,
+      "step": 307
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.5938732795593552e-05,
+      "loss": 0.6777,
+      "step": 308
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.586059492211805e-05,
+      "loss": 0.6561,
+      "step": 309
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.5782433611505658e-05,
+      "loss": 0.6708,
+      "step": 310
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.5704250992373804e-05,
+      "loss": 0.6733,
+      "step": 311
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.5626049193920197e-05,
+      "loss": 0.6656,
+      "step": 312
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.5547830345864887e-05,
+      "loss": 0.6851,
+      "step": 313
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.546959657839223e-05,
+      "loss": 0.6897,
+      "step": 314
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.5391350022092913e-05,
+      "loss": 0.6772,
+      "step": 315
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.5313092807905892e-05,
+      "loss": 0.6664,
+      "step": 316
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.5234827067060387e-05,
+      "loss": 0.6771,
+      "step": 317
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.5156554931017825e-05,
+      "loss": 0.6817,
+      "step": 318
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.5078278531413795e-05,
+      "loss": 0.6699,
+      "step": 319
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.5e-05,
+      "loss": 0.6657,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.4921721468586213e-05,
+      "loss": 0.6913,
+      "step": 321
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.4843445068982178e-05,
+      "loss": 0.6894,
+      "step": 322
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.4765172932939616e-05,
+      "loss": 0.6846,
+      "step": 323
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.4686907192094107e-05,
+      "loss": 0.6518,
+      "step": 324
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.460864997790709e-05,
+      "loss": 0.6762,
+      "step": 325
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.4530403421607774e-05,
+      "loss": 0.6591,
+      "step": 326
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.4452169654135116e-05,
+      "loss": 0.6477,
+      "step": 327
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.4373950806079805e-05,
+      "loss": 0.6711,
+      "step": 328
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.4295749007626199e-05,
+      "loss": 0.6589,
+      "step": 329
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.4217566388494344e-05,
+      "loss": 0.6857,
+      "step": 330
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.4139405077881956e-05,
+      "loss": 0.6907,
+      "step": 331
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.406126720440645e-05,
+      "loss": 0.6897,
+      "step": 332
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.3983154896046962e-05,
+      "loss": 0.6564,
+      "step": 333
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.3905070280086387e-05,
+      "loss": 0.6703,
+      "step": 334
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.382701548305347e-05,
+      "loss": 0.664,
+      "step": 335
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.3748992630664866e-05,
+      "loss": 0.6555,
+      "step": 336
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.3671003847767259e-05,
+      "loss": 0.6859,
+      "step": 337
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.3593051258279512e-05,
+      "loss": 0.6828,
+      "step": 338
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.3515136985134789e-05,
+      "loss": 0.6836,
+      "step": 339
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.3437263150222782e-05,
+      "loss": 0.6757,
+      "step": 340
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.3359431874331888e-05,
+      "loss": 0.6696,
+      "step": 341
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.3281645277091462e-05,
+      "loss": 0.6853,
+      "step": 342
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.3203905476914116e-05,
+      "loss": 0.6705,
+      "step": 343
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.312621459093799e-05,
+      "loss": 0.6695,
+      "step": 344
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.304857473496912e-05,
+      "loss": 0.6804,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.297098802342381e-05,
+      "loss": 0.6812,
+      "step": 346
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.2893456569271036e-05,
+      "loss": 0.6945,
+      "step": 347
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.281598248397493e-05,
+      "loss": 0.6509,
+      "step": 348
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.2738567877437247e-05,
+      "loss": 0.6806,
+      "step": 349
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.2661214857939933e-05,
+      "loss": 0.6799,
+      "step": 350
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.2583925532087681e-05,
+      "loss": 0.6727,
+      "step": 351
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.2506702004750575e-05,
+      "loss": 0.6653,
+      "step": 352
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.242954637900678e-05,
+      "loss": 0.6809,
+      "step": 353
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.235246075608523e-05,
+      "loss": 0.6738,
+      "step": 354
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.2275447235308454e-05,
+      "loss": 0.6654,
+      "step": 355
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.2198507914035357e-05,
+      "loss": 0.6541,
+      "step": 356
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.2121644887604116e-05,
+      "loss": 0.6696,
+      "step": 357
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.2044860249275147e-05,
+      "loss": 0.6656,
+      "step": 358
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.1968156090174045e-05,
+      "loss": 0.7009,
+      "step": 359
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.1891534499234688e-05,
+      "loss": 0.6805,
+      "step": 360
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.1814997563142299e-05,
+      "loss": 0.6777,
+      "step": 361
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.1738547366276648e-05,
+      "loss": 0.6735,
+      "step": 362
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.1662185990655285e-05,
+      "loss": 0.6855,
+      "step": 363
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.1585915515876832e-05,
+      "loss": 0.678,
+      "step": 364
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.150973801906435e-05,
+      "loss": 0.6796,
+      "step": 365
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.1433655574808768e-05,
+      "loss": 0.6588,
+      "step": 366
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.1357670255112379e-05,
+      "loss": 0.6762,
+      "step": 367
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.1281784129332445e-05,
+      "loss": 0.6666,
+      "step": 368
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.1205999264124788e-05,
+      "loss": 0.6739,
+      "step": 369
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.1130317723387562e-05,
+      "loss": 0.6588,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.1054741568204992e-05,
+      "loss": 0.6836,
+      "step": 371
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.0979272856791295e-05,
+      "loss": 0.6659,
+      "step": 372
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.0903913644434587e-05,
+      "loss": 0.6524,
+      "step": 373
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.0828665983440921e-05,
+      "loss": 0.6626,
+      "step": 374
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.0753531923078425e-05,
+      "loss": 0.6531,
+      "step": 375
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.0678513509521436e-05,
+      "loss": 0.6903,
+      "step": 376
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.0603612785794833e-05,
+      "loss": 0.6547,
+      "step": 377
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.0528831791718355e-05,
+      "loss": 0.6785,
+      "step": 378
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.0454172563851072e-05,
+      "loss": 0.6648,
+      "step": 379
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.037963713543592e-05,
+      "loss": 0.6711,
+      "step": 380
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.0305227536344315e-05,
+      "loss": 0.6746,
+      "step": 381
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.0230945793020896e-05,
+      "loss": 0.6571,
+      "step": 382
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.015679392842831e-05,
+      "loss": 0.6527,
+      "step": 383
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.0082773961992134e-05,
+      "loss": 0.6639,
+      "step": 384
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.0008887909545892e-05,
+      "loss": 0.6692,
+      "step": 385
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.93513778327612e-06,
+      "loss": 0.6476,
+      "step": 386
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.86152559166761e-06,
+      "loss": 0.6693,
+      "step": 387
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.788053339448676e-06,
+      "loss": 0.6757,
+      "step": 388
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.71472302753657e-06,
+      "loss": 0.6538,
+      "step": 389
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.64153665298301e-06,
+      "loss": 0.6764,
+      "step": 390
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.568496208919752e-06,
+      "loss": 0.6782,
+      "step": 391
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.495603684504356e-06,
+      "loss": 0.6636,
+      "step": 392
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.422861064865974e-06,
+      "loss": 0.6572,
+      "step": 393
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.350270331051307e-06,
+      "loss": 0.6717,
+      "step": 394
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.277833459970657e-06,
+      "loss": 0.6626,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.205552424344078e-06,
+      "loss": 0.6557,
+      "step": 396
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.133429192647661e-06,
+      "loss": 0.6786,
+      "step": 397
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.061465729059918e-06,
+      "loss": 0.6863,
+      "step": 398
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.989663993408286e-06,
+      "loss": 0.6953,
+      "step": 399
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.91802594111578e-06,
+      "loss": 0.6529,
+      "step": 400
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.846553523147695e-06,
+      "loss": 0.6736,
+      "step": 401
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.775248685958526e-06,
+      "loss": 0.6552,
+      "step": 402
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.704113371438907e-06,
+      "loss": 0.658,
+      "step": 403
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.633149516862777e-06,
+      "loss": 0.6607,
+      "step": 404
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.562359054834574e-06,
+      "loss": 0.6745,
+      "step": 405
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.491743913236629e-06,
+      "loss": 0.6748,
+      "step": 406
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.421306015176677e-06,
+      "loss": 0.6648,
+      "step": 407
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.351047278935443e-06,
+      "loss": 0.6497,
+      "step": 408
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.280969617914427e-06,
+      "loss": 0.6842,
+      "step": 409
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.211074940583807e-06,
+      "loss": 0.6424,
+      "step": 410
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.141365150430423e-06,
+      "loss": 0.6695,
+      "step": 411
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.071842145905988e-06,
+      "loss": 0.6587,
+      "step": 412
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.002507820375342e-06,
+      "loss": 0.6602,
+      "step": 413
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.933364062064914e-06,
+      "loss": 0.6345,
+      "step": 414
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.864412754011303e-06,
+      "loss": 0.6601,
+      "step": 415
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.795655774009967e-06,
+      "loss": 0.6338,
+      "step": 416
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.727094994564123e-06,
+      "loss": 0.6599,
+      "step": 417
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.658732282833721e-06,
+      "loss": 0.6751,
+      "step": 418
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.590569500584597e-06,
+      "loss": 0.6762,
+      "step": 419
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.522608504137799e-06,
+      "loss": 0.6748,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.454851144318987e-06,
+      "loss": 0.67,
+      "step": 421
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.3872992664080845e-06,
+      "loss": 0.6793,
+      "step": 422
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.3199547100889635e-06,
+      "loss": 0.6494,
+      "step": 423
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.2528193093993835e-06,
+      "loss": 0.6762,
+      "step": 424
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.185894892681048e-06,
+      "loss": 0.6485,
+      "step": 425
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.119183282529772e-06,
+      "loss": 0.6787,
+      "step": 426
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.052686295745899e-06,
+      "loss": 0.6633,
+      "step": 427
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.986405743284776e-06,
+      "loss": 0.6638,
+      "step": 428
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.920343430207455e-06,
+      "loss": 0.6499,
+      "step": 429
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.854501155631553e-06,
+      "loss": 0.6632,
+      "step": 430
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.788880712682212e-06,
+      "loss": 0.6423,
+      "step": 431
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.72348388844331e-06,
+      "loss": 0.6747,
+      "step": 432
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.658312463908763e-06,
+      "loss": 0.6632,
+      "step": 433
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.593368213934023e-06,
+      "loss": 0.6534,
+      "step": 434
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.528652907187774e-06,
+      "loss": 0.6441,
+      "step": 435
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.46416830610372e-06,
+      "loss": 0.6463,
+      "step": 436
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.39991616683261e-06,
+      "loss": 0.6642,
+      "step": 437
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.335898239194431e-06,
+      "loss": 0.6728,
+      "step": 438
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.27211626663071e-06,
+      "loss": 0.6566,
+      "step": 439
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.208571986157068e-06,
+      "loss": 0.6737,
+      "step": 440
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.145267128315897e-06,
+      "loss": 0.6633,
+      "step": 441
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.082203417129252e-06,
+      "loss": 0.6456,
+      "step": 442
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.019382570051874e-06,
+      "loss": 0.6604,
+      "step": 443
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.956806297924426e-06,
+      "loss": 0.6463,
+      "step": 444
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.894476304926917e-06,
+      "loss": 0.6336,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.832394288532261e-06,
+      "loss": 0.6498,
+      "step": 446
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.770561939460085e-06,
+      "loss": 0.649,
+      "step": 447
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.708980941630648e-06,
+      "loss": 0.6479,
+      "step": 448
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.647652972118998e-06,
+      "loss": 0.6544,
+      "step": 449
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.586579701109316e-06,
+      "loss": 0.6672,
+      "step": 450
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.525762791849396e-06,
+      "loss": 0.6377,
+      "step": 451
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.465203900605381e-06,
+      "loss": 0.6561,
+      "step": 452
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.404904676616634e-06,
+      "loss": 0.6439,
+      "step": 453
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.344866762050831e-06,
+      "loss": 0.666,
+      "step": 454
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.2850917919592496e-06,
+      "loss": 0.6604,
+      "step": 455
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.22558139423222e-06,
+      "loss": 0.6531,
+      "step": 456
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.1663371895548135e-06,
+      "loss": 0.632,
+      "step": 457
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.1073607913626844e-06,
+      "loss": 0.675,
+      "step": 458
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.048653805798138e-06,
+      "loss": 0.6424,
+      "step": 459
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.99021783166641e-06,
+      "loss": 0.66,
+      "step": 460
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.932054460392082e-06,
+      "loss": 0.6559,
+      "step": 461
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.8741652759757915e-06,
+      "loss": 0.6646,
+      "step": 462
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.8165518549510476e-06,
+      "loss": 0.6756,
+      "step": 463
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.7592157663413195e-06,
+      "loss": 0.6445,
+      "step": 464
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.70215857161732e-06,
+      "loss": 0.6625,
+      "step": 465
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.645381824654444e-06,
+      "loss": 0.6372,
+      "step": 466
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.588887071690491e-06,
+      "loss": 0.653,
+      "step": 467
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.532675851283522e-06,
+      "loss": 0.6484,
+      "step": 468
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.476749694269972e-06,
+      "loss": 0.6638,
+      "step": 469
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.421110123722973e-06,
+      "loss": 0.6513,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.365758654910855e-06,
+      "loss": 0.6703,
+      "step": 471
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.310696795255885e-06,
+      "loss": 0.6336,
+      "step": 472
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.255926044293216e-06,
+      "loss": 0.6557,
+      "step": 473
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.201447893630065e-06,
+      "loss": 0.641,
+      "step": 474
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.147263826905059e-06,
+      "loss": 0.6607,
+      "step": 475
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.093375319747849e-06,
+      "loss": 0.6619,
+      "step": 476
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.039783839738937e-06,
+      "loss": 0.6575,
+      "step": 477
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.986490846369674e-06,
+      "loss": 0.6526,
+      "step": 478
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.933497791002547e-06,
+      "loss": 0.6655,
+      "step": 479
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.880806116831625e-06,
+      "loss": 0.6429,
+      "step": 480
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.828417258843272e-06,
+      "loss": 0.6545,
+      "step": 481
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.7763326437770757e-06,
+      "loss": 0.6499,
+      "step": 482
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.724553690086959e-06,
+      "loss": 0.6471,
+      "step": 483
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.6730818079025926e-06,
+      "loss": 0.6649,
+      "step": 484
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.6219183989909528e-06,
+      "loss": 0.6546,
+      "step": 485
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.5710648567181725e-06,
+      "loss": 0.665,
+      "step": 486
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.52052256601159e-06,
+      "loss": 0.6672,
+      "step": 487
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.4702929033220176e-06,
+      "loss": 0.6583,
+      "step": 488
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.4203772365862835e-06,
+      "loss": 0.6856,
+      "step": 489
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.3707769251899463e-06,
+      "loss": 0.6614,
+      "step": 490
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.3214933199302915e-06,
+      "loss": 0.6712,
+      "step": 491
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.272527762979553e-06,
+      "loss": 0.6562,
+      "step": 492
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.2238815878483357e-06,
+      "loss": 0.6517,
+      "step": 493
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.175556119349326e-06,
+      "loss": 0.6514,
+      "step": 494
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.12755267356119e-06,
+      "loss": 0.6519,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.07987255779274e-06,
+      "loss": 0.6721,
+      "step": 496
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.032517070547348e-06,
+      "loss": 0.6442,
+      "step": 497
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.9854875014875495e-06,
+      "loss": 0.6488,
+      "step": 498
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.9387851313999555e-06,
+      "loss": 0.6445,
+      "step": 499
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.8924112321603456e-06,
+      "loss": 0.6612,
+      "step": 500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.846367066699041e-06,
+      "loss": 0.6561,
+      "step": 501
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.8006538889665194e-06,
+      "loss": 0.6589,
+      "step": 502
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.7552729438992486e-06,
+      "loss": 0.6379,
+      "step": 503
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.710225467385788e-06,
+      "loss": 0.6169,
+      "step": 504
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.6655126862331354e-06,
+      "loss": 0.6592,
+      "step": 505
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.621135818133321e-06,
+      "loss": 0.6792,
+      "step": 506
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.5770960716302274e-06,
+      "loss": 0.643,
+      "step": 507
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.5333946460866875e-06,
+      "loss": 0.6683,
+      "step": 508
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.490032731651833e-06,
+      "loss": 0.6676,
+      "step": 509
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.447011509228659e-06,
+      "loss": 0.6738,
+      "step": 510
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.4043321504418725e-06,
+      "loss": 0.6536,
+      "step": 511
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.3619958176060038e-06,
+      "loss": 0.6744,
+      "step": 512
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.320003663693718e-06,
+      "loss": 0.6374,
+      "step": 513
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.2783568323044484e-06,
+      "loss": 0.644,
+      "step": 514
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.2370564576332254e-06,
+      "loss": 0.6675,
+      "step": 515
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.1961036644398034e-06,
+      "loss": 0.6605,
+      "step": 516
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.155499568018034e-06,
+      "loss": 0.6561,
+      "step": 517
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.11524527416547e-06,
+      "loss": 0.6564,
+      "step": 518
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.07534187915328e-06,
+      "loss": 0.661,
+      "step": 519
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.0357904696963696e-06,
+      "loss": 0.6591,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.996592122923791e-06,
+      "loss": 0.6595,
+      "step": 521
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.9577479063494263e-06,
+      "loss": 0.6546,
+      "step": 522
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.9192588778428844e-06,
+      "loss": 0.6511,
+      "step": 523
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.8811260856007246e-06,
+      "loss": 0.6696,
+      "step": 524
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.8433505681178835e-06,
+      "loss": 0.646,
+      "step": 525
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.8059333541594015e-06,
+      "loss": 0.6612,
+      "step": 526
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7688754627324182e-06,
+      "loss": 0.6761,
+      "step": 527
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7321779030584022e-06,
+      "loss": 0.6783,
+      "step": 528
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6958416745456829e-06,
+      "loss": 0.6575,
+      "step": 529
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6598677667622176e-06,
+      "loss": 0.6424,
+      "step": 530
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6242571594086487e-06,
+      "loss": 0.6536,
+      "step": 531
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.5890108222916311e-06,
+      "loss": 0.6722,
+      "step": 532
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.554129715297407e-06,
+      "loss": 0.6739,
+      "step": 533
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.5196147883656752e-06,
+      "loss": 0.6712,
+      "step": 534
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.4854669814637145e-06,
+      "loss": 0.6634,
+      "step": 535
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.4516872245607816e-06,
+      "loss": 0.6601,
+      "step": 536
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.4182764376028007e-06,
+      "loss": 0.6306,
+      "step": 537
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.3852355304872928e-06,
+      "loss": 0.6671,
+      "step": 538
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.352565403038604e-06,
+      "loss": 0.6445,
+      "step": 539
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.3202669449833943e-06,
+      "loss": 0.6716,
+      "step": 540
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2883410359264219e-06,
+      "loss": 0.6546,
+      "step": 541
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2567885453265653e-06,
+      "loss": 0.6616,
+      "step": 542
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2256103324731627e-06,
+      "loss": 0.6658,
+      "step": 543
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.1948072464626102e-06,
+      "loss": 0.6756,
+      "step": 544
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.1643801261752235e-06,
+      "loss": 0.6577,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.1343298002524027e-06,
+      "loss": 0.6617,
+      "step": 546
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.1046570870740718e-06,
+      "loss": 0.6414,
+      "step": 547
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.0753627947363709e-06,
+      "loss": 0.6282,
+      "step": 548
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.0464477210296752e-06,
+      "loss": 0.6308,
+      "step": 549
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.0179126534168415e-06,
+      "loss": 0.6623,
+      "step": 550
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.897583690117813e-07,
+      "loss": 0.6504,
+      "step": 551
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.619856345582911e-07,
+      "loss": 0.6543,
+      "step": 552
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.345952064091718e-07,
+      "loss": 0.642,
+      "step": 553
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.075878305056284e-07,
+      "loss": 0.6407,
+      "step": 554
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.80964242356958e-07,
+      "loss": 0.6494,
+      "step": 555
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.547251670205147e-07,
+      "loss": 0.647,
+      "step": 556
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.288713190819758e-07,
+      "loss": 0.6616,
+      "step": 557
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.034034026358589e-07,
+      "loss": 0.657,
+      "step": 558
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.783221112663757e-07,
+      "loss": 0.6627,
+      "step": 559
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.536281280285156e-07,
+      "loss": 0.6636,
+      "step": 560
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.293221254294586e-07,
+      "loss": 0.6591,
+      "step": 561
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.05404765410263e-07,
+      "loss": 0.653,
+      "step": 562
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.818766993278241e-07,
+      "loss": 0.6587,
+      "step": 563
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.587385679371527e-07,
+      "loss": 0.659,
+      "step": 564
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.359910013739123e-07,
+      "loss": 0.6789,
+      "step": 565
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.136346191372582e-07,
+      "loss": 0.6499,
+      "step": 566
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.916700300729827e-07,
+      "loss": 0.6653,
+      "step": 567
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.700978323569061e-07,
+      "loss": 0.6673,
+      "step": 568
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.489186134786173e-07,
+      "loss": 0.6495,
+      "step": 569
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.281329502254489e-07,
+      "loss": 0.6466,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.077414086667792e-07,
+      "loss": 0.6553,
+      "step": 571
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.877445441386219e-07,
+      "loss": 0.6712,
+      "step": 572
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.681429012284921e-07,
+      "loss": 0.6615,
+      "step": 573
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.489370137605814e-07,
+      "loss": 0.6401,
+      "step": 574
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.3012740478121595e-07,
+      "loss": 0.647,
+      "step": 575
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.1171458654461644e-07,
+      "loss": 0.6583,
+      "step": 576
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.9369906049894435e-07,
+      "loss": 0.6597,
+      "step": 577
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.760813172726457e-07,
+      "loss": 0.643,
+      "step": 578
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.588618366610941e-07,
+      "loss": 0.6689,
+      "step": 579
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.4204108761351214e-07,
+      "loss": 0.6574,
+      "step": 580
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.2561952822021735e-07,
+      "loss": 0.6379,
+      "step": 581
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.095976057001332e-07,
+      "loss": 0.6415,
+      "step": 582
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.9397575638861416e-07,
+      "loss": 0.6556,
+      "step": 583
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.787544057255653e-07,
+      "loss": 0.6292,
+      "step": 584
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.639339682438496e-07,
+      "loss": 0.6759,
+      "step": 585
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.495148475580089e-07,
+      "loss": 0.6475,
+      "step": 586
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.3549743635325914e-07,
+      "loss": 0.6688,
+      "step": 587
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.2188211637480416e-07,
+      "loss": 0.6398,
+      "step": 588
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.086692584174438e-07,
+      "loss": 0.6675,
+      "step": 589
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.958592223154604e-07,
+      "loss": 0.6431,
+      "step": 590
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.8345235693283835e-07,
+      "loss": 0.6493,
+      "step": 591
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.7144900015374666e-07,
+      "loss": 0.6634,
+      "step": 592
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5984947887334622e-07,
+      "loss": 0.6646,
+      "step": 593
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.4865410898888875e-07,
+      "loss": 0.6755,
+      "step": 594
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.3786319539110191e-07,
+      "loss": 0.6517,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.2747703195590432e-07,
+      "loss": 0.6442,
+      "step": 596
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1749590153638524e-07,
+      "loss": 0.6653,
+      "step": 597
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0792007595510911e-07,
+      "loss": 0.6346,
+      "step": 598
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.874981599671484e-08,
+      "loss": 0.6534,
+      "step": 599
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.998537140081143e-08,
+      "loss": 0.647,
+      "step": 600
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.162698085517173e-08,
+      "loss": 0.6583,
+      "step": 601
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.367487198924106e-08,
+      "loss": 0.6525,
+      "step": 602
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.612926136793207e-08,
+      "loss": 0.6536,
+      "step": 603
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.899035448572621e-08,
+      "loss": 0.6546,
+      "step": 604
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.225834576108313e-08,
+      "loss": 0.6654,
+      "step": 605
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.593341853114164e-08,
+      "loss": 0.6448,
+      "step": 606
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.0015745046725336e-08,
+      "loss": 0.6473,
+      "step": 607
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.4505486467654725e-08,
+      "loss": 0.6412,
+      "step": 608
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.9402792858359007e-08,
+      "loss": 0.638,
+      "step": 609
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.4707803183784407e-08,
+      "loss": 0.6524,
+      "step": 610
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.0420645305617158e-08,
+      "loss": 0.6531,
+      "step": 611
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.654143597879132e-08,
+      "loss": 0.6422,
+      "step": 612
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3070280848319627e-08,
+      "loss": 0.6528,
+      "step": 613
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0007274446409143e-08,
+      "loss": 0.648,
+      "step": 614
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.352500189891642e-09,
+      "loss": 0.6459,
+      "step": 615
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.106030377945437e-09,
+      "loss": 0.6581,
+      "step": 616
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.2679261901319424e-09,
+      "loss": 0.6712,
+      "step": 617
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.8382376847320137e-09,
+      "loss": 0.6489,
+      "step": 618
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.170037973737054e-10,
+      "loss": 0.6542,
+      "step": 619
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.0425233997645177e-10,
+      "loss": 0.662,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.6322,
+      "step": 621
+    },
+    {
+      "epoch": 1.0,
+      "step": 621,
+      "total_flos": 1.1837910281302835e+18,
+      "train_loss": 0.7008271510090421,
+      "train_runtime": 50081.8172,
+      "train_samples_per_second": 1.59,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "max_steps": 621,
+  "num_train_epochs": 1,
+  "total_flos": 1.1837910281302835e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9af53a0c93400db979d74723f9dd5e83ff7048449f8c8a3ca5993457be81c02
+size 4664