Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<im_end>": 32003,
+  "<im_patch>": 32001,
+  "<im_start>": 32002,
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "alexshengzhili/vicuna-7b-v0",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "mm_hidden_size": 1024,
+  "mm_use_im_start_end": true,
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14",
+  "model_type": "llava",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "sep_image_conv_front": false,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vocab_size": 32004
+}

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"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0589f81e58a6b58144ce5670f10fdcf5ffa9471ca405d1fc1bfab8a72f53e0b7
+size 6742674890

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebec5d6826dc0fa5080558695efd48a9ee5585da37664ed2f08e7fe60db4f5ec
+size 9878059026

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5432547201c8b5aa2de649ae007fa3362009d1bebe81bdf3493afd88137b7252
+size 9894805046

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4653b00a31d598a6c6df3c29b8cb052a9a17af88ef72adfebb820954cae7b65
+size 7197853429

pytorch_model.bin.index.json

@@ -0,0 +1,332 @@
+{
+  "metadata": {
+    "total_size": 26970595328
+  },
+  "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.mm_projector.bias": "pytorch_model-00003-of-00003.bin",
+    "model.mm_projector.weight": "pytorch_model-00003-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a961c7aa8293531040f379f129f1930093670f11c91d3736bf6d8518af2b1507
+size 14583

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc4475e8615a434844642d2b6db8c82a3eb4d1532c0358142650af35982f7d4
+size 14583

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881eb4ea22a97cf8b6f92b147ff4c6e2ae57dcc7e36f52b570b5be3eeb7887b6
+size 14583

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b494daea51340989a686bc325649dfd2d62f65af56b0d25143e33790c8a957a
+size 14583

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a88b3a9b9d34f9c56a628c06043f3d84338d75c0f6730bf31d21d05f60a24e7
+size 14583

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1556e939ee7eca3367a22108d1bd8653197711d2ab29b9fc7633bec21b96125
+size 14583

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e9ed27d35f586c7ec30600373ad7abf89086510211847110cb4a979365cfa0
+size 14583

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1828f5f1b78bdfd59c65a849162815831fbce941a063f6c4056e93648685a2ec
+size 14583

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a263831488bd0dc14c4e90b72806a981f938f1c27e60121054b4dc51b2c55a
+size 627

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": "[PAD]",
+  "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": "/root/.cache/huggingface/hub/models--lmsys--vicuna-7b-delta-v1.1/snapshots/59055f912e1c5cee762a793eda99d51e80807f11/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 +1,3016 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1111111111111112,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.9268292682926833e-06,
+      "loss": 2.0292,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.853658536585367e-06,
+      "loss": 2.0417,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.780487804878048e-06,
+      "loss": 1.5471,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1707317073170733e-05,
+      "loss": 1.4769,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4634146341463415e-05,
+      "loss": 1.3682,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7560975609756096e-05,
+      "loss": 1.3256,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.048780487804878e-05,
+      "loss": 1.317,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3414634146341466e-05,
+      "loss": 1.3441,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.6341463414634148e-05,
+      "loss": 1.3028,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.926829268292683e-05,
+      "loss": 1.3212,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2195121951219514e-05,
+      "loss": 1.2535,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.512195121951219e-05,
+      "loss": 1.2933,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.804878048780488e-05,
+      "loss": 1.2811,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.097560975609756e-05,
+      "loss": 1.304,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.390243902439024e-05,
+      "loss": 1.3205,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.682926829268293e-05,
+      "loss": 1.2825,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.975609756097561e-05,
+      "loss": 1.2774,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.2682926829268296e-05,
+      "loss": 1.2641,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.560975609756098e-05,
+      "loss": 1.2429,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.853658536585366e-05,
+      "loss": 1.2503,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.146341463414634e-05,
+      "loss": 1.2882,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.439024390243903e-05,
+      "loss": 1.3068,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.731707317073171e-05,
+      "loss": 1.2592,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.024390243902439e-05,
+      "loss": 1.2538,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.317073170731707e-05,
+      "loss": 1.3129,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.609756097560976e-05,
+      "loss": 1.2578,
+      "step": 26
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.902439024390244e-05,
+      "loss": 1.2534,
+      "step": 27
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.195121951219513e-05,
+      "loss": 1.3043,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.48780487804878e-05,
+      "loss": 1.2677,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.780487804878048e-05,
+      "loss": 1.2535,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.073170731707318e-05,
+      "loss": 1.2639,
+      "step": 31
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.365853658536587e-05,
+      "loss": 1.3038,
+      "step": 32
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.658536585365855e-05,
+      "loss": 1.2966,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.951219512195122e-05,
+      "loss": 1.2355,
+      "step": 34
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001024390243902439,
+      "loss": 1.2861,
+      "step": 35
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00010536585365853659,
+      "loss": 1.3257,
+      "step": 36
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00010829268292682928,
+      "loss": 1.3195,
+      "step": 37
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00011121951219512196,
+      "loss": 1.3274,
+      "step": 38
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011414634146341463,
+      "loss": 1.2388,
+      "step": 39
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011707317073170732,
+      "loss": 1.2686,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00012,
+      "loss": 1.274,
+      "step": 41
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011999982720089112,
+      "loss": 1.2754,
+      "step": 42
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00011999930880455974,
+      "loss": 1.2609,
+      "step": 43
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00011999844481399185,
+      "loss": 1.3151,
+      "step": 44
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00011999723523416397,
+      "loss": 1.3002,
+      "step": 45
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00011999568007204328,
+      "loss": 1.2993,
+      "step": 46
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00011999377933658745,
+      "loss": 1.301,
+      "step": 47
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00011999153303874466,
+      "loss": 1.3308,
+      "step": 48
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00011998894119145353,
+      "loss": 1.2533,
+      "step": 49
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00011998600380964302,
+      "loss": 1.2932,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00011998272091023235,
+      "loss": 1.2577,
+      "step": 51
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00011997909251213094,
+      "loss": 1.3185,
+      "step": 52
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00011997511863623823,
+      "loss": 1.2698,
+      "step": 53
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00011997079930544366,
+      "loss": 1.2681,
+      "step": 54
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00011996613454462643,
+      "loss": 1.2688,
+      "step": 55
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001199611243806554,
+      "loss": 1.2947,
+      "step": 56
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000119955768842389,
+      "loss": 1.3007,
+      "step": 57
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00011995006796067497,
+      "loss": 1.2609,
+      "step": 58
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00011994402176835021,
+      "loss": 1.3019,
+      "step": 59
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001199376303002406,
+      "loss": 1.3291,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00011993089359316082,
+      "loss": 1.271,
+      "step": 61
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00011992381168591412,
+      "loss": 1.3238,
+      "step": 62
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00011991638461929203,
+      "loss": 1.325,
+      "step": 63
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00011990861243607424,
+      "loss": 1.249,
+      "step": 64
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00011990049518102833,
+      "loss": 1.2804,
+      "step": 65
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00011989203290090944,
+      "loss": 1.2872,
+      "step": 66
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00011988322564446003,
+      "loss": 1.3123,
+      "step": 67
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00011987407346240964,
+      "loss": 1.3108,
+      "step": 68
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00011986457640747457,
+      "loss": 1.3069,
+      "step": 69
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00011985473453435758,
+      "loss": 1.2944,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00011984454789974758,
+      "loss": 1.2525,
+      "step": 71
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00011983401656231926,
+      "loss": 1.2582,
+      "step": 72
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001198231405827328,
+      "loss": 1.3009,
+      "step": 73
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00011981192002363357,
+      "loss": 1.3136,
+      "step": 74
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00011980035494965159,
+      "loss": 1.2795,
+      "step": 75
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001197884454274014,
+      "loss": 1.3302,
+      "step": 76
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00011977619152548147,
+      "loss": 1.3062,
+      "step": 77
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001197635933144739,
+      "loss": 1.2965,
+      "step": 78
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00011975065086694404,
+      "loss": 1.27,
+      "step": 79
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00011973736425743998,
+      "loss": 1.2587,
+      "step": 80
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001197237335624922,
+      "loss": 1.3065,
+      "step": 81
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00011970975886061309,
+      "loss": 1.2612,
+      "step": 82
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00011969544023229654,
+      "loss": 1.317,
+      "step": 83
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011968077776001742,
+      "loss": 1.3093,
+      "step": 84
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011966577152823111,
+      "loss": 1.2632,
+      "step": 85
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011965042162337308,
+      "loss": 1.2846,
+      "step": 86
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011963472813385833,
+      "loss": 1.3133,
+      "step": 87
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00011961869115008088,
+      "loss": 1.3272,
+      "step": 88
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001196023107644133,
+      "loss": 1.2728,
+      "step": 89
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001195855870712061,
+      "loss": 1.2478,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00011956852016678727,
+      "loss": 1.2854,
+      "step": 91
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00011955111014946166,
+      "loss": 1.2712,
+      "step": 92
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00011953335711951047,
+      "loss": 1.2605,
+      "step": 93
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00011951526117919063,
+      "loss": 1.3021,
+      "step": 94
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00011949682243273419,
+      "loss": 1.2482,
+      "step": 95
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001194780409863478,
+      "loss": 1.2801,
+      "step": 96
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00011945891694821206,
+      "loss": 1.2746,
+      "step": 97
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001194394504284808,
+      "loss": 1.28,
+      "step": 98
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00011941964153928065,
+      "loss": 1.2296,
+      "step": 99
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00011939949039471018,
+      "loss": 1.2531,
+      "step": 100
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00011937899711083942,
+      "loss": 1.2641,
+      "step": 101
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011935816180570905,
+      "loss": 1.3043,
+      "step": 102
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011933698459932983,
+      "loss": 1.2511,
+      "step": 103
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011931546561368184,
+      "loss": 1.2838,
+      "step": 104
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011929360497271377,
+      "loss": 1.2616,
+      "step": 105
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0001192714028023423,
+      "loss": 1.3006,
+      "step": 106
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011924885923045124,
+      "loss": 1.2762,
+      "step": 107
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011922597438689093,
+      "loss": 1.2797,
+      "step": 108
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011920274840347734,
+      "loss": 1.2526,
+      "step": 109
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011917918141399149,
+      "loss": 1.2742,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001191552735541785,
+      "loss": 1.2698,
+      "step": 111
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011913102496174698,
+      "loss": 1.2516,
+      "step": 112
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011910643577636807,
+      "loss": 1.2814,
+      "step": 113
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011908150613967473,
+      "loss": 1.3506,
+      "step": 114
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011905623619526097,
+      "loss": 1.3044,
+      "step": 115
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001190306260886809,
+      "loss": 1.2427,
+      "step": 116
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011900467596744797,
+      "loss": 1.3192,
+      "step": 117
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011897838598103412,
+      "loss": 1.2457,
+      "step": 118
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011895175628086887,
+      "loss": 1.2686,
+      "step": 119
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0001189247870203385,
+      "loss": 1.2782,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011889747835478518,
+      "loss": 1.3098,
+      "step": 121
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011886983044150598,
+      "loss": 1.266,
+      "step": 122
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011884184343975209,
+      "loss": 1.2918,
+      "step": 123
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011881351751072778,
+      "loss": 1.2611,
+      "step": 124
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011878485281758958,
+      "loss": 1.2192,
+      "step": 125
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011875584952544527,
+      "loss": 1.3018,
+      "step": 126
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011872650780135294,
+      "loss": 1.304,
+      "step": 127
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011869682781432005,
+      "loss": 1.3303,
+      "step": 128
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00011866680973530246,
+      "loss": 1.2869,
+      "step": 129
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00011863645373720338,
+      "loss": 1.2533,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00011860575999487249,
+      "loss": 1.2678,
+      "step": 131
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00011857472868510483,
+      "loss": 1.2895,
+      "step": 132
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001185433599866398,
+      "loss": 1.3199,
+      "step": 133
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001185116540801602,
+      "loss": 1.264,
+      "step": 134
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00011847961114829109,
+      "loss": 1.2979,
+      "step": 135
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001184472313755988,
+      "loss": 1.2764,
+      "step": 136
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001184145149485899,
+      "loss": 1.286,
+      "step": 137
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00011838146205571,
+      "loss": 1.2782,
+      "step": 138
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00011834807288734277,
+      "loss": 1.2893,
+      "step": 139
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00011831434763580886,
+      "loss": 1.2874,
+      "step": 140
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001182802864953647,
+      "loss": 1.3005,
+      "step": 141
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00011824588966220147,
+      "loss": 1.2885,
+      "step": 142
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00011821115733444388,
+      "loss": 1.291,
+      "step": 143
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00011817608971214912,
+      "loss": 1.2475,
+      "step": 144
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00011814068699730562,
+      "loss": 1.2787,
+      "step": 145
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00011810494939383203,
+      "loss": 1.2816,
+      "step": 146
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00011806887710757583,
+      "loss": 1.3126,
+      "step": 147
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00011803247034631235,
+      "loss": 1.3111,
+      "step": 148
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00011799572931974343,
+      "loss": 1.2751,
+      "step": 149
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001179586542394963,
+      "loss": 1.232,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00011792124531912233,
+      "loss": 1.2673,
+      "step": 151
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00011788350277409578,
+      "loss": 1.2299,
+      "step": 152
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00011784542682181257,
+      "loss": 1.2662,
+      "step": 153
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001178070176815891,
+      "loss": 1.2464,
+      "step": 154
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00011776827557466086,
+      "loss": 1.2414,
+      "step": 155
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00011772920072418121,
+      "loss": 1.254,
+      "step": 156
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00011768979335522015,
+      "loss": 1.2713,
+      "step": 157
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00011765005369476294,
+      "loss": 1.2481,
+      "step": 158
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00011760998197170885,
+      "loss": 1.2539,
+      "step": 159
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00011756957841686985,
+      "loss": 1.2687,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00011752884326296917,
+      "loss": 1.2749,
+      "step": 161
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00011748777674464008,
+      "loss": 1.2518,
+      "step": 162
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00011744637909842455,
+      "loss": 1.3132,
+      "step": 163
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00011740465056277176,
+      "loss": 1.3026,
+      "step": 164
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00011736259137803685,
+      "loss": 1.2225,
+      "step": 165
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00011732020178647945,
+      "loss": 1.2805,
+      "step": 166
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001172774820322624,
+      "loss": 1.2332,
+      "step": 167
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00011723443236145015,
+      "loss": 1.2702,
+      "step": 168
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00011719105302200757,
+      "loss": 1.2665,
+      "step": 169
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00011714734426379837,
+      "loss": 1.2261,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00011710330633858367,
+      "loss": 1.2395,
+      "step": 171
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00011705893950002063,
+      "loss": 1.2588,
+      "step": 172
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0001170142440036609,
+      "loss": 1.2609,
+      "step": 173
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00011696922010694925,
+      "loss": 1.2454,
+      "step": 174
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00011692386806922196,
+      "loss": 1.2901,
+      "step": 175
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00011687818815170541,
+      "loss": 1.2764,
+      "step": 176
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001168321806175146,
+      "loss": 1.2632,
+      "step": 177
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00011678584573165155,
+      "loss": 1.2594,
+      "step": 178
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001167391837610038,
+      "loss": 1.2609,
+      "step": 179
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00011669219497434297,
+      "loss": 1.2928,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00011664487964232302,
+      "loss": 1.2612,
+      "step": 181
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00011659723803747888,
+      "loss": 1.3024,
+      "step": 182
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00011654927043422479,
+      "loss": 1.2663,
+      "step": 183
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001165009771088527,
+      "loss": 1.2345,
+      "step": 184
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00011645235833953074,
+      "loss": 1.3054,
+      "step": 185
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00011640341440630155,
+      "loss": 1.2414,
+      "step": 186
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00011635414559108078,
+      "loss": 1.304,
+      "step": 187
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00011630455217765531,
+      "loss": 1.2611,
+      "step": 188
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00011625463445168175,
+      "loss": 1.2403,
+      "step": 189
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00011620439270068469,
+      "loss": 1.2718,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00011615382721405513,
+      "loss": 1.2647,
+      "step": 191
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001161029382830488,
+      "loss": 1.2481,
+      "step": 192
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00011605172620078439,
+      "loss": 1.25,
+      "step": 193
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.000116000191262242,
+      "loss": 1.2761,
+      "step": 194
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00011594833376426134,
+      "loss": 1.3131,
+      "step": 195
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011589615400554007,
+      "loss": 1.222,
+      "step": 196
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011584365228663202,
+      "loss": 1.2354,
+      "step": 197
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011579082890994557,
+      "loss": 1.2224,
+      "step": 198
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011573768417974176,
+      "loss": 1.2783,
+      "step": 199
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011568421840213267,
+      "loss": 1.2999,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011563043188507961,
+      "loss": 1.2273,
+      "step": 201
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0001155763249383913,
+      "loss": 1.2849,
+      "step": 202
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011552189787372217,
+      "loss": 1.2166,
+      "step": 203
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011546715100457046,
+      "loss": 1.2472,
+      "step": 204
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011541208464627652,
+      "loss": 1.2523,
+      "step": 205
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011535669911602097,
+      "loss": 1.2413,
+      "step": 206
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011530099473282279,
+      "loss": 1.2395,
+      "step": 207
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011524497181753759,
+      "loss": 1.2717,
+      "step": 208
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011518863069285567,
+      "loss": 1.2152,
+      "step": 209
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011513197168330026,
+      "loss": 1.2583,
+      "step": 210
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011507499511522556,
+      "loss": 1.2311,
+      "step": 211
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011501770131681491,
+      "loss": 1.276,
+      "step": 212
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001149600906180789,
+      "loss": 1.2171,
+      "step": 213
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011490216335085345,
+      "loss": 1.2381,
+      "step": 214
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011484391984879785,
+      "loss": 1.2577,
+      "step": 215
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.000114785360447393,
+      "loss": 1.2659,
+      "step": 216
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011472648548393928,
+      "loss": 1.2436,
+      "step": 217
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011466729529755472,
+      "loss": 1.2542,
+      "step": 218
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00011460779022917307,
+      "loss": 1.2525,
+      "step": 219
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00011454797062154173,
+      "loss": 1.2511,
+      "step": 220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00011448783681921988,
+      "loss": 1.2654,
+      "step": 221
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00011442738916857643,
+      "loss": 1.2532,
+      "step": 222
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00011436662801778805,
+      "loss": 1.2714,
+      "step": 223
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00011430555371683716,
+      "loss": 1.2708,
+      "step": 224
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00011424416661750994,
+      "loss": 1.1997,
+      "step": 225
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00011418246707339422,
+      "loss": 1.2324,
+      "step": 226
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00011412045543987757,
+      "loss": 1.2788,
+      "step": 227
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00011405813207414514,
+      "loss": 1.2543,
+      "step": 228
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0001139954973351777,
+      "loss": 1.2854,
+      "step": 229
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00011393255158374945,
+      "loss": 1.2034,
+      "step": 230
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00011386929518242606,
+      "loss": 1.2724,
+      "step": 231
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00011380572849556251,
+      "loss": 1.2631,
+      "step": 232
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00011374185188930107,
+      "loss": 1.281,
+      "step": 233
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00011367766573156905,
+      "loss": 1.2162,
+      "step": 234
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00011361317039207682,
+      "loss": 1.2456,
+      "step": 235
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00011354836624231564,
+      "loss": 1.2486,
+      "step": 236
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00011348325365555547,
+      "loss": 1.2923,
+      "step": 237
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00011341783300684288,
+      "loss": 1.2268,
+      "step": 238
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00011335210467299887,
+      "loss": 1.2583,
+      "step": 239
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00011328606903261669,
+      "loss": 1.2731,
+      "step": 240
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00011321972646605965,
+      "loss": 1.2224,
+      "step": 241
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00011315307735545897,
+      "loss": 1.2495,
+      "step": 242
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00011308612208471157,
+      "loss": 1.2641,
+      "step": 243
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0001130188610394778,
+      "loss": 1.2308,
+      "step": 244
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00011295129460717928,
+      "loss": 1.2406,
+      "step": 245
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00011288342317699666,
+      "loss": 1.252,
+      "step": 246
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00011281524713986736,
+      "loss": 1.2578,
+      "step": 247
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00011274676688848332,
+      "loss": 1.2609,
+      "step": 248
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00011267798281728878,
+      "loss": 1.2398,
+      "step": 249
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00011260889532247793,
+      "loss": 1.2689,
+      "step": 250
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00011253950480199267,
+      "loss": 1.2193,
+      "step": 251
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00011246981165552038,
+      "loss": 1.2361,
+      "step": 252
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00011239981628449148,
+      "loss": 1.2999,
+      "step": 253
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00011232951909207721,
+      "loss": 1.2357,
+      "step": 254
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00011225892048318737,
+      "loss": 1.2478,
+      "step": 255
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0001121880208644678,
+      "loss": 1.2718,
+      "step": 256
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00011211682064429823,
+      "loss": 1.2786,
+      "step": 257
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00011204532023278979,
+      "loss": 1.2636,
+      "step": 258
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00011197352004178271,
+      "loss": 1.2662,
+      "step": 259
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00011190142048484403,
+      "loss": 1.2616,
+      "step": 260
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00011182902197726497,
+      "loss": 1.2511,
+      "step": 261
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00011175632493605883,
+      "loss": 1.2794,
+      "step": 262
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00011168332977995841,
+      "loss": 1.2709,
+      "step": 263
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00011161003692941364,
+      "loss": 1.2583,
+      "step": 264
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00011153644680658915,
+      "loss": 1.2573,
+      "step": 265
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00011146255983536184,
+      "loss": 1.2251,
+      "step": 266
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001113883764413185,
+      "loss": 1.2647,
+      "step": 267
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00011131389705175328,
+      "loss": 1.2252,
+      "step": 268
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00011123912209566525,
+      "loss": 1.2373,
+      "step": 269
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00011116405200375591,
+      "loss": 1.2447,
+      "step": 270
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00011108868720842679,
+      "loss": 1.2294,
+      "step": 271
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00011101302814377686,
+      "loss": 1.2497,
+      "step": 272
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00011093707524560006,
+      "loss": 1.2151,
+      "step": 273
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00011086082895138288,
+      "loss": 1.2533,
+      "step": 274
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00011078428970030167,
+      "loss": 1.2424,
+      "step": 275
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00011070745793322026,
+      "loss": 1.2656,
+      "step": 276
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00011063033409268734,
+      "loss": 1.2047,
+      "step": 277
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00011055291862293394,
+      "loss": 1.2705,
+      "step": 278
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00011047521196987087,
+      "loss": 1.2819,
+      "step": 279
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00011039721458108616,
+      "loss": 1.2561,
+      "step": 280
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00011031892690584239,
+      "loss": 1.2291,
+      "step": 281
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00011024034939507433,
+      "loss": 1.2234,
+      "step": 282
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00011016148250138605,
+      "loss": 1.247,
+      "step": 283
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00011008232667904853,
+      "loss": 1.2593,
+      "step": 284
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00011000288238399695,
+      "loss": 1.255,
+      "step": 285
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001099231500738281,
+      "loss": 1.2471,
+      "step": 286
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00010984313020779771,
+      "loss": 1.2817,
+      "step": 287
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00010976282324681785,
+      "loss": 1.2424,
+      "step": 288
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00010968222965345421,
+      "loss": 1.2042,
+      "step": 289
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001096013498919235,
+      "loss": 1.2324,
+      "step": 290
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00010952018442809074,
+      "loss": 1.2063,
+      "step": 291
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00010943873372946661,
+      "loss": 1.2345,
+      "step": 292
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00010935699826520467,
+      "loss": 1.2373,
+      "step": 293
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00010927497850609882,
+      "loss": 1.2694,
+      "step": 294
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00010919267492458041,
+      "loss": 1.2393,
+      "step": 295
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00010911008799471562,
+      "loss": 1.2307,
+      "step": 296
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00010902721819220271,
+      "loss": 1.2317,
+      "step": 297
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001089440659943693,
+      "loss": 1.2129,
+      "step": 298
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00010886063188016958,
+      "loss": 1.2341,
+      "step": 299
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00010877691633018154,
+      "loss": 1.2456,
+      "step": 300
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001086929198266043,
+      "loss": 1.2511,
+      "step": 301
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001086086428532552,
+      "loss": 1.247,
+      "step": 302
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001085240858955671,
+      "loss": 1.2702,
+      "step": 303
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00010843924944058557,
+      "loss": 1.2601,
+      "step": 304
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001083541339769661,
+      "loss": 1.1809,
+      "step": 305
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00010826873999497118,
+      "loss": 1.2388,
+      "step": 306
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00010818306798646766,
+      "loss": 1.2608,
+      "step": 307
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00010809711844492373,
+      "loss": 1.2479,
+      "step": 308
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010801089186540621,
+      "loss": 1.2148,
+      "step": 309
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010792438874457763,
+      "loss": 1.225,
+      "step": 310
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010783760958069341,
+      "loss": 1.2321,
+      "step": 311
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010775055487359894,
+      "loss": 1.2556,
+      "step": 312
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010766322512472675,
+      "loss": 1.2122,
+      "step": 313
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010757562083709362,
+      "loss": 1.2606,
+      "step": 314
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010748774251529763,
+      "loss": 1.2528,
+      "step": 315
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010739959066551528,
+      "loss": 1.2228,
+      "step": 316
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010731116579549864,
+      "loss": 1.1934,
+      "step": 317
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00010722246841457232,
+      "loss": 1.2169,
+      "step": 318
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0001071334990336306,
+      "loss": 1.2657,
+      "step": 319
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0001070442581651345,
+      "loss": 1.2457,
+      "step": 320
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00010695474632310871,
+      "loss": 1.2288,
+      "step": 321
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00010686496402313882,
+      "loss": 1.2224,
+      "step": 322
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00010677491178236823,
+      "loss": 1.2083,
+      "step": 323
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00010668459011949512,
+      "loss": 1.2031,
+      "step": 324
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00010659399955476964,
+      "loss": 1.2406,
+      "step": 325
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00010650314060999073,
+      "loss": 1.1586,
+      "step": 326
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00010641201380850319,
+      "loss": 1.2393,
+      "step": 327
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00010632061967519473,
+      "loss": 1.1987,
+      "step": 328
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00010622895873649281,
+      "loss": 1.1982,
+      "step": 329
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00010613703152036172,
+      "loss": 1.2368,
+      "step": 330
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00010604483855629952,
+      "loss": 1.2315,
+      "step": 331
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00010595238037533491,
+      "loss": 1.1949,
+      "step": 332
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001058596575100243,
+      "loss": 1.2115,
+      "step": 333
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00010576667049444861,
+      "loss": 1.2225,
+      "step": 334
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001056734198642103,
+      "loss": 1.2243,
+      "step": 335
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00010557990615643023,
+      "loss": 1.2686,
+      "step": 336
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00010548612990974458,
+      "loss": 1.2224,
+      "step": 337
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00010539209166430176,
+      "loss": 1.2389,
+      "step": 338
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00010529779196175924,
+      "loss": 1.2085,
+      "step": 339
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00010520323134528051,
+      "loss": 1.2501,
+      "step": 340
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00010510841035953194,
+      "loss": 1.2202,
+      "step": 341
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00010501332955067958,
+      "loss": 1.2156,
+      "step": 342
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00010491798946638606,
+      "loss": 1.2211,
+      "step": 343
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00010482239065580742,
+      "loss": 1.2209,
+      "step": 344
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00010472653366958998,
+      "loss": 1.2249,
+      "step": 345
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00010463041905986715,
+      "loss": 1.1985,
+      "step": 346
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0001045340473802562,
+      "loss": 1.2689,
+      "step": 347
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00010443741918585517,
+      "loss": 1.2237,
+      "step": 348
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00010434053503323955,
+      "loss": 1.2322,
+      "step": 349
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00010424339548045921,
+      "loss": 1.195,
+      "step": 350
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001041460010870351,
+      "loss": 1.1922,
+      "step": 351
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00010404835241395601,
+      "loss": 1.2476,
+      "step": 352
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00010395045002367541,
+      "loss": 1.2289,
+      "step": 353
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00010385229448010814,
+      "loss": 1.249,
+      "step": 354
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00010375388634862723,
+      "loss": 1.2138,
+      "step": 355
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00010365522619606062,
+      "loss": 1.1953,
+      "step": 356
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00010355631459068779,
+      "loss": 1.2433,
+      "step": 357
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00010345715210223671,
+      "loss": 1.1922,
+      "step": 358
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00010335773930188036,
+      "loss": 1.2071,
+      "step": 359
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0001032580767622335,
+      "loss": 1.2189,
+      "step": 360
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0001031581650573494,
+      "loss": 1.2081,
+      "step": 361
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00010305800476271651,
+      "loss": 1.2028,
+      "step": 362
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00010295759645525515,
+      "loss": 1.2179,
+      "step": 363
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00010285694071331422,
+      "loss": 1.2041,
+      "step": 364
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00010275603811666778,
+      "loss": 1.2169,
+      "step": 365
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00010265488924651176,
+      "loss": 1.2272,
+      "step": 366
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00010255349468546072,
+      "loss": 1.2104,
+      "step": 367
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00010245185501754425,
+      "loss": 1.2381,
+      "step": 368
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00010234997082820383,
+      "loss": 1.2231,
+      "step": 369
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00010224784270428942,
+      "loss": 1.2252,
+      "step": 370
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00010214547123405592,
+      "loss": 1.2611,
+      "step": 371
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00010204285700715998,
+      "loss": 1.2557,
+      "step": 372
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00010194000061465648,
+      "loss": 1.2176,
+      "step": 373
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00010183690264899521,
+      "loss": 1.2211,
+      "step": 374
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00010173356370401741,
+      "loss": 1.2117,
+      "step": 375
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010162998437495228,
+      "loss": 1.2404,
+      "step": 376
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0001015261652584137,
+      "loss": 1.2181,
+      "step": 377
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0001014221069523967,
+      "loss": 1.2391,
+      "step": 378
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010131781005627406,
+      "loss": 1.2204,
+      "step": 379
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010121327517079276,
+      "loss": 1.2545,
+      "step": 380
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010110850289807066,
+      "loss": 1.2036,
+      "step": 381
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010100349384159291,
+      "loss": 1.2642,
+      "step": 382
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010089824860620861,
+      "loss": 1.2331,
+      "step": 383
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010079276779812714,
+      "loss": 1.2063,
+      "step": 384
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00010068705202491485,
+      "loss": 1.1969,
+      "step": 385
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00010058110189549143,
+      "loss": 1.2161,
+      "step": 386
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00010047491802012648,
+      "loss": 1.2371,
+      "step": 387
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.000100368501010436,
+      "loss": 1.2154,
+      "step": 388
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00010026185147937877,
+      "loss": 1.2139,
+      "step": 389
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00010015497004125293,
+      "loss": 1.2437,
+      "step": 390
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00010004785731169242,
+      "loss": 1.2077,
+      "step": 391
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.994051390766333e-05,
+      "loss": 1.2164,
+      "step": 392
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.983294044746051e-05,
+      "loss": 1.2177,
+      "step": 393
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.97251375507039e-05,
+      "loss": 1.2081,
+      "step": 394
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.961710583833494e-05,
+      "loss": 1.2373,
+      "step": 395
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.950884593261315e-05,
+      "loss": 1.218,
+      "step": 396
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.940035845711232e-05,
+      "loss": 1.24,
+      "step": 397
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.929164403671711e-05,
+      "loss": 1.1771,
+      "step": 398
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.918270329761933e-05,
+      "loss": 1.2131,
+      "step": 399
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.907353686731444e-05,
+      "loss": 1.2335,
+      "step": 400
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.89641453745978e-05,
+      "loss": 1.2427,
+      "step": 401
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.885452944956118e-05,
+      "loss": 1.2184,
+      "step": 402
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.874468972358904e-05,
+      "loss": 1.2157,
+      "step": 403
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.863462682935493e-05,
+      "loss": 1.2399,
+      "step": 404
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.852434140081789e-05,
+      "loss": 1.221,
+      "step": 405
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.841383407321866e-05,
+      "loss": 1.2568,
+      "step": 406
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.830310548307622e-05,
+      "loss": 1.2178,
+      "step": 407
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.819215626818392e-05,
+      "loss": 1.2101,
+      "step": 408
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.808098706760595e-05,
+      "loss": 1.212,
+      "step": 409
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.796959852167363e-05,
+      "loss": 1.2028,
+      "step": 410
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.785799127198162e-05,
+      "loss": 1.1922,
+      "step": 411
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.77461659613844e-05,
+      "loss": 1.1668,
+      "step": 412
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.763412323399245e-05,
+      "loss": 1.1926,
+      "step": 413
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.752186373516853e-05,
+      "loss": 1.2085,
+      "step": 414
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.740938811152401e-05,
+      "loss": 1.2137,
+      "step": 415
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.729669701091517e-05,
+      "loss": 1.2701,
+      "step": 416
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 9.718379108243939e-05,
+      "loss": 1.2591,
+      "step": 417
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 9.707067097643147e-05,
+      "loss": 1.2277,
+      "step": 418
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 9.695733734445982e-05,
+      "loss": 1.2128,
+      "step": 419
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 9.684379083932286e-05,
+      "loss": 1.2091,
+      "step": 420
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.673003211504503e-05,
+      "loss": 1.2067,
+      "step": 421
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.661606182687324e-05,
+      "loss": 1.191,
+      "step": 422
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.650188063127296e-05,
+      "loss": 1.1973,
+      "step": 423
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.638748918592445e-05,
+      "loss": 1.2405,
+      "step": 424
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.627288814971908e-05,
+      "loss": 1.2487,
+      "step": 425
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.615807818275539e-05,
+      "loss": 1.1887,
+      "step": 426
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.604305994633539e-05,
+      "loss": 1.2214,
+      "step": 427
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.592783410296071e-05,
+      "loss": 1.2136,
+      "step": 428
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.581240131632876e-05,
+      "loss": 1.2074,
+      "step": 429
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.569676225132898e-05,
+      "loss": 1.1687,
+      "step": 430
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.558091757403897e-05,
+      "loss": 1.1988,
+      "step": 431
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.54648679517206e-05,
+      "loss": 1.2025,
+      "step": 432
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.534861405281625e-05,
+      "loss": 1.2027,
+      "step": 433
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.523215654694493e-05,
+      "loss": 1.2192,
+      "step": 434
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.511549610489844e-05,
+      "loss": 1.2245,
+      "step": 435
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.499863339863741e-05,
+      "loss": 1.1959,
+      "step": 436
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.48815691012876e-05,
+      "loss": 1.2241,
+      "step": 437
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.476430388713586e-05,
+      "loss": 1.2185,
+      "step": 438
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.464683843162635e-05,
+      "loss": 1.202,
+      "step": 439
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.45291734113566e-05,
+      "loss": 1.2031,
+      "step": 440
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.441130950407367e-05,
+      "loss": 1.2341,
+      "step": 441
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.42932473886701e-05,
+      "loss": 1.2146,
+      "step": 442
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.417498774518019e-05,
+      "loss": 1.2221,
+      "step": 443
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.4056531254776e-05,
+      "loss": 1.2147,
+      "step": 444
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.393787859976338e-05,
+      "loss": 1.229,
+      "step": 445
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.381903046357809e-05,
+      "loss": 1.2305,
+      "step": 446
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.369998753078188e-05,
+      "loss": 1.2403,
+      "step": 447
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.35807504870585e-05,
+      "loss": 1.2102,
+      "step": 448
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.346132001920977e-05,
+      "loss": 1.1927,
+      "step": 449
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.334169681515164e-05,
+      "loss": 1.1759,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.322188156391023e-05,
+      "loss": 0.9853,
+      "step": 451
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.31018749556178e-05,
+      "loss": 0.9395,
+      "step": 452
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.29816776815089e-05,
+      "loss": 0.9399,
+      "step": 453
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.28612904339162e-05,
+      "loss": 0.8974,
+      "step": 454
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.27407139062667e-05,
+      "loss": 0.9517,
+      "step": 455
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.261994879307761e-05,
+      "loss": 0.889,
+      "step": 456
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.24989957899524e-05,
+      "loss": 0.9045,
+      "step": 457
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.237785559357675e-05,
+      "loss": 0.8965,
+      "step": 458
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.225652890171464e-05,
+      "loss": 0.9576,
+      "step": 459
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.213501641320418e-05,
+      "loss": 0.9374,
+      "step": 460
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.20133188279537e-05,
+      "loss": 0.8864,
+      "step": 461
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.189143684693768e-05,
+      "loss": 0.8912,
+      "step": 462
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.176937117219272e-05,
+      "loss": 0.8981,
+      "step": 463
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.164712250681344e-05,
+      "loss": 0.892,
+      "step": 464
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.152469155494857e-05,
+      "loss": 0.8896,
+      "step": 465
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.140207902179673e-05,
+      "loss": 0.9112,
+      "step": 466
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.127928561360246e-05,
+      "loss": 0.8909,
+      "step": 467
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.115631203765218e-05,
+      "loss": 0.9034,
+      "step": 468
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.103315900226999e-05,
+      "loss": 0.903,
+      "step": 469
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.090982721681376e-05,
+      "loss": 0.9069,
+      "step": 470
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.07863173916709e-05,
+      "loss": 0.877,
+      "step": 471
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.06626302382543e-05,
+      "loss": 0.874,
+      "step": 472
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.05387664689983e-05,
+      "loss": 0.8924,
+      "step": 473
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.041472679735459e-05,
+      "loss": 0.9288,
+      "step": 474
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.029051193778793e-05,
+      "loss": 0.8858,
+      "step": 475
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.016612260577223e-05,
+      "loss": 0.869,
+      "step": 476
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.004155951778635e-05,
+      "loss": 0.8812,
+      "step": 477
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 8.991682339130999e-05,
+      "loss": 0.8824,
+      "step": 478
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 8.979191494481956e-05,
+      "loss": 0.891,
+      "step": 479
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.966683489778394e-05,
+      "loss": 0.8898,
+      "step": 480
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.954158397066053e-05,
+      "loss": 0.8971,
+      "step": 481
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.941616288489093e-05,
+      "loss": 0.8956,
+      "step": 482
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.929057236289687e-05,
+      "loss": 0.903,
+      "step": 483
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.916481312807606e-05,
+      "loss": 0.9051,
+      "step": 484
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.90388859047979e-05,
+      "loss": 0.8458,
+      "step": 485
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.891279141839948e-05,
+      "loss": 0.8767,
+      "step": 486
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.878653039518131e-05,
+      "loss": 0.878,
+      "step": 487
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.866010356240313e-05,
+      "loss": 0.9164,
+      "step": 488
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.853351164827973e-05,
+      "loss": 0.8943,
+      "step": 489
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.840675538197676e-05,
+      "loss": 0.8845,
+      "step": 490
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.827983549360659e-05,
+      "loss": 0.8685,
+      "step": 491
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.815275271422398e-05,
+      "loss": 0.898,
+      "step": 492
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.802550777582197e-05,
+      "loss": 0.8824,
+      "step": 493
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.789810141132762e-05,
+      "loss": 0.9068,
+      "step": 494
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.777053435459781e-05,
+      "loss": 0.9178,
+      "step": 495
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.7642807340415e-05,
+      "loss": 0.886,
+      "step": 496
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.7514921104483e-05,
+      "loss": 0.8724,
+      "step": 497
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.738687638342273e-05,
+      "loss": 0.8978,
+      "step": 498
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.725867391476798e-05,
+      "loss": 0.9092,
+      "step": 499
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.713031443696114e-05,
+      "loss": 0.9074,
+      "step": 500
+    }
+  ],
+  "max_steps": 1350,
+  "num_train_epochs": 3,
+  "total_flos": 4.9660776799430246e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec794cf2a744aebfddf8da932b53a867de494475dc2d023514e32a174e3f5b0b
+size 4091