Upload folder using huggingface_hub

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "airoboros-13b-gpt4-1.1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": -1,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b902638d8338272862f1ce8845bcd14cb764c0c3cdac3992bd9a3ffc2f8c078a
+size 9956543883

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e5cdec0ad64d38d2a061b632b07f063e61cbd51c514f96561b0936687b92d4
+size 9940856385

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7574c0c0f421c2826ee2abadff794276fbbd697cb132d816762817bd14748926
+size 9940856943

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6bf65831762f10e7dafee4ac973afef8088fd631ac4f09fdb21c5d318d5779
+size 9867415289

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08974979849429bbb0dc2bff400d2bf8e408ea08c84ab9caeacb152ac16995c
+size 9867456961

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a4012e52d5d277b94b206aa29a9cf15274e8b720db098a533cda020fd255a5
+size 2490476207

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 52063467520
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.norm.weight": "pytorch_model-00006-of-00006.bin"
+  }
+}

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,3481 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 576,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.1666666666666667e-07,
+      "loss": 0.6228,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.6226,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.25e-06,
+      "loss": 0.5863,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.5544,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.4827,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6049,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.916666666666667e-06,
+      "loss": 0.5721,
+      "step": 7
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.5307,
+      "step": 8
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.5169,
+      "step": 9
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.6051,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.583333333333333e-06,
+      "loss": 0.5554,
+      "step": 11
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 5e-06,
+      "loss": 0.4904,
+      "step": 12
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.416666666666667e-06,
+      "loss": 0.538,
+      "step": 13
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.6105,
+      "step": 14
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 6.25e-06,
+      "loss": 0.4848,
+      "step": 15
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.4959,
+      "step": 16
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.083333333333335e-06,
+      "loss": 0.4867,
+      "step": 17
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.4887,
+      "step": 18
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 7.916666666666667e-06,
+      "loss": 0.4997,
+      "step": 19
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.4535,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.4364,
+      "step": 21
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.4912,
+      "step": 22
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.583333333333335e-06,
+      "loss": 0.4796,
+      "step": 23
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1e-05,
+      "loss": 0.4205,
+      "step": 24
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.999919023234347e-06,
+      "loss": 0.5209,
+      "step": 25
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.999676095560278e-06,
+      "loss": 0.4793,
+      "step": 26
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.999271224846397e-06,
+      "loss": 0.5478,
+      "step": 27
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.998704424206747e-06,
+      "loss": 0.4269,
+      "step": 28
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.997975712000405e-06,
+      "loss": 0.4837,
+      "step": 29
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.99708511183087e-06,
+      "loss": 0.4503,
+      "step": 30
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.996032652545316e-06,
+      "loss": 0.5008,
+      "step": 31
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.994818368233639e-06,
+      "loss": 0.4619,
+      "step": 32
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.993442298227365e-06,
+      "loss": 0.5088,
+      "step": 33
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.991904487098376e-06,
+      "loss": 0.4037,
+      "step": 34
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.990204984657458e-06,
+      "loss": 0.3666,
+      "step": 35
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.988343845952697e-06,
+      "loss": 0.4376,
+      "step": 36
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.98632113126769e-06,
+      "loss": 0.4527,
+      "step": 37
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.984136906119592e-06,
+      "loss": 0.5132,
+      "step": 38
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.981791241257001e-06,
+      "loss": 0.4329,
+      "step": 39
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.979284212657658e-06,
+      "loss": 0.4311,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.976615901525988e-06,
+      "loss": 0.494,
+      "step": 41
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.973786394290475e-06,
+      "loss": 0.4842,
+      "step": 42
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.970795782600856e-06,
+      "loss": 0.3968,
+      "step": 43
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.967644163325157e-06,
+      "loss": 0.4588,
+      "step": 44
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.96433163854655e-06,
+      "loss": 0.5148,
+      "step": 45
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.960858315560054e-06,
+      "loss": 0.4377,
+      "step": 46
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.957224306869053e-06,
+      "loss": 0.3878,
+      "step": 47
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.953429730181653e-06,
+      "loss": 0.4087,
+      "step": 48
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.949474708406879e-06,
+      "loss": 0.3732,
+      "step": 49
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.945359369650673e-06,
+      "loss": 0.3988,
+      "step": 50
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.941083847211765e-06,
+      "loss": 0.4186,
+      "step": 51
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.93664827957735e-06,
+      "loss": 0.4103,
+      "step": 52
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.932052810418591e-06,
+      "loss": 0.4734,
+      "step": 53
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.927297588585984e-06,
+      "loss": 0.3813,
+      "step": 54
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.922382768104522e-06,
+      "loss": 0.4658,
+      "step": 55
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.917308508168712e-06,
+      "loss": 0.4664,
+      "step": 56
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.912074973137413e-06,
+      "loss": 0.4378,
+      "step": 57
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.906682332528525e-06,
+      "loss": 0.4106,
+      "step": 58
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.901130761013485e-06,
+      "loss": 0.3443,
+      "step": 59
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.895420438411616e-06,
+      "loss": 0.5413,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.889551549684298e-06,
+      "loss": 0.4417,
+      "step": 61
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.883524284928982e-06,
+      "loss": 0.411,
+      "step": 62
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.877338839373032e-06,
+      "loss": 0.3888,
+      "step": 63
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.870995413367397e-06,
+      "loss": 0.4585,
+      "step": 64
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.864494212380125e-06,
+      "loss": 0.4716,
+      "step": 65
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.857835446989708e-06,
+      "loss": 0.444,
+      "step": 66
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.851019332878261e-06,
+      "loss": 0.4093,
+      "step": 67
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.844046090824533e-06,
+      "loss": 0.4385,
+      "step": 68
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.83691594669676e-06,
+      "loss": 0.446,
+      "step": 69
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.829629131445342e-06,
+      "loss": 0.4389,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.822185881095376e-06,
+      "loss": 0.5123,
+      "step": 71
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.814586436738998e-06,
+      "loss": 0.4392,
+      "step": 72
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.806831044527574e-06,
+      "loss": 0.4739,
+      "step": 73
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.798919955663738e-06,
+      "loss": 0.4497,
+      "step": 74
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.790853426393246e-06,
+      "loss": 0.4983,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.782631717996675e-06,
+      "loss": 0.5268,
+      "step": 76
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.774255096780969e-06,
+      "loss": 0.4357,
+      "step": 77
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.765723834070805e-06,
+      "loss": 0.3865,
+      "step": 78
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.757038206199807e-06,
+      "loss": 0.4707,
+      "step": 79
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.748198494501598e-06,
+      "loss": 0.3794,
+      "step": 80
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.73920498530068e-06,
+      "loss": 0.4031,
+      "step": 81
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.73005796990317e-06,
+      "loss": 0.466,
+      "step": 82
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.720757744587354e-06,
+      "loss": 0.438,
+      "step": 83
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.711304610594104e-06,
+      "loss": 0.4813,
+      "step": 84
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.7016988741171e-06,
+      "loss": 0.4782,
+      "step": 85
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.691940846292936e-06,
+      "loss": 0.4512,
+      "step": 86
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.682030843191021e-06,
+      "loss": 0.3891,
+      "step": 87
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.671969185803357e-06,
+      "loss": 0.3776,
+      "step": 88
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.661756200034131e-06,
+      "loss": 0.3567,
+      "step": 89
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.651392216689167e-06,
+      "loss": 0.485,
+      "step": 90
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.640877571465204e-06,
+      "loss": 0.3875,
+      "step": 91
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.630212604939026e-06,
+      "loss": 0.3931,
+      "step": 92
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.3597,
+      "step": 93
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.608433094621047e-06,
+      "loss": 0.4372,
+      "step": 94
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.597319256282968e-06,
+      "loss": 0.4184,
+      "step": 95
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.586056507527266e-06,
+      "loss": 0.4245,
+      "step": 96
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.574645213162329e-06,
+      "loss": 0.451,
+      "step": 97
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.56308574280804e-06,
+      "loss": 0.4343,
+      "step": 98
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.551378470883813e-06,
+      "loss": 0.5133,
+      "step": 99
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.539523776596446e-06,
+      "loss": 0.4918,
+      "step": 100
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.527522043927864e-06,
+      "loss": 0.4277,
+      "step": 101
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.515373661622665e-06,
+      "loss": 0.4445,
+      "step": 102
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.50307902317553e-06,
+      "loss": 0.41,
+      "step": 103
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.490638526818482e-06,
+      "loss": 0.4083,
+      "step": 104
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.478052575507983e-06,
+      "loss": 0.5396,
+      "step": 105
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.465321576911889e-06,
+      "loss": 0.4625,
+      "step": 106
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.452445943396233e-06,
+      "loss": 0.3989,
+      "step": 107
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.439426092011877e-06,
+      "loss": 0.3583,
+      "step": 108
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.426262444481004e-06,
+      "loss": 0.4445,
+      "step": 109
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.412955427183457e-06,
+      "loss": 0.3978,
+      "step": 110
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.39950547114292e-06,
+      "loss": 0.3654,
+      "step": 111
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.385913012012972e-06,
+      "loss": 0.4874,
+      "step": 112
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.372178490062961e-06,
+      "loss": 0.3056,
+      "step": 113
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.358302350163758e-06,
+      "loss": 0.3603,
+      "step": 114
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.344285041773329e-06,
+      "loss": 0.3776,
+      "step": 115
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.4359,
+      "step": 116
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.315828740198714e-06,
+      "loss": 0.4142,
+      "step": 117
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.301390668734236e-06,
+      "loss": 0.3697,
+      "step": 118
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.28681327218809e-06,
+      "loss": 0.529,
+      "step": 119
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.272097022732444e-06,
+      "loss": 0.4071,
+      "step": 120
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.257242397037014e-06,
+      "loss": 0.4541,
+      "step": 121
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.242249876253617e-06,
+      "loss": 0.4562,
+      "step": 122
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.22711994600059e-06,
+      "loss": 0.3675,
+      "step": 123
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.211853096347059e-06,
+      "loss": 0.4719,
+      "step": 124
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.196449821797067e-06,
+      "loss": 0.4509,
+      "step": 125
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 9.180910621273555e-06,
+      "loss": 0.4665,
+      "step": 126
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 9.165235998102204e-06,
+      "loss": 0.3802,
+      "step": 127
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 9.149426459995127e-06,
+      "loss": 0.4071,
+      "step": 128
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 9.133482519034428e-06,
+      "loss": 0.4573,
+      "step": 129
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.11740469165562e-06,
+      "loss": 0.3656,
+      "step": 130
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.101193498630886e-06,
+      "loss": 0.4184,
+      "step": 131
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 9.08484946505221e-06,
+      "loss": 0.4245,
+      "step": 132
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 9.068373120314392e-06,
+      "loss": 0.4423,
+      "step": 133
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.05176499809787e-06,
+      "loss": 0.4013,
+      "step": 134
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.035025636351453e-06,
+      "loss": 0.3466,
+      "step": 135
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.018155577274891e-06,
+      "loss": 0.3971,
+      "step": 136
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.001155367301312e-06,
+      "loss": 0.4159,
+      "step": 137
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.984025557079523e-06,
+      "loss": 0.4659,
+      "step": 138
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.966766701456177e-06,
+      "loss": 0.3389,
+      "step": 139
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.949379359457795e-06,
+      "loss": 0.4077,
+      "step": 140
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.931864094272663e-06,
+      "loss": 0.3795,
+      "step": 141
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.914221473232594e-06,
+      "loss": 0.3625,
+      "step": 142
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.896452067794542e-06,
+      "loss": 0.3363,
+      "step": 143
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.8785564535221e-06,
+      "loss": 0.3743,
+      "step": 144
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 8.860535210066851e-06,
+      "loss": 0.4334,
+      "step": 145
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 8.842388921149603e-06,
+      "loss": 0.3556,
+      "step": 146
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 8.824118174541464e-06,
+      "loss": 0.3977,
+      "step": 147
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 8.805723562044825e-06,
+      "loss": 0.4037,
+      "step": 148
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 8.787205679474174e-06,
+      "loss": 0.4265,
+      "step": 149
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 8.768565126636806e-06,
+      "loss": 0.4058,
+      "step": 150
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 8.749802507313393e-06,
+      "loss": 0.3564,
+      "step": 151
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 8.730918429238429e-06,
+      "loss": 0.3238,
+      "step": 152
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 8.711913504080534e-06,
+      "loss": 0.4479,
+      "step": 153
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 8.692788347422662e-06,
+      "loss": 0.4177,
+      "step": 154
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.673543578742141e-06,
+      "loss": 0.4248,
+      "step": 155
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.65417982139062e-06,
+      "loss": 0.491,
+      "step": 156
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.63469770257388e-06,
+      "loss": 0.3718,
+      "step": 157
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.615097853331505e-06,
+      "loss": 0.3699,
+      "step": 158
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.595380908516454e-06,
+      "loss": 0.4468,
+      "step": 159
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.575547506774498e-06,
+      "loss": 0.3366,
+      "step": 160
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.555598290523525e-06,
+      "loss": 0.4067,
+      "step": 161
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.366,
+      "step": 162
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.515355002901727e-06,
+      "loss": 0.3512,
+      "step": 163
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.49506223503941e-06,
+      "loss": 0.3967,
+      "step": 164
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 8.474656259642874e-06,
+      "loss": 0.4167,
+      "step": 165
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 8.45413773767607e-06,
+      "loss": 0.295,
+      "step": 166
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.433507333748419e-06,
+      "loss": 0.4049,
+      "step": 167
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.412765716093273e-06,
+      "loss": 0.4096,
+      "step": 168
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.391913556546273e-06,
+      "loss": 0.2775,
+      "step": 169
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.370951530523602e-06,
+      "loss": 0.3666,
+      "step": 170
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.349880317000083e-06,
+      "loss": 0.4301,
+      "step": 171
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.328700598487203e-06,
+      "loss": 0.4707,
+      "step": 172
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.307413061011007e-06,
+      "loss": 0.3716,
+      "step": 173
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 8.286018394089864e-06,
+      "loss": 0.3055,
+      "step": 174
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 8.264517290712146e-06,
+      "loss": 0.399,
+      "step": 175
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.24291044731378e-06,
+      "loss": 0.4073,
+      "step": 176
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.221198563755683e-06,
+      "loss": 0.3961,
+      "step": 177
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.199382343301094e-06,
+      "loss": 0.3826,
+      "step": 178
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.177462492592807e-06,
+      "loss": 0.4113,
+      "step": 179
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.155439721630265e-06,
+      "loss": 0.3691,
+      "step": 180
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.133314743746572e-06,
+      "loss": 0.4212,
+      "step": 181
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 8.11108827558539e-06,
+      "loss": 0.4468,
+      "step": 182
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 8.088761037077718e-06,
+      "loss": 0.3119,
+      "step": 183
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.066333751418582e-06,
+      "loss": 0.2805,
+      "step": 184
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.043807145043604e-06,
+      "loss": 0.3691,
+      "step": 185
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.021181947605474e-06,
+      "loss": 0.3757,
+      "step": 186
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.998458891950317e-06,
+      "loss": 0.3971,
+      "step": 187
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.97563871409395e-06,
+      "loss": 0.3847,
+      "step": 188
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.952722153198054e-06,
+      "loss": 0.3331,
+      "step": 189
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.929709951546224e-06,
+      "loss": 0.4079,
+      "step": 190
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.906602854519921e-06,
+      "loss": 0.463,
+      "step": 191
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.883401610574338e-06,
+      "loss": 0.2378,
+      "step": 192
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 7.86010697121415e-06,
+      "loss": 0.2147,
+      "step": 193
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 7.836719690969183e-06,
+      "loss": 0.3056,
+      "step": 194
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 7.813240527369958e-06,
+      "loss": 0.2191,
+      "step": 195
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 7.789670240923169e-06,
+      "loss": 0.1942,
+      "step": 196
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 7.766009595087037e-06,
+      "loss": 0.221,
+      "step": 197
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 7.742259356246594e-06,
+      "loss": 0.2422,
+      "step": 198
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 7.71842029368885e-06,
+      "loss": 0.2253,
+      "step": 199
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 7.69449317957788e-06,
+      "loss": 0.2009,
+      "step": 200
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 7.670478788929803e-06,
+      "loss": 0.231,
+      "step": 201
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 7.646377899587695e-06,
+      "loss": 0.2143,
+      "step": 202
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 7.622191292196386e-06,
+      "loss": 0.2713,
+      "step": 203
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 7.597919750177168e-06,
+      "loss": 0.2116,
+      "step": 204
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 7.573564059702432e-06,
+      "loss": 0.2123,
+      "step": 205
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 7.549125009670193e-06,
+      "loss": 0.2131,
+      "step": 206
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 7.524603391678541e-06,
+      "loss": 0.2569,
+      "step": 207
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.26,
+      "step": 208
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7.475315631555808e-06,
+      "loss": 0.2613,
+      "step": 209
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7.450551085890087e-06,
+      "loss": 0.2455,
+      "step": 210
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 7.425707165143965e-06,
+      "loss": 0.2206,
+      "step": 211
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 7.400784674029579e-06,
+      "loss": 0.2643,
+      "step": 212
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 7.375784419804018e-06,
+      "loss": 0.2097,
+      "step": 213
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 7.3507072122431765e-06,
+      "loss": 0.2464,
+      "step": 214
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 7.325553863615516e-06,
+      "loss": 0.2359,
+      "step": 215
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 7.300325188655762e-06,
+      "loss": 0.2527,
+      "step": 216
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 7.275022004538515e-06,
+      "loss": 0.2187,
+      "step": 217
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.249645130851782e-06,
+      "loss": 0.2043,
+      "step": 218
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.224195389570422e-06,
+      "loss": 0.2255,
+      "step": 219
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.198673605029529e-06,
+      "loss": 0.2796,
+      "step": 220
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.173080603897732e-06,
+      "loss": 0.1442,
+      "step": 221
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.147417215150411e-06,
+      "loss": 0.2157,
+      "step": 222
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.121684270042851e-06,
+      "loss": 0.237,
+      "step": 223
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.095882602083321e-06,
+      "loss": 0.1775,
+      "step": 224
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.070013047006068e-06,
+      "loss": 0.2371,
+      "step": 225
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.044076442744252e-06,
+      "loss": 0.1903,
+      "step": 226
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.018073629402802e-06,
+      "loss": 0.235,
+      "step": 227
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 6.9920054492312086e-06,
+      "loss": 0.242,
+      "step": 228
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 6.965872746596236e-06,
+      "loss": 0.2306,
+      "step": 229
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.939676367954582e-06,
+      "loss": 0.187,
+      "step": 230
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.149,
+      "step": 231
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.887095978763072e-06,
+      "loss": 0.2301,
+      "step": 232
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.860713671329161e-06,
+      "loss": 0.1915,
+      "step": 233
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.834271094065284e-06,
+      "loss": 0.2224,
+      "step": 234
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.8077691034651936e-06,
+      "loss": 0.1945,
+      "step": 235
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.781208557947085e-06,
+      "loss": 0.2624,
+      "step": 236
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.754590317825785e-06,
+      "loss": 0.2425,
+      "step": 237
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.727915245284891e-06,
+      "loss": 0.2268,
+      "step": 238
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.7011842043488405e-06,
+      "loss": 0.2312,
+      "step": 239
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.674398060854931e-06,
+      "loss": 0.2165,
+      "step": 240
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.647557682425267e-06,
+      "loss": 0.2298,
+      "step": 241
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.620663938438664e-06,
+      "loss": 0.1871,
+      "step": 242
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.59371770000248e-06,
+      "loss": 0.1738,
+      "step": 243
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.566719839924412e-06,
+      "loss": 0.2292,
+      "step": 244
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.539671232684215e-06,
+      "loss": 0.2016,
+      "step": 245
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.51257275440538e-06,
+      "loss": 0.2075,
+      "step": 246
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.485425282826757e-06,
+      "loss": 0.1901,
+      "step": 247
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.458229697274125e-06,
+      "loss": 0.2148,
+      "step": 248
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 6.430986878631708e-06,
+      "loss": 0.2336,
+      "step": 249
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 6.403697709313639e-06,
+      "loss": 0.1997,
+      "step": 250
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 6.376363073235388e-06,
+      "loss": 0.1798,
+      "step": 251
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 6.348983855785122e-06,
+      "loss": 0.2341,
+      "step": 252
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 6.321560943795032e-06,
+      "loss": 0.2797,
+      "step": 253
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 6.294095225512604e-06,
+      "loss": 0.2282,
+      "step": 254
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 6.266587590571852e-06,
+      "loss": 0.2132,
+      "step": 255
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 6.2390389299645e-06,
+      "loss": 0.3393,
+      "step": 256
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 6.211450136011121e-06,
+      "loss": 0.2429,
+      "step": 257
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 6.183822102332234e-06,
+      "loss": 0.2086,
+      "step": 258
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 6.1561557238193655e-06,
+      "loss": 0.1825,
+      "step": 259
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 6.128451896606054e-06,
+      "loss": 0.1507,
+      "step": 260
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 6.100711518038828e-06,
+      "loss": 0.2533,
+      "step": 261
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 6.072935486648144e-06,
+      "loss": 0.1819,
+      "step": 262
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 6.045124702119274e-06,
+      "loss": 0.1806,
+      "step": 263
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 6.0172800652631706e-06,
+      "loss": 0.2453,
+      "step": 264
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 5.9894024779872865e-06,
+      "loss": 0.2334,
+      "step": 265
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 5.961492843266363e-06,
+      "loss": 0.2178,
+      "step": 266
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 5.933552065113182e-06,
+      "loss": 0.1856,
+      "step": 267
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 5.905581048549279e-06,
+      "loss": 0.2256,
+      "step": 268
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 5.877580699575638e-06,
+      "loss": 0.1834,
+      "step": 269
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 5.849551925143334e-06,
+      "loss": 0.1553,
+      "step": 270
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 5.821495633124169e-06,
+      "loss": 0.1962,
+      "step": 271
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.793412732281258e-06,
+      "loss": 0.1645,
+      "step": 272
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.76530413223959e-06,
+      "loss": 0.1862,
+      "step": 273
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.737170743456573e-06,
+      "loss": 0.127,
+      "step": 274
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.709013477192541e-06,
+      "loss": 0.1874,
+      "step": 275
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 5.680833245481234e-06,
+      "loss": 0.2084,
+      "step": 276
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 5.65263096110026e-06,
+      "loss": 0.2198,
+      "step": 277
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.6244075375415255e-06,
+      "loss": 0.187,
+      "step": 278
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.596163888981656e-06,
+      "loss": 0.219,
+      "step": 279
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 5.567900930252375e-06,
+      "loss": 0.1906,
+      "step": 280
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 5.539619576810877e-06,
+      "loss": 0.2745,
+      "step": 281
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5.511320744710171e-06,
+      "loss": 0.1857,
+      "step": 282
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5.4830053505694204e-06,
+      "loss": 0.2473,
+      "step": 283
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 5.454674311544236e-06,
+      "loss": 0.2235,
+      "step": 284
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 5.4263285452969805e-06,
+      "loss": 0.2309,
+      "step": 285
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 5.397968969967044e-06,
+      "loss": 0.1904,
+      "step": 286
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 5.3695965041411015e-06,
+      "loss": 0.2391,
+      "step": 287
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 5.341212066823356e-06,
+      "loss": 0.2283,
+      "step": 288
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 5.31281657740578e-06,
+      "loss": 0.2984,
+      "step": 289
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 5.284410955638335e-06,
+      "loss": 0.1973,
+      "step": 290
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 5.255996121599167e-06,
+      "loss": 0.1753,
+      "step": 291
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 5.227572995664819e-06,
+      "loss": 0.1709,
+      "step": 292
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 5.199142498480415e-06,
+      "loss": 0.219,
+      "step": 293
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 5.17070555092984e-06,
+      "loss": 0.1841,
+      "step": 294
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 5.1422630741059075e-06,
+      "loss": 0.1877,
+      "step": 295
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 5.113815989280528e-06,
+      "loss": 0.1924,
+      "step": 296
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 5.085365217874875e-06,
+      "loss": 0.2146,
+      "step": 297
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 5.056911681429521e-06,
+      "loss": 0.2247,
+      "step": 298
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 5.0284563015746144e-06,
+      "loss": 0.2197,
+      "step": 299
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 5e-06,
+      "loss": 0.1898,
+      "step": 300
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.971543698425386e-06,
+      "loss": 0.254,
+      "step": 301
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.9430883185704796e-06,
+      "loss": 0.2529,
+      "step": 302
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.914634782125127e-06,
+      "loss": 0.2218,
+      "step": 303
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.886184010719472e-06,
+      "loss": 0.2202,
+      "step": 304
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 4.857736925894093e-06,
+      "loss": 0.2077,
+      "step": 305
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 4.829294449070161e-06,
+      "loss": 0.2233,
+      "step": 306
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.800857501519587e-06,
+      "loss": 0.2463,
+      "step": 307
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.772427004335183e-06,
+      "loss": 0.1808,
+      "step": 308
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.744003878400836e-06,
+      "loss": 0.2034,
+      "step": 309
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.715589044361667e-06,
+      "loss": 0.1448,
+      "step": 310
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.687183422594221e-06,
+      "loss": 0.2125,
+      "step": 311
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.6587879331766465e-06,
+      "loss": 0.2391,
+      "step": 312
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.630403495858901e-06,
+      "loss": 0.2339,
+      "step": 313
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.6020310300329575e-06,
+      "loss": 0.1453,
+      "step": 314
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.57367145470302e-06,
+      "loss": 0.2064,
+      "step": 315
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.545325688455766e-06,
+      "loss": 0.2278,
+      "step": 316
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.516994649430581e-06,
+      "loss": 0.1749,
+      "step": 317
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 4.488679255289829e-06,
+      "loss": 0.2473,
+      "step": 318
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 4.460380423189124e-06,
+      "loss": 0.1748,
+      "step": 319
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 4.432099069747625e-06,
+      "loss": 0.2509,
+      "step": 320
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 4.403836111018346e-06,
+      "loss": 0.212,
+      "step": 321
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 4.375592462458477e-06,
+      "loss": 0.2655,
+      "step": 322
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 4.347369038899744e-06,
+      "loss": 0.1895,
+      "step": 323
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 4.319166754518768e-06,
+      "loss": 0.186,
+      "step": 324
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 4.29098652280746e-06,
+      "loss": 0.2375,
+      "step": 325
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.262829256543429e-06,
+      "loss": 0.1883,
+      "step": 326
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.234695867760412e-06,
+      "loss": 0.1836,
+      "step": 327
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.206587267718743e-06,
+      "loss": 0.2208,
+      "step": 328
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.178504366875832e-06,
+      "loss": 0.217,
+      "step": 329
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 4.150448074856667e-06,
+      "loss": 0.2423,
+      "step": 330
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 4.122419300424363e-06,
+      "loss": 0.2313,
+      "step": 331
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 4.094418951450721e-06,
+      "loss": 0.2213,
+      "step": 332
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 4.066447934886819e-06,
+      "loss": 0.2091,
+      "step": 333
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 4.038507156733637e-06,
+      "loss": 0.1929,
+      "step": 334
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 4.010597522012716e-06,
+      "loss": 0.2606,
+      "step": 335
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.982719934736832e-06,
+      "loss": 0.2008,
+      "step": 336
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.954875297880729e-06,
+      "loss": 0.1968,
+      "step": 337
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.927064513351858e-06,
+      "loss": 0.2177,
+      "step": 338
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.899288481961173e-06,
+      "loss": 0.2031,
+      "step": 339
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.871548103393947e-06,
+      "loss": 0.1929,
+      "step": 340
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.843844276180636e-06,
+      "loss": 0.2393,
+      "step": 341
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.816177897667767e-06,
+      "loss": 0.1986,
+      "step": 342
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.788549863988881e-06,
+      "loss": 0.214,
+      "step": 343
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.7609610700355014e-06,
+      "loss": 0.1814,
+      "step": 344
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.733412409428148e-06,
+      "loss": 0.2161,
+      "step": 345
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.705904774487396e-06,
+      "loss": 0.199,
+      "step": 346
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.678439056204968e-06,
+      "loss": 0.1796,
+      "step": 347
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.6510161442148783e-06,
+      "loss": 0.2804,
+      "step": 348
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.6236369267646148e-06,
+      "loss": 0.2226,
+      "step": 349
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.5963022906863633e-06,
+      "loss": 0.1898,
+      "step": 350
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.5690131213682943e-06,
+      "loss": 0.1913,
+      "step": 351
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.5417703027258752e-06,
+      "loss": 0.2153,
+      "step": 352
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.5145747171732448e-06,
+      "loss": 0.2056,
+      "step": 353
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.4874272455946217e-06,
+      "loss": 0.209,
+      "step": 354
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.4603287673157866e-06,
+      "loss": 0.2405,
+      "step": 355
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.4332801600755895e-06,
+      "loss": 0.1774,
+      "step": 356
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.406282299997521e-06,
+      "loss": 0.2372,
+      "step": 357
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.3793360615613375e-06,
+      "loss": 0.1953,
+      "step": 358
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.3524423175747334e-06,
+      "loss": 0.181,
+      "step": 359
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 3.3256019391450696e-06,
+      "loss": 0.2042,
+      "step": 360
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 3.2988157956511594e-06,
+      "loss": 0.2109,
+      "step": 361
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.2720847547151096e-06,
+      "loss": 0.1941,
+      "step": 362
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.245409682174217e-06,
+      "loss": 0.1783,
+      "step": 363
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.2187914420529176e-06,
+      "loss": 0.224,
+      "step": 364
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.192230896534808e-06,
+      "loss": 0.1999,
+      "step": 365
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 3.1657289059347184e-06,
+      "loss": 0.1669,
+      "step": 366
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 3.139286328670841e-06,
+      "loss": 0.2206,
+      "step": 367
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.1129040212369286e-06,
+      "loss": 0.2675,
+      "step": 368
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.2056,
+      "step": 369
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 3.0603236320454195e-06,
+      "loss": 0.1654,
+      "step": 370
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 3.0341272534037657e-06,
+      "loss": 0.1978,
+      "step": 371
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 3.007994550768793e-06,
+      "loss": 0.1651,
+      "step": 372
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.9819263705971984e-06,
+      "loss": 0.274,
+      "step": 373
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.9559235572557486e-06,
+      "loss": 0.2052,
+      "step": 374
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.929986952993933e-06,
+      "loss": 0.2441,
+      "step": 375
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.9041173979166813e-06,
+      "loss": 0.2067,
+      "step": 376
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.878315729957151e-06,
+      "loss": 0.2262,
+      "step": 377
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.8525827848495912e-06,
+      "loss": 0.1759,
+      "step": 378
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.826919396102269e-06,
+      "loss": 0.2122,
+      "step": 379
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.8013263949704706e-06,
+      "loss": 0.2447,
+      "step": 380
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.77580461042958e-06,
+      "loss": 0.2236,
+      "step": 381
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.75035486914822e-06,
+      "loss": 0.1704,
+      "step": 382
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.7249779954614865e-06,
+      "loss": 0.2155,
+      "step": 383
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.6996748113442397e-06,
+      "loss": 0.2013,
+      "step": 384
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 2.674446136384486e-06,
+      "loss": 0.1242,
+      "step": 385
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 2.6492927877568243e-06,
+      "loss": 0.1077,
+      "step": 386
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 2.6242155801959814e-06,
+      "loss": 0.1202,
+      "step": 387
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 2.599215325970423e-06,
+      "loss": 0.1065,
+      "step": 388
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 2.574292834856037e-06,
+      "loss": 0.112,
+      "step": 389
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 2.5494489141099155e-06,
+      "loss": 0.1099,
+      "step": 390
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 2.5246843684441953e-06,
+      "loss": 0.0902,
+      "step": 391
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.115,
+      "step": 392
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 2.4753966083214613e-06,
+      "loss": 0.1344,
+      "step": 393
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 2.4508749903298086e-06,
+      "loss": 0.0988,
+      "step": 394
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 2.4264359402975683e-06,
+      "loss": 0.0935,
+      "step": 395
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 2.4020802498228333e-06,
+      "loss": 0.0863,
+      "step": 396
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 2.377808707803616e-06,
+      "loss": 0.1165,
+      "step": 397
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 2.3536221004123068e-06,
+      "loss": 0.116,
+      "step": 398
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.3295212110701994e-06,
+      "loss": 0.0955,
+      "step": 399
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.3055068204221226e-06,
+      "loss": 0.0887,
+      "step": 400
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 2.28157970631115e-06,
+      "loss": 0.0977,
+      "step": 401
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 2.2577406437534055e-06,
+      "loss": 0.0857,
+      "step": 402
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 2.2339904049129648e-06,
+      "loss": 0.1049,
+      "step": 403
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 2.2103297590768334e-06,
+      "loss": 0.0902,
+      "step": 404
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 2.186759472630045e-06,
+      "loss": 0.101,
+      "step": 405
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 2.1632803090308194e-06,
+      "loss": 0.0944,
+      "step": 406
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 2.1398930287858515e-06,
+      "loss": 0.1011,
+      "step": 407
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 2.1165983894256647e-06,
+      "loss": 0.0983,
+      "step": 408
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 2.093397145480081e-06,
+      "loss": 0.1193,
+      "step": 409
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 2.070290048453777e-06,
+      "loss": 0.1118,
+      "step": 410
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 2.0472778468019456e-06,
+      "loss": 0.0822,
+      "step": 411
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 2.0243612859060526e-06,
+      "loss": 0.0824,
+      "step": 412
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 2.001541108049687e-06,
+      "loss": 0.1003,
+      "step": 413
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.978818052394528e-06,
+      "loss": 0.1292,
+      "step": 414
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.956192854956397e-06,
+      "loss": 0.0978,
+      "step": 415
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.933666248581418e-06,
+      "loss": 0.1109,
+      "step": 416
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.911238962922282e-06,
+      "loss": 0.0916,
+      "step": 417
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.888911724414612e-06,
+      "loss": 0.0734,
+      "step": 418
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.8666852562534288e-06,
+      "loss": 0.1082,
+      "step": 419
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.8445602783697375e-06,
+      "loss": 0.0735,
+      "step": 420
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.8225375074071943e-06,
+      "loss": 0.0999,
+      "step": 421
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.8006176566989064e-06,
+      "loss": 0.0849,
+      "step": 422
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.778801436244319e-06,
+      "loss": 0.0865,
+      "step": 423
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.7570895526862202e-06,
+      "loss": 0.1245,
+      "step": 424
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.735482709287854e-06,
+      "loss": 0.1155,
+      "step": 425
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.7139816059101372e-06,
+      "loss": 0.0941,
+      "step": 426
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.6925869389889954e-06,
+      "loss": 0.0855,
+      "step": 427
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.6712994015127976e-06,
+      "loss": 0.1066,
+      "step": 428
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.6501196829999179e-06,
+      "loss": 0.0912,
+      "step": 429
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.629048469476398e-06,
+      "loss": 0.0805,
+      "step": 430
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.6080864434537259e-06,
+      "loss": 0.0978,
+      "step": 431
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.5872342839067305e-06,
+      "loss": 0.0821,
+      "step": 432
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.5664926662515834e-06,
+      "loss": 0.0929,
+      "step": 433
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.5458622623239306e-06,
+      "loss": 0.1106,
+      "step": 434
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.525343740357128e-06,
+      "loss": 0.1023,
+      "step": 435
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.5049377649605906e-06,
+      "loss": 0.0907,
+      "step": 436
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.4846449970982747e-06,
+      "loss": 0.0884,
+      "step": 437
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.099,
+      "step": 438
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.4444017094764762e-06,
+      "loss": 0.1076,
+      "step": 439
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.4244524932255026e-06,
+      "loss": 0.1244,
+      "step": 440
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.404619091483546e-06,
+      "loss": 0.0884,
+      "step": 441
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.384902146668497e-06,
+      "loss": 0.1157,
+      "step": 442
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.3653022974261216e-06,
+      "loss": 0.0925,
+      "step": 443
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.3458201786093795e-06,
+      "loss": 0.1063,
+      "step": 444
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.3264564212578613e-06,
+      "loss": 0.0987,
+      "step": 445
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.3072116525773399e-06,
+      "loss": 0.1159,
+      "step": 446
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.2880864959194666e-06,
+      "loss": 0.0787,
+      "step": 447
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.2690815707615727e-06,
+      "loss": 0.0789,
+      "step": 448
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.2501974926866067e-06,
+      "loss": 0.0919,
+      "step": 449
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.2314348733631958e-06,
+      "loss": 0.0977,
+      "step": 450
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.212794320525828e-06,
+      "loss": 0.1385,
+      "step": 451
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.194276437955177e-06,
+      "loss": 0.0776,
+      "step": 452
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.175881825458537e-06,
+      "loss": 0.0822,
+      "step": 453
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.1576110788503985e-06,
+      "loss": 0.1106,
+      "step": 454
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.1394647899331484e-06,
+      "loss": 0.1128,
+      "step": 455
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.1214435464779006e-06,
+      "loss": 0.0835,
+      "step": 456
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.1035479322054594e-06,
+      "loss": 0.0534,
+      "step": 457
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.085778526767407e-06,
+      "loss": 0.1092,
+      "step": 458
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.0681359057273388e-06,
+      "loss": 0.0824,
+      "step": 459
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.050620640542208e-06,
+      "loss": 0.1089,
+      "step": 460
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.0332332985438248e-06,
+      "loss": 0.1,
+      "step": 461
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.0159744429204776e-06,
+      "loss": 0.1081,
+      "step": 462
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 9.988446326986885e-07,
+      "loss": 0.0898,
+      "step": 463
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 9.81844422725109e-07,
+      "loss": 0.0862,
+      "step": 464
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 9.64974363648548e-07,
+      "loss": 0.1157,
+      "step": 465
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 9.482350019021314e-07,
+      "loss": 0.1023,
+      "step": 466
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 9.316268796856093e-07,
+      "loss": 0.1397,
+      "step": 467
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 9.151505349477901e-07,
+      "loss": 0.1318,
+      "step": 468
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.988065013691166e-07,
+      "loss": 0.1084,
+      "step": 469
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 8.8259530834438e-07,
+      "loss": 0.0718,
+      "step": 470
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 8.665174809655707e-07,
+      "loss": 0.1179,
+      "step": 471
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 8.505735400048748e-07,
+      "loss": 0.0964,
+      "step": 472
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 8.347640018977976e-07,
+      "loss": 0.0914,
+      "step": 473
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 8.19089378726447e-07,
+      "loss": 0.0838,
+      "step": 474
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 8.035501782029348e-07,
+      "loss": 0.0839,
+      "step": 475
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.881469036529427e-07,
+      "loss": 0.0858,
+      "step": 476
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.728800539994113e-07,
+      "loss": 0.0994,
+      "step": 477
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.577501237463841e-07,
+      "loss": 0.0939,
+      "step": 478
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.427576029629868e-07,
+      "loss": 0.0941,
+      "step": 479
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.279029772675572e-07,
+      "loss": 0.116,
+      "step": 480
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 7.131867278119131e-07,
+      "loss": 0.0997,
+      "step": 481
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 6.98609331265766e-07,
+      "loss": 0.1012,
+      "step": 482
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 6.841712598012867e-07,
+      "loss": 0.0957,
+      "step": 483
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.0828,
+      "step": 484
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 6.557149582266726e-07,
+      "loss": 0.0887,
+      "step": 485
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 6.416976498362432e-07,
+      "loss": 0.0826,
+      "step": 486
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 6.278215099370388e-07,
+      "loss": 0.102,
+      "step": 487
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 6.140869879870287e-07,
+      "loss": 0.0971,
+      "step": 488
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 6.004945288570813e-07,
+      "loss": 0.0942,
+      "step": 489
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 5.870445728165447e-07,
+      "loss": 0.0809,
+      "step": 490
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 5.737375555189966e-07,
+      "loss": 0.1007,
+      "step": 491
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 5.60573907988124e-07,
+      "loss": 0.0954,
+      "step": 492
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 5.475540566037685e-07,
+      "loss": 0.0896,
+      "step": 493
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 5.346784230881119e-07,
+      "loss": 0.0798,
+      "step": 494
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 5.219474244920164e-07,
+      "loss": 0.0998,
+      "step": 495
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 5.0936147318152e-07,
+      "loss": 0.0859,
+      "step": 496
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 4.96920976824472e-07,
+      "loss": 0.1017,
+      "step": 497
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 4.846263383773364e-07,
+      "loss": 0.0919,
+      "step": 498
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.7247795607213656e-07,
+      "loss": 0.0834,
+      "step": 499
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.604762234035548e-07,
+      "loss": 0.0962,
+      "step": 500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.486215291161894e-07,
+      "loss": 0.0901,
+      "step": 501
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.369142571919599e-07,
+      "loss": 0.0805,
+      "step": 502
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 4.2535478683767173e-07,
+      "loss": 0.1045,
+      "step": 503
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 4.139434924727359e-07,
+      "loss": 0.0901,
+      "step": 504
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 4.0268074371703324e-07,
+      "loss": 0.0974,
+      "step": 505
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 3.915669053789528e-07,
+      "loss": 0.1047,
+      "step": 506
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.0727,
+      "step": 507
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 3.697873950609737e-07,
+      "loss": 0.0828,
+      "step": 508
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 3.591224285347972e-07,
+      "loss": 0.091,
+      "step": 509
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 3.486077833108342e-07,
+      "loss": 0.0707,
+      "step": 510
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 3.382437999658705e-07,
+      "loss": 0.0831,
+      "step": 511
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 3.2803081419664483e-07,
+      "loss": 0.1058,
+      "step": 512
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 3.179691568089799e-07,
+      "loss": 0.102,
+      "step": 513
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 3.0805915370706596e-07,
+      "loss": 0.138,
+      "step": 514
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.983011258829005e-07,
+      "loss": 0.0981,
+      "step": 515
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.88695389405898e-07,
+      "loss": 0.1052,
+      "step": 516
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.7924225541264616e-07,
+      "loss": 0.079,
+      "step": 517
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 2.699420300968314e-07,
+      "loss": 0.102,
+      "step": 518
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 2.6079501469932154e-07,
+      "loss": 0.1104,
+      "step": 519
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.518015054984041e-07,
+      "loss": 0.1007,
+      "step": 520
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.429617938001938e-07,
+      "loss": 0.0771,
+      "step": 521
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.3427616592919587e-07,
+      "loss": 0.0873,
+      "step": 522
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.257449032190323e-07,
+      "loss": 0.0779,
+      "step": 523
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 2.1736828200332628e-07,
+      "loss": 0.0913,
+      "step": 524
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 2.0914657360675606e-07,
+      "loss": 0.079,
+      "step": 525
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 2.0108004433626316e-07,
+      "loss": 0.0872,
+      "step": 526
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 1.9316895547242698e-07,
+      "loss": 0.0913,
+      "step": 527
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.8541356326100436e-07,
+      "loss": 0.1249,
+      "step": 528
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.7781411890462453e-07,
+      "loss": 0.0924,
+      "step": 529
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.7037086855465902e-07,
+      "loss": 0.0917,
+      "step": 530
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.6308405330324294e-07,
+      "loss": 0.1011,
+      "step": 531
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.559539091754686e-07,
+      "loss": 0.1398,
+      "step": 532
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.4898066712173974e-07,
+      "loss": 0.0915,
+      "step": 533
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.4216455301029274e-07,
+      "loss": 0.1069,
+      "step": 534
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.3550578761987675e-07,
+      "loss": 0.1412,
+      "step": 535
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.2900458663260506e-07,
+      "loss": 0.0882,
+      "step": 536
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.2266116062696954e-07,
+      "loss": 0.1067,
+      "step": 537
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.164757150710194e-07,
+      "loss": 0.0994,
+      "step": 538
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.1044845031570383e-07,
+      "loss": 0.1005,
+      "step": 539
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.0457956158838545e-07,
+      "loss": 0.1116,
+      "step": 540
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 9.886923898651534e-08,
+      "loss": 0.0821,
+      "step": 541
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 9.33176674714753e-08,
+      "loss": 0.1077,
+      "step": 542
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 8.792502686258752e-08,
+      "loss": 0.0869,
+      "step": 543
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 8.269149183128988e-08,
+      "loss": 0.0711,
+      "step": 544
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 7.76172318954782e-08,
+      "loss": 0.108,
+      "step": 545
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 7.270241141401568e-08,
+      "loss": 0.0847,
+      "step": 546
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 6.794718958140933e-08,
+      "loss": 0.0918,
+      "step": 547
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 6.335172042265192e-08,
+      "loss": 0.106,
+      "step": 548
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.891615278823537e-08,
+      "loss": 0.0872,
+      "step": 549
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.4640630349329094e-08,
+      "loss": 0.1141,
+      "step": 550
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.052529159312258e-08,
+      "loss": 0.0851,
+      "step": 551
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 4.657026981834623e-08,
+      "loss": 0.084,
+      "step": 552
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 4.2775693130948094e-08,
+      "loss": 0.1081,
+      "step": 553
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 3.91416844399467e-08,
+      "loss": 0.1032,
+      "step": 554
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 3.566836145345032e-08,
+      "loss": 0.1003,
+      "step": 555
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 3.235583667484443e-08,
+      "loss": 0.1128,
+      "step": 556
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2.9204217399144696e-08,
+      "loss": 0.0991,
+      "step": 557
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.6213605709525803e-08,
+      "loss": 0.1097,
+      "step": 558
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.338409847401302e-08,
+      "loss": 0.1033,
+      "step": 559
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2.0715787342343586e-08,
+      "loss": 0.0857,
+      "step": 560
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.820875874300021e-08,
+      "loss": 0.1114,
+      "step": 561
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.5863093880408852e-08,
+      "loss": 0.085,
+      "step": 562
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.3678868732311945e-08,
+      "loss": 0.1088,
+      "step": 563
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.1656154047303691e-08,
+      "loss": 0.0743,
+      "step": 564
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 9.795015342543013e-09,
+      "loss": 0.0933,
+      "step": 565
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.095512901625247e-09,
+      "loss": 0.1196,
+      "step": 566
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 6.557701772635372e-09,
+      "loss": 0.0742,
+      "step": 567
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.181631766362216e-09,
+      "loss": 0.0911,
+      "step": 568
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 3.967347454684745e-09,
+      "loss": 0.0682,
+      "step": 569
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 2.9148881691298812e-09,
+      "loss": 0.09,
+      "step": 570
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 2.0242879995968632e-09,
+      "loss": 0.145,
+      "step": 571
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.2955757932542334e-09,
+      "loss": 0.0886,
+      "step": 572
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 7.287751536050324e-10,
+      "loss": 0.1035,
+      "step": 573
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 3.2390443972241113e-10,
+      "loss": 0.0897,
+      "step": 574
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 8.097676565399504e-11,
+      "loss": 0.0778,
+      "step": 575
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0837,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "step": 576,
+      "total_flos": 8.257647728205496e+17,
+      "train_loss": 0.2478648494127103,
+      "train_runtime": 19054.9588,
+      "train_samples_per_second": 1.625,
+      "train_steps_per_second": 0.03
+    }
+  ],
+  "max_steps": 576,
+  "num_train_epochs": 3,
+  "total_flos": 8.257647728205496e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b9db6c3068c41b45d4e581f86be350bc69310c14b9f4d47c0c2a1fae58a592
+size 3771