13bv1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/home/baaidial/models/llama-2-13b-hf/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.3",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.33.3"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e4ae964650282a197f0409497a1f49113b05ca56db62773ded37e8c728ecc9
+size 9948719433

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9724388278fe252121da2c8c62d94215c2f953403cc50c6d8647d9d6c4912f
+size 9904155408

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a10850c5956604e56447c9397e19e000fa4e1fc4a7f2ee86f5399b87d4fafd
+size 6178978207

pytorch_model.bin.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26031728640
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "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
+  },
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,3682 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9963099630996313,
+  "eval_steps": 500,
+  "global_step": 609,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 1.3013,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 1.2825,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.9473684210526315e-06,
+      "loss": 1.3755,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 1.2644,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 1.2507,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.894736842105263e-06,
+      "loss": 1.1368,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.210526315789474e-06,
+      "loss": 1.1033,
+      "step": 7
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 1.0729,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1842105263157895e-05,
+      "loss": 1.0756,
+      "step": 9
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 1.0396,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.4473684210526317e-05,
+      "loss": 1.0539,
+      "step": 11
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5789473684210526e-05,
+      "loss": 1.085,
+      "step": 12
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.7105263157894737e-05,
+      "loss": 1.0104,
+      "step": 13
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 1.0773,
+      "step": 14
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 1.0052,
+      "step": 15
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 1.0603,
+      "step": 16
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.236842105263158e-05,
+      "loss": 1.0628,
+      "step": 17
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 1.0233,
+      "step": 18
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0953,
+      "step": 19
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.499982279551347e-05,
+      "loss": 1.0786,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.4999291187078104e-05,
+      "loss": 1.0389,
+      "step": 21
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.4998405189766444e-05,
+      "loss": 1.0168,
+      "step": 22
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.4997164828698926e-05,
+      "loss": 1.036,
+      "step": 23
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.4995570139043158e-05,
+      "loss": 1.0171,
+      "step": 24
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.4993621166012923e-05,
+      "loss": 1.0811,
+      "step": 25
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.4991317964866905e-05,
+      "loss": 1.0955,
+      "step": 26
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.4988660600907115e-05,
+      "loss": 1.0038,
+      "step": 27
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.4985649149477043e-05,
+      "loss": 1.0558,
+      "step": 28
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.4982283695959525e-05,
+      "loss": 1.0707,
+      "step": 29
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.4978564335774313e-05,
+      "loss": 1.1162,
+      "step": 30
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.4974491174375374e-05,
+      "loss": 1.006,
+      "step": 31
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.497006432724791e-05,
+      "loss": 1.0481,
+      "step": 32
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.4965283919905065e-05,
+      "loss": 1.0609,
+      "step": 33
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.4960150087884376e-05,
+      "loss": 1.0946,
+      "step": 34
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.4954662976743944e-05,
+      "loss": 1.0222,
+      "step": 35
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.494882274205827e-05,
+      "loss": 1.0427,
+      "step": 36
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.4942629549413894e-05,
+      "loss": 1.0987,
+      "step": 37
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.4936083574404646e-05,
+      "loss": 1.1212,
+      "step": 38
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.4929185002626714e-05,
+      "loss": 1.0986,
+      "step": 39
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.492193402967336e-05,
+      "loss": 1.05,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.4914330861129376e-05,
+      "loss": 1.0784,
+      "step": 41
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.4906375712565245e-05,
+      "loss": 1.0997,
+      "step": 42
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.489806880953106e-05,
+      "loss": 1.0774,
+      "step": 43
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.4889410387550093e-05,
+      "loss": 1.0832,
+      "step": 44
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.488040069211214e-05,
+      "loss": 1.0649,
+      "step": 45
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.487103997866655e-05,
+      "loss": 1.0684,
+      "step": 46
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.4861328512615e-05,
+      "loss": 1.0857,
+      "step": 47
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.485126656930394e-05,
+      "loss": 1.0896,
+      "step": 48
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.4840854434016808e-05,
+      "loss": 1.0719,
+      "step": 49
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.4830092401965942e-05,
+      "loss": 1.0917,
+      "step": 50
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.4818980778284202e-05,
+      "loss": 1.0893,
+      "step": 51
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.4807519878016313e-05,
+      "loss": 1.0136,
+      "step": 52
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.4795710026109954e-05,
+      "loss": 1.0472,
+      "step": 53
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.4783551557406515e-05,
+      "loss": 1.0625,
+      "step": 54
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.4771044816631635e-05,
+      "loss": 1.1197,
+      "step": 55
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.4758190158385402e-05,
+      "loss": 1.0531,
+      "step": 56
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.4744987947132318e-05,
+      "loss": 1.0767,
+      "step": 57
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.473143855719095e-05,
+      "loss": 1.0852,
+      "step": 58
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.4717542372723333e-05,
+      "loss": 1.093,
+      "step": 59
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.4703299787724065e-05,
+      "loss": 1.0991,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.468871120600913e-05,
+      "loss": 1.0982,
+      "step": 61
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.4673777041204478e-05,
+      "loss": 1.1232,
+      "step": 62
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.465849771673427e-05,
+      "loss": 1.0692,
+      "step": 63
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.4642873665808873e-05,
+      "loss": 1.1136,
+      "step": 64
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.4626905331412608e-05,
+      "loss": 1.0771,
+      "step": 65
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.4610593166291143e-05,
+      "loss": 1.0464,
+      "step": 66
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.4593937632938695e-05,
+      "loss": 1.0578,
+      "step": 67
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.457693920358491e-05,
+      "loss": 1.0322,
+      "step": 68
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.455959836018145e-05,
+      "loss": 1.0573,
+      "step": 69
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.454191559438836e-05,
+      "loss": 1.083,
+      "step": 70
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.4523891407560107e-05,
+      "loss": 1.0426,
+      "step": 71
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.4505526310731376e-05,
+      "loss": 1.0706,
+      "step": 72
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.448682082460257e-05,
+      "loss": 1.089,
+      "step": 73
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.446777547952507e-05,
+      "loss": 1.0918,
+      "step": 74
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.4448390815486165e-05,
+      "loss": 1.0869,
+      "step": 75
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.4428667382093762e-05,
+      "loss": 1.0751,
+      "step": 76
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.440860573856081e-05,
+      "loss": 1.0684,
+      "step": 77
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.438820645368942e-05,
+      "loss": 1.0704,
+      "step": 78
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.4367470105854766e-05,
+      "loss": 1.0671,
+      "step": 79
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.4346397282988666e-05,
+      "loss": 1.0434,
+      "step": 80
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.432498858256292e-05,
+      "loss": 1.0605,
+      "step": 81
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.4303244611572372e-05,
+      "loss": 1.0536,
+      "step": 82
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.4281165986517696e-05,
+      "loss": 1.0807,
+      "step": 83
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.425875333338792e-05,
+      "loss": 1.0605,
+      "step": 84
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.4236007287642664e-05,
+      "loss": 1.056,
+      "step": 85
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.421292849419416e-05,
+      "loss": 1.0294,
+      "step": 86
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.4189517607388918e-05,
+      "loss": 1.0571,
+      "step": 87
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.416577529098921e-05,
+      "loss": 1.1025,
+      "step": 88
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.4141702218154232e-05,
+      "loss": 1.1459,
+      "step": 89
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.4117299071421023e-05,
+      "loss": 1.0755,
+      "step": 90
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.4092566542685123e-05,
+      "loss": 1.0686,
+      "step": 91
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.4067505333180938e-05,
+      "loss": 1.0586,
+      "step": 92
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.404211615346187e-05,
+      "loss": 1.1033,
+      "step": 93
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.401639972338016e-05,
+      "loss": 1.0253,
+      "step": 94
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.399035677206651e-05,
+      "loss": 1.0888,
+      "step": 95
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.396398803790936e-05,
+      "loss": 1.0677,
+      "step": 96
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.393729426853399e-05,
+      "loss": 1.0582,
+      "step": 97
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.3910276220781314e-05,
+      "loss": 1.0223,
+      "step": 98
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.3882934660686418e-05,
+      "loss": 1.0885,
+      "step": 99
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.3855270363456833e-05,
+      "loss": 1.0553,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.382728411345058e-05,
+      "loss": 1.1293,
+      "step": 101
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.3798976704153906e-05,
+      "loss": 1.1106,
+      "step": 102
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.3770348938158805e-05,
+      "loss": 1.0647,
+      "step": 103
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.3741401627140242e-05,
+      "loss": 1.078,
+      "step": 104
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.371213559183316e-05,
+      "loss": 1.0344,
+      "step": 105
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.3682551662009203e-05,
+      "loss": 1.095,
+      "step": 106
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3652650676453188e-05,
+      "loss": 1.0794,
+      "step": 107
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.362243348293931e-05,
+      "loss": 0.9938,
+      "step": 108
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3591900938207147e-05,
+      "loss": 1.1374,
+      "step": 109
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3561053907937315e-05,
+      "loss": 1.0443,
+      "step": 110
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.352989326672696e-05,
+      "loss": 1.0452,
+      "step": 111
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.349841989806495e-05,
+      "loss": 1.0359,
+      "step": 112
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.346663469430683e-05,
+      "loss": 1.0973,
+      "step": 113
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.3434538556649515e-05,
+      "loss": 1.138,
+      "step": 114
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.3402132395105737e-05,
+      "loss": 1.0806,
+      "step": 115
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.336941712847825e-05,
+      "loss": 1.1112,
+      "step": 116
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.3336393684333778e-05,
+      "loss": 1.0837,
+      "step": 117
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.3303062998976712e-05,
+      "loss": 1.0794,
+      "step": 118
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.3269426017422576e-05,
+      "loss": 1.0757,
+      "step": 119
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.3235483693371214e-05,
+      "loss": 0.9923,
+      "step": 120
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.3201236989179766e-05,
+      "loss": 1.0442,
+      "step": 121
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.3166686875835365e-05,
+      "loss": 1.0608,
+      "step": 122
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.313183433292764e-05,
+      "loss": 1.0806,
+      "step": 123
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.3096680348620886e-05,
+      "loss": 1.0728,
+      "step": 124
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.3061225919626124e-05,
+      "loss": 1.0979,
+      "step": 125
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.3025472051172755e-05,
+      "loss": 1.0827,
+      "step": 126
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.2989419756980134e-05,
+      "loss": 1.0715,
+      "step": 127
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.295307005922879e-05,
+      "loss": 1.0668,
+      "step": 128
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.2916423988531437e-05,
+      "loss": 1.0726,
+      "step": 129
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.2879482583903783e-05,
+      "loss": 1.1038,
+      "step": 130
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.2842246892735053e-05,
+      "loss": 1.0698,
+      "step": 131
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.2804717970758286e-05,
+      "loss": 1.0782,
+      "step": 132
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.2766896882020422e-05,
+      "loss": 1.0834,
+      "step": 133
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.2728784698852114e-05,
+      "loss": 1.0536,
+      "step": 134
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.2690382501837344e-05,
+      "loss": 1.0867,
+      "step": 135
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.2651691379782764e-05,
+      "loss": 1.0369,
+      "step": 136
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.2612712429686845e-05,
+      "loss": 1.0474,
+      "step": 137
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.2573446756708754e-05,
+      "loss": 1.129,
+      "step": 138
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.2533895474137047e-05,
+      "loss": 1.0561,
+      "step": 139
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.2494059703358073e-05,
+      "loss": 1.1228,
+      "step": 140
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.24539405738242e-05,
+      "loss": 1.1673,
+      "step": 141
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.2413539223021794e-05,
+      "loss": 1.0184,
+      "step": 142
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.237285679643895e-05,
+      "loss": 1.0699,
+      "step": 143
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.2331894447533035e-05,
+      "loss": 1.0924,
+      "step": 144
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.229065333769796e-05,
+      "loss": 1.0106,
+      "step": 145
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.2249134636231285e-05,
+      "loss": 1.0525,
+      "step": 146
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.2207339520301033e-05,
+      "loss": 1.1001,
+      "step": 147
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.216526917491234e-05,
+      "loss": 1.0832,
+      "step": 148
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.2122924792873827e-05,
+      "loss": 0.9838,
+      "step": 149
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.2080307574763824e-05,
+      "loss": 1.0705,
+      "step": 150
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.2037418728896282e-05,
+      "loss": 1.1082,
+      "step": 151
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.1994259471286545e-05,
+      "loss": 1.0794,
+      "step": 152
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.1950831025616873e-05,
+      "loss": 1.0738,
+      "step": 153
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.190713462320173e-05,
+      "loss": 1.0687,
+      "step": 154
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.186317150295289e-05,
+      "loss": 0.9987,
+      "step": 155
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.1818942911344283e-05,
+      "loss": 1.0749,
+      "step": 156
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.17744501023767e-05,
+      "loss": 1.053,
+      "step": 157
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.1729694337542196e-05,
+      "loss": 1.0967,
+      "step": 158
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.168467688578834e-05,
+      "loss": 1.1154,
+      "step": 159
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.163939902348225e-05,
+      "loss": 1.0552,
+      "step": 160
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1593862034374365e-05,
+      "loss": 1.0798,
+      "step": 161
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.15480672095621e-05,
+      "loss": 1.073,
+      "step": 162
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.15020158474532e-05,
+      "loss": 1.0787,
+      "step": 163
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.145570925372894e-05,
+      "loss": 1.034,
+      "step": 164
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.1409148741307107e-05,
+      "loss": 1.0699,
+      "step": 165
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.1362335630304768e-05,
+      "loss": 0.9939,
+      "step": 166
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.131527124800086e-05,
+      "loss": 1.0616,
+      "step": 167
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.1267956928798525e-05,
+      "loss": 0.992,
+      "step": 168
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.1220394014187312e-05,
+      "loss": 1.0463,
+      "step": 169
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.1172583852705115e-05,
+      "loss": 1.071,
+      "step": 170
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.1124527799899953e-05,
+      "loss": 1.0274,
+      "step": 171
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.1076227218291535e-05,
+      "loss": 1.0593,
+      "step": 172
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.1027683477332623e-05,
+      "loss": 1.0286,
+      "step": 173
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.0978897953370204e-05,
+      "loss": 1.0657,
+      "step": 174
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.0929872029606472e-05,
+      "loss": 1.0616,
+      "step": 175
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.088060709605962e-05,
+      "loss": 1.0425,
+      "step": 176
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.08311045495244e-05,
+      "loss": 1.0024,
+      "step": 177
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.078136579353255e-05,
+      "loss": 1.0252,
+      "step": 178
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.0731392238312985e-05,
+      "loss": 1.0623,
+      "step": 179
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.0681185300751814e-05,
+      "loss": 1.0712,
+      "step": 180
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.0630746404352168e-05,
+      "loss": 1.0976,
+      "step": 181
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.058007697919386e-05,
+      "loss": 1.0481,
+      "step": 182
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.0529178461892785e-05,
+      "loss": 1.0502,
+      "step": 183
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.0478052295560253e-05,
+      "loss": 1.0707,
+      "step": 184
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.0426699929762035e-05,
+      "loss": 1.0669,
+      "step": 185
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.037512282047726e-05,
+      "loss": 1.0067,
+      "step": 186
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.0323322430057166e-05,
+      "loss": 1.1202,
+      "step": 187
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.0271300227183598e-05,
+      "loss": 1.074,
+      "step": 188
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.02190576868274e-05,
+      "loss": 1.0394,
+      "step": 189
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.016659629020658e-05,
+      "loss": 1.0368,
+      "step": 190
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0113917524744308e-05,
+      "loss": 1.0733,
+      "step": 191
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0061022884026762e-05,
+      "loss": 1.0594,
+      "step": 192
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.0007913867760763e-05,
+      "loss": 1.0401,
+      "step": 193
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.995459198173127e-05,
+      "loss": 1.0903,
+      "step": 194
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.9901058737758667e-05,
+      "loss": 1.1046,
+      "step": 195
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.9847315653655915e-05,
+      "loss": 1.0478,
+      "step": 196
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.9793364253185518e-05,
+      "loss": 1.0747,
+      "step": 197
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.9739206066016307e-05,
+      "loss": 1.0484,
+      "step": 198
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.9684842627680088e-05,
+      "loss": 1.0897,
+      "step": 199
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.963027547952808e-05,
+      "loss": 1.0715,
+      "step": 200
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.9575506168687247e-05,
+      "loss": 1.0671,
+      "step": 201
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.9520536248016403e-05,
+      "loss": 0.9719,
+      "step": 202
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.946536727606219e-05,
+      "loss": 1.0384,
+      "step": 203
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.941000081701492e-05,
+      "loss": 0.7968,
+      "step": 204
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.9354438440664167e-05,
+      "loss": 0.6873,
+      "step": 205
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.929868172235433e-05,
+      "loss": 0.6435,
+      "step": 206
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.9242732242939893e-05,
+      "loss": 0.6083,
+      "step": 207
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.9186591588740667e-05,
+      "loss": 0.6499,
+      "step": 208
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.913026135149678e-05,
+      "loss": 0.6342,
+      "step": 209
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.9073743128323558e-05,
+      "loss": 0.6186,
+      "step": 210
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.9017038521666232e-05,
+      "loss": 0.6751,
+      "step": 211
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.8960149139254513e-05,
+      "loss": 0.6175,
+      "step": 212
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.8903076594057013e-05,
+      "loss": 0.5863,
+      "step": 213
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.88458225042355e-05,
+      "loss": 0.6271,
+      "step": 214
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.8788388493099033e-05,
+      "loss": 0.6416,
+      "step": 215
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.8730776189057918e-05,
+      "loss": 0.653,
+      "step": 216
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.8672987225577552e-05,
+      "loss": 0.6631,
+      "step": 217
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.8615023241132127e-05,
+      "loss": 0.6022,
+      "step": 218
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.855688587915813e-05,
+      "loss": 0.645,
+      "step": 219
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.8498576788007775e-05,
+      "loss": 0.6546,
+      "step": 220
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.8440097620902284e-05,
+      "loss": 0.6453,
+      "step": 221
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.838145003588497e-05,
+      "loss": 0.6509,
+      "step": 222
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.832263569577427e-05,
+      "loss": 0.5689,
+      "step": 223
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.8263656268116576e-05,
+      "loss": 0.5919,
+      "step": 224
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.8204513425138952e-05,
+      "loss": 0.6308,
+      "step": 225
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.8145208843701742e-05,
+      "loss": 0.6666,
+      "step": 226
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.808574420525101e-05,
+      "loss": 0.584,
+      "step": 227
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.8026121195770874e-05,
+      "loss": 0.5634,
+      "step": 228
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.7966341505735695e-05,
+      "loss": 0.5975,
+      "step": 229
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.7906406830062156e-05,
+      "loss": 0.6015,
+      "step": 230
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.7846318868061212e-05,
+      "loss": 0.5879,
+      "step": 231
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.7786079323389893e-05,
+      "loss": 0.6187,
+      "step": 232
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.7725689904003006e-05,
+      "loss": 0.617,
+      "step": 233
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.766515232210473e-05,
+      "loss": 0.6135,
+      "step": 234
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.7604468294100034e-05,
+      "loss": 0.6676,
+      "step": 235
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.754363954054605e-05,
+      "loss": 0.6294,
+      "step": 236
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.7482667786103256e-05,
+      "loss": 0.6308,
+      "step": 237
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.7421554759486614e-05,
+      "loss": 0.5851,
+      "step": 238
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.736030219341651e-05,
+      "loss": 0.6303,
+      "step": 239
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.7298911824569676e-05,
+      "loss": 0.6124,
+      "step": 240
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.7237385393529916e-05,
+      "loss": 0.6291,
+      "step": 241
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.7175724644738773e-05,
+      "loss": 0.6457,
+      "step": 242
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.7113931326446054e-05,
+      "loss": 0.6475,
+      "step": 243
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.705200719066028e-05,
+      "loss": 0.6723,
+      "step": 244
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.6989953993098998e-05,
+      "loss": 0.6456,
+      "step": 245
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.6927773493139014e-05,
+      "loss": 0.613,
+      "step": 246
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.68654674537665e-05,
+      "loss": 0.6202,
+      "step": 247
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.6803037641527002e-05,
+      "loss": 0.5821,
+      "step": 248
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.674048582647538e-05,
+      "loss": 0.6698,
+      "step": 249
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.6677813782125592e-05,
+      "loss": 0.6762,
+      "step": 250
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.6615023285400432e-05,
+      "loss": 0.6087,
+      "step": 251
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.6552116116581133e-05,
+      "loss": 0.6154,
+      "step": 252
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.648909405925691e-05,
+      "loss": 0.6162,
+      "step": 253
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.6425958900274362e-05,
+      "loss": 0.624,
+      "step": 254
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.6362712429686846e-05,
+      "loss": 0.5986,
+      "step": 255
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.629935644070369e-05,
+      "loss": 0.6152,
+      "step": 256
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.6235892729639378e-05,
+      "loss": 0.6114,
+      "step": 257
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.617232309586261e-05,
+      "loss": 0.603,
+      "step": 258
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.6108649341745262e-05,
+      "loss": 0.6791,
+      "step": 259
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.604487327261133e-05,
+      "loss": 0.6662,
+      "step": 260
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.59809966966857e-05,
+      "loss": 0.6407,
+      "step": 261
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.591702142504291e-05,
+      "loss": 0.629,
+      "step": 262
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5852949271555787e-05,
+      "loss": 0.6191,
+      "step": 263
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.5788782052844015e-05,
+      "loss": 0.6332,
+      "step": 264
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.572452158822265e-05,
+      "loss": 0.642,
+      "step": 265
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.5660169699650503e-05,
+      "loss": 0.6257,
+      "step": 266
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.5595728211678525e-05,
+      "loss": 0.6622,
+      "step": 267
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.553119895139803e-05,
+      "loss": 0.6221,
+      "step": 268
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.546658374838894e-05,
+      "loss": 0.641,
+      "step": 269
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.5401884434667864e-05,
+      "loss": 0.6199,
+      "step": 270
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.5337102844636188e-05,
+      "loss": 0.6204,
+      "step": 271
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.5272240815028067e-05,
+      "loss": 0.6315,
+      "step": 272
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.520730018485832e-05,
+      "loss": 0.6727,
+      "step": 273
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.5142282795370305e-05,
+      "loss": 0.6628,
+      "step": 274
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.5077190489983728e-05,
+      "loss": 0.6742,
+      "step": 275
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.5012025114242355e-05,
+      "loss": 0.6381,
+      "step": 276
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.49467885157617e-05,
+      "loss": 0.6467,
+      "step": 277
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.4881482544176627e-05,
+      "loss": 0.6497,
+      "step": 278
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.4816109051088931e-05,
+      "loss": 0.6165,
+      "step": 279
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.4750669890014807e-05,
+      "loss": 0.6183,
+      "step": 280
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.468516691633233e-05,
+      "loss": 0.6557,
+      "step": 281
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.4619601987228832e-05,
+      "loss": 0.6581,
+      "step": 282
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.4553976961648244e-05,
+      "loss": 0.6562,
+      "step": 283
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.4488293700238401e-05,
+      "loss": 0.6587,
+      "step": 284
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.4422554065298286e-05,
+      "loss": 0.6124,
+      "step": 285
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.435675992072521e-05,
+      "loss": 0.6168,
+      "step": 286
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.4290913131961997e-05,
+      "loss": 0.6346,
+      "step": 287
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.4225015565944072e-05,
+      "loss": 0.6851,
+      "step": 288
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.4159069091046526e-05,
+      "loss": 0.652,
+      "step": 289
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.4093075577031157e-05,
+      "loss": 0.6331,
+      "step": 290
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.4027036894993442e-05,
+      "loss": 0.6402,
+      "step": 291
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.396095491730951e-05,
+      "loss": 0.6072,
+      "step": 292
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.3894831517583017e-05,
+      "loss": 0.6314,
+      "step": 293
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.3828668570592069e-05,
+      "loss": 0.5981,
+      "step": 294
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.3762467952236027e-05,
+      "loss": 0.6045,
+      "step": 295
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.369623153948235e-05,
+      "loss": 0.6773,
+      "step": 296
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3629961210313353e-05,
+      "loss": 0.6185,
+      "step": 297
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.3563658843672985e-05,
+      "loss": 0.6684,
+      "step": 298
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.3497326319413539e-05,
+      "loss": 0.5952,
+      "step": 299
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.3430965518242362e-05,
+      "loss": 0.6146,
+      "step": 300
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.336457832166852e-05,
+      "loss": 0.6532,
+      "step": 301
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.3298166611949467e-05,
+      "loss": 0.6521,
+      "step": 302
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.3231732272037672e-05,
+      "loss": 0.6157,
+      "step": 303
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.3165277185527234e-05,
+      "loss": 0.6474,
+      "step": 304
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.3098803236600462e-05,
+      "loss": 0.5977,
+      "step": 305
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.3032312309974482e-05,
+      "loss": 0.624,
+      "step": 306
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.2965806290847768e-05,
+      "loss": 0.6255,
+      "step": 307
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2899287064846725e-05,
+      "loss": 0.6181,
+      "step": 308
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2832756517972185e-05,
+      "loss": 0.6159,
+      "step": 309
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2766216536545984e-05,
+      "loss": 0.6414,
+      "step": 310
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2699669007157435e-05,
+      "loss": 0.5773,
+      "step": 311
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.2633115816609867e-05,
+      "loss": 0.627,
+      "step": 312
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.2566558851867106e-05,
+      "loss": 0.5812,
+      "step": 313
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.25e-05,
+      "loss": 0.6219,
+      "step": 314
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.2433441148132897e-05,
+      "loss": 0.6287,
+      "step": 315
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.236688418339014e-05,
+      "loss": 0.5863,
+      "step": 316
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.2300330992842566e-05,
+      "loss": 0.5904,
+      "step": 317
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.223378346345402e-05,
+      "loss": 0.6398,
+      "step": 318
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.2167243482027816e-05,
+      "loss": 0.6025,
+      "step": 319
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.2100712935153283e-05,
+      "loss": 0.6047,
+      "step": 320
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.2034193709152231e-05,
+      "loss": 0.6134,
+      "step": 321
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.196768769002552e-05,
+      "loss": 0.6624,
+      "step": 322
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.190119676339954e-05,
+      "loss": 0.6065,
+      "step": 323
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.1834722814472771e-05,
+      "loss": 0.6245,
+      "step": 324
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.1768267727962328e-05,
+      "loss": 0.6223,
+      "step": 325
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.1701833388050536e-05,
+      "loss": 0.638,
+      "step": 326
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.1635421678331485e-05,
+      "loss": 0.6685,
+      "step": 327
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.1569034481757644e-05,
+      "loss": 0.6236,
+      "step": 328
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.150267368058646e-05,
+      "loss": 0.6174,
+      "step": 329
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.1436341156327016e-05,
+      "loss": 0.6431,
+      "step": 330
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.137003878968665e-05,
+      "loss": 0.6326,
+      "step": 331
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.1303768460517657e-05,
+      "loss": 0.6585,
+      "step": 332
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.1237532047763974e-05,
+      "loss": 0.653,
+      "step": 333
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.1171331429407934e-05,
+      "loss": 0.6169,
+      "step": 334
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.1105168482416984e-05,
+      "loss": 0.5823,
+      "step": 335
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.1039045082690496e-05,
+      "loss": 0.6307,
+      "step": 336
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.0972963105006556e-05,
+      "loss": 0.6119,
+      "step": 337
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.0906924422968846e-05,
+      "loss": 0.6236,
+      "step": 338
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.0840930908953477e-05,
+      "loss": 0.5794,
+      "step": 339
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.0774984434055932e-05,
+      "loss": 0.6227,
+      "step": 340
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.0709086868038005e-05,
+      "loss": 0.6367,
+      "step": 341
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.064324007927479e-05,
+      "loss": 0.6325,
+      "step": 342
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.0577445934701717e-05,
+      "loss": 0.6073,
+      "step": 343
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.0511706299761602e-05,
+      "loss": 0.6616,
+      "step": 344
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.044602303835176e-05,
+      "loss": 0.6514,
+      "step": 345
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.0380398012771169e-05,
+      "loss": 0.6421,
+      "step": 346
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0314833083667672e-05,
+      "loss": 0.6286,
+      "step": 347
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0249330109985198e-05,
+      "loss": 0.6372,
+      "step": 348
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.0183890948911074e-05,
+      "loss": 0.6379,
+      "step": 349
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.0118517455823374e-05,
+      "loss": 0.6726,
+      "step": 350
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.0053211484238303e-05,
+      "loss": 0.6715,
+      "step": 351
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.987974885757647e-06,
+      "loss": 0.6376,
+      "step": 352
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 9.922809510016277e-06,
+      "loss": 0.6052,
+      "step": 353
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 9.857717204629696e-06,
+      "loss": 0.6083,
+      "step": 354
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 9.792699815141685e-06,
+      "loss": 0.6343,
+      "step": 355
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 9.727759184971936e-06,
+      "loss": 0.631,
+      "step": 356
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 9.662897155363814e-06,
+      "loss": 0.6598,
+      "step": 357
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 9.598115565332142e-06,
+      "loss": 0.6396,
+      "step": 358
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 9.533416251611064e-06,
+      "loss": 0.6778,
+      "step": 359
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 9.468801048601972e-06,
+      "loss": 0.6252,
+      "step": 360
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 9.404271788321482e-06,
+      "loss": 0.6119,
+      "step": 361
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 9.339830300349498e-06,
+      "loss": 0.6523,
+      "step": 362
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 9.275478411777354e-06,
+      "loss": 0.6336,
+      "step": 363
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 9.211217947155986e-06,
+      "loss": 0.592,
+      "step": 364
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 9.147050728444215e-06,
+      "loss": 0.6204,
+      "step": 365
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 9.08297857495709e-06,
+      "loss": 0.6273,
+      "step": 366
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 9.0190033033143e-06,
+      "loss": 0.5883,
+      "step": 367
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 8.955126727388672e-06,
+      "loss": 0.6282,
+      "step": 368
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 8.89135065825474e-06,
+      "loss": 0.6745,
+      "step": 369
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 8.827676904137397e-06,
+      "loss": 0.6146,
+      "step": 370
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 8.76410727036062e-06,
+      "loss": 0.5944,
+      "step": 371
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 8.700643559296313e-06,
+      "loss": 0.6359,
+      "step": 372
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.637287570313159e-06,
+      "loss": 0.5846,
+      "step": 373
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.574041099725644e-06,
+      "loss": 0.6315,
+      "step": 374
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 8.510905940743093e-06,
+      "loss": 0.5993,
+      "step": 375
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 8.447883883418866e-06,
+      "loss": 0.652,
+      "step": 376
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 8.38497671459957e-06,
+      "loss": 0.6542,
+      "step": 377
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 8.32218621787441e-06,
+      "loss": 0.6168,
+      "step": 378
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 8.25951417352462e-06,
+      "loss": 0.632,
+      "step": 379
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 8.196962358473e-06,
+      "loss": 0.6016,
+      "step": 380
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 8.134532546233505e-06,
+      "loss": 0.5967,
+      "step": 381
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 8.072226506860988e-06,
+      "loss": 0.6398,
+      "step": 382
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 8.010046006901001e-06,
+      "loss": 0.6485,
+      "step": 383
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 7.947992809339723e-06,
+      "loss": 0.588,
+      "step": 384
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 7.88606867355395e-06,
+      "loss": 0.6784,
+      "step": 385
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 7.824275355261233e-06,
+      "loss": 0.6223,
+      "step": 386
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 7.762614606470084e-06,
+      "loss": 0.5966,
+      "step": 387
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 7.701088175430327e-06,
+      "loss": 0.6124,
+      "step": 388
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 7.639697806583493e-06,
+      "loss": 0.637,
+      "step": 389
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 7.578445240513393e-06,
+      "loss": 0.6198,
+      "step": 390
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 7.517332213896743e-06,
+      "loss": 0.6397,
+      "step": 391
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 7.456360459453952e-06,
+      "loss": 0.6308,
+      "step": 392
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 7.395531705899969e-06,
+      "loss": 0.5814,
+      "step": 393
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 7.334847677895276e-06,
+      "loss": 0.5953,
+      "step": 394
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 7.274310095997e-06,
+      "loss": 0.6071,
+      "step": 395
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.213920676610112e-06,
+      "loss": 0.6304,
+      "step": 396
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.153681131938791e-06,
+      "loss": 0.6411,
+      "step": 397
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 7.093593169937849e-06,
+      "loss": 0.6012,
+      "step": 398
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 7.033658494264309e-06,
+      "loss": 0.6503,
+      "step": 399
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.973878804229131e-06,
+      "loss": 0.6363,
+      "step": 400
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.914255794748989e-06,
+      "loss": 0.6212,
+      "step": 401
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.8547911562982595e-06,
+      "loss": 0.6694,
+      "step": 402
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.7954865748610515e-06,
+      "loss": 0.6147,
+      "step": 403
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 6.736343731883425e-06,
+      "loss": 0.6615,
+      "step": 404
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 6.677364304225731e-06,
+      "loss": 0.602,
+      "step": 405
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.618549964115033e-06,
+      "loss": 0.604,
+      "step": 406
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.559902379097721e-06,
+      "loss": 0.4458,
+      "step": 407
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 6.501423211992224e-06,
+      "loss": 0.3383,
+      "step": 408
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 6.443114120841874e-06,
+      "loss": 0.3288,
+      "step": 409
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 6.384976758867875e-06,
+      "loss": 0.3252,
+      "step": 410
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 6.32701277442245e-06,
+      "loss": 0.3226,
+      "step": 411
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 6.269223810942086e-06,
+      "loss": 0.3122,
+      "step": 412
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 6.211611506900973e-06,
+      "loss": 0.2519,
+      "step": 413
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 6.1541774957645045e-06,
+      "loss": 0.3158,
+      "step": 414
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 6.096923405942989e-06,
+      "loss": 0.2846,
+      "step": 415
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 6.03985086074549e-06,
+      "loss": 0.2747,
+      "step": 416
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 5.982961478333768e-06,
+      "loss": 0.2876,
+      "step": 417
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 5.926256871676443e-06,
+      "loss": 0.2596,
+      "step": 418
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 5.86973864850322e-06,
+      "loss": 0.28,
+      "step": 419
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 5.813408411259331e-06,
+      "loss": 0.2694,
+      "step": 420
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 5.757267757060109e-06,
+      "loss": 0.2707,
+      "step": 421
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 5.701318277645675e-06,
+      "loss": 0.2814,
+      "step": 422
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 5.645561559335832e-06,
+      "loss": 0.2916,
+      "step": 423
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 5.589999182985087e-06,
+      "loss": 0.3062,
+      "step": 424
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 5.534632723937809e-06,
+      "loss": 0.2818,
+      "step": 425
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 5.479463751983603e-06,
+      "loss": 0.263,
+      "step": 426
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 5.424493831312757e-06,
+      "loss": 0.2992,
+      "step": 427
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 5.369724520471925e-06,
+      "loss": 0.2966,
+      "step": 428
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 5.315157372319915e-06,
+      "loss": 0.2803,
+      "step": 429
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 5.2607939339836945e-06,
+      "loss": 0.2749,
+      "step": 430
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 5.2066357468144824e-06,
+      "loss": 0.2728,
+      "step": 431
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 5.152684346344087e-06,
+      "loss": 0.2545,
+      "step": 432
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 5.0989412622413345e-06,
+      "loss": 0.2722,
+      "step": 433
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 5.0454080182687314e-06,
+      "loss": 0.3021,
+      "step": 434
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.992086132239238e-06,
+      "loss": 0.2483,
+      "step": 435
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 4.938977115973242e-06,
+      "loss": 0.2703,
+      "step": 436
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 4.886082475255694e-06,
+      "loss": 0.2829,
+      "step": 437
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 4.833403709793424e-06,
+      "loss": 0.2634,
+      "step": 438
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 4.780942313172602e-06,
+      "loss": 0.2684,
+      "step": 439
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 4.728699772816407e-06,
+      "loss": 0.3123,
+      "step": 440
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 4.6766775699428365e-06,
+      "loss": 0.2837,
+      "step": 441
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 4.624877179522742e-06,
+      "loss": 0.2915,
+      "step": 442
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 4.573300070237973e-06,
+      "loss": 0.305,
+      "step": 443
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 4.5219477044397525e-06,
+      "loss": 0.2537,
+      "step": 444
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 4.470821538107219e-06,
+      "loss": 0.2782,
+      "step": 445
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 4.419923020806148e-06,
+      "loss": 0.3202,
+      "step": 446
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 4.36925359564783e-06,
+      "loss": 0.2547,
+      "step": 447
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 4.318814699248188e-06,
+      "loss": 0.2707,
+      "step": 448
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 4.268607761687019e-06,
+      "loss": 0.246,
+      "step": 449
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 4.218634206467449e-06,
+      "loss": 0.2737,
+      "step": 450
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 4.1688954504756e-06,
+      "loss": 0.2921,
+      "step": 451
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 4.119392903940384e-06,
+      "loss": 0.2677,
+      "step": 452
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 4.07012797039353e-06,
+      "loss": 0.2979,
+      "step": 453
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 4.021102046629799e-06,
+      "loss": 0.2459,
+      "step": 454
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.972316522667381e-06,
+      "loss": 0.2745,
+      "step": 455
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.923772781708468e-06,
+      "loss": 0.2943,
+      "step": 456
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.875472200100051e-06,
+      "loss": 0.2403,
+      "step": 457
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.827416147294888e-06,
+      "loss": 0.2781,
+      "step": 458
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.7796059858126927e-06,
+      "loss": 0.2766,
+      "step": 459
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.7320430712014796e-06,
+      "loss": 0.2738,
+      "step": 460
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 3.6847287519991434e-06,
+      "loss": 0.3136,
+      "step": 461
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 3.637664369695233e-06,
+      "loss": 0.2902,
+      "step": 462
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 3.590851258692894e-06,
+      "loss": 0.2516,
+      "step": 463
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 3.5442907462710605e-06,
+      "loss": 0.2668,
+      "step": 464
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 3.4979841525468016e-06,
+      "loss": 0.2789,
+      "step": 465
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 3.451932790437898e-06,
+      "loss": 0.2794,
+      "step": 466
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 3.4061379656256345e-06,
+      "loss": 0.273,
+      "step": 467
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 3.3606009765177555e-06,
+      "loss": 0.2828,
+      "step": 468
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 3.3153231142116617e-06,
+      "loss": 0.2836,
+      "step": 469
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 3.270305662457805e-06,
+      "loss": 0.2781,
+      "step": 470
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 3.225549897623302e-06,
+      "loss": 0.2911,
+      "step": 471
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 3.181057088655719e-06,
+      "loss": 0.3071,
+      "step": 472
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 3.136828497047116e-06,
+      "loss": 0.2583,
+      "step": 473
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 3.0928653767982695e-06,
+      "loss": 0.2976,
+      "step": 474
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 3.0491689743831277e-06,
+      "loss": 0.2727,
+      "step": 475
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 3.005740528713458e-06,
+      "loss": 0.2843,
+      "step": 476
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.9625812711037206e-06,
+      "loss": 0.2655,
+      "step": 477
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.91969242523618e-06,
+      "loss": 0.2759,
+      "step": 478
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.87707520712617e-06,
+      "loss": 0.272,
+      "step": 479
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.834730825087663e-06,
+      "loss": 0.2734,
+      "step": 480
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.7926604796989676e-06,
+      "loss": 0.312,
+      "step": 481
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.7508653637687176e-06,
+      "loss": 0.2608,
+      "step": 482
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.709346662302041e-06,
+      "loss": 0.3084,
+      "step": 483
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.6681055524669694e-06,
+      "loss": 0.3209,
+      "step": 484
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.6271432035610513e-06,
+      "loss": 0.2781,
+      "step": 485
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.5864607769782084e-06,
+      "loss": 0.2379,
+      "step": 486
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.5460594261757996e-06,
+      "loss": 0.2945,
+      "step": 487
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.5059402966419303e-06,
+      "loss": 0.2545,
+      "step": 488
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.466104525862957e-06,
+      "loss": 0.285,
+      "step": 489
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.426553243291249e-06,
+      "loss": 0.2818,
+      "step": 490
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 2.3872875703131583e-06,
+      "loss": 0.2743,
+      "step": 491
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 2.3483086202172377e-06,
+      "loss": 0.2991,
+      "step": 492
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.309617498162657e-06,
+      "loss": 0.2778,
+      "step": 493
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.271215301147887e-06,
+      "loss": 0.2723,
+      "step": 494
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 2.2331031179795792e-06,
+      "loss": 0.2684,
+      "step": 495
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 2.1952820292417143e-06,
+      "loss": 0.2818,
+      "step": 496
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 2.1577531072649495e-06,
+      "loss": 0.2658,
+      "step": 497
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 2.120517416096217e-06,
+      "loss": 0.2865,
+      "step": 498
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 2.083576011468562e-06,
+      "loss": 0.2744,
+      "step": 499
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 2.0469299407712112e-06,
+      "loss": 0.2939,
+      "step": 500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 2.010580243019865e-06,
+      "loss": 0.3174,
+      "step": 501
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.9745279488272484e-06,
+      "loss": 0.2805,
+      "step": 502
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.938774080373884e-06,
+      "loss": 0.2587,
+      "step": 503
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.9033196513791138e-06,
+      "loss": 0.2591,
+      "step": 504
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.8681656670723663e-06,
+      "loss": 0.28,
+      "step": 505
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.833313124164636e-06,
+      "loss": 0.2757,
+      "step": 506
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.7987630108202355e-06,
+      "loss": 0.2684,
+      "step": 507
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.764516306628787e-06,
+      "loss": 0.3003,
+      "step": 508
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.7305739825774228e-06,
+      "loss": 0.2826,
+      "step": 509
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.6969370010232882e-06,
+      "loss": 0.2531,
+      "step": 510
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.663606315666226e-06,
+      "loss": 0.277,
+      "step": 511
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.6305828715217506e-06,
+      "loss": 0.2838,
+      "step": 512
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.597867604894264e-06,
+      "loss": 0.3017,
+      "step": 513
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.5654614433504841e-06,
+      "loss": 0.2695,
+      "step": 514
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.5333653056931684e-06,
+      "loss": 0.3005,
+      "step": 515
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.5015801019350476e-06,
+      "loss": 0.259,
+      "step": 516
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.4701067332730426e-06,
+      "loss": 0.276,
+      "step": 517
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.4389460920626887e-06,
+      "loss": 0.2706,
+      "step": 518
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.4080990617928571e-06,
+      "loss": 0.2808,
+      "step": 519
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.3775665170606896e-06,
+      "loss": 0.2925,
+      "step": 520
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.3473493235468177e-06,
+      "loss": 0.2644,
+      "step": 521
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.3174483379907996e-06,
+      "loss": 0.2484,
+      "step": 522
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.2878644081668403e-06,
+      "loss": 0.3012,
+      "step": 523
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.2585983728597608e-06,
+      "loss": 0.3033,
+      "step": 524
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.2296510618411957e-06,
+      "loss": 0.33,
+      "step": 525
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.201023295846093e-06,
+      "loss": 0.2513,
+      "step": 526
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.1727158865494206e-06,
+      "loss": 0.2871,
+      "step": 527
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.1447296365431668e-06,
+      "loss": 0.2592,
+      "step": 528
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.1170653393135847e-06,
+      "loss": 0.2672,
+      "step": 529
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.0897237792186862e-06,
+      "loss": 0.2589,
+      "step": 530
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.0627057314660114e-06,
+      "loss": 0.2851,
+      "step": 531
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.0360119620906426e-06,
+      "loss": 0.2319,
+      "step": 532
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.0096432279334905e-06,
+      "loss": 0.2757,
+      "step": 533
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 9.836002766198379e-07,
+      "loss": 0.2742,
+      "step": 534
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 9.57883846538135e-07,
+      "loss": 0.324,
+      "step": 535
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 9.324946668190657e-07,
+      "loss": 0.2435,
+      "step": 536
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 9.074334573148783e-07,
+      "loss": 0.2795,
+      "step": 537
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 8.827009285789778e-07,
+      "loss": 0.3012,
+      "step": 538
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 8.582977818457696e-07,
+      "loss": 0.2663,
+      "step": 539
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 8.342247090107919e-07,
+      "loss": 0.2469,
+      "step": 540
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 8.104823926110811e-07,
+      "loss": 0.2835,
+      "step": 541
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 7.870715058058406e-07,
+      "loss": 0.2554,
+      "step": 542
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 7.639927123573351e-07,
+      "loss": 0.2571,
+      "step": 543
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 7.412466666120846e-07,
+      "loss": 0.2679,
+      "step": 544
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 7.188340134823043e-07,
+      "loss": 0.2569,
+      "step": 545
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.967553884276279e-07,
+      "loss": 0.2704,
+      "step": 546
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.750114174370797e-07,
+      "loss": 0.3005,
+      "step": 547
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.536027170113354e-07,
+      "loss": 0.2542,
+      "step": 548
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.32529894145234e-07,
+      "loss": 0.2783,
+      "step": 549
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.117935463105809e-07,
+      "loss": 0.2264,
+      "step": 550
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 5.913942614391931e-07,
+      "loss": 0.2635,
+      "step": 551
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 5.713326179062409e-07,
+      "loss": 0.2658,
+      "step": 552
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 5.516091845138377e-07,
+      "loss": 0.2681,
+      "step": 553
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 5.322245204749319e-07,
+      "loss": 0.3189,
+      "step": 554
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 5.131791753974296e-07,
+      "loss": 0.2983,
+      "step": 555
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.944736892686278e-07,
+      "loss": 0.2887,
+      "step": 556
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.761085924398959e-07,
+      "loss": 0.2594,
+      "step": 557
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.580844056116418e-07,
+      "loss": 0.2366,
+      "step": 558
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.4040163981855095e-07,
+      "loss": 0.3332,
+      "step": 559
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 4.2306079641509094e-07,
+      "loss": 0.2593,
+      "step": 560
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 4.0606236706130367e-07,
+      "loss": 0.2825,
+      "step": 561
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.89406833708858e-07,
+      "loss": 0.2865,
+      "step": 562
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.73094668587394e-07,
+      "loss": 0.3002,
+      "step": 563
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.5712633419112686e-07,
+      "loss": 0.2941,
+      "step": 564
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 3.4150228326573356e-07,
+      "loss": 0.3138,
+      "step": 565
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 3.262229587955232e-07,
+      "loss": 0.3054,
+      "step": 566
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.112887939908715e-07,
+      "loss": 0.2502,
+      "step": 567
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.9670021227593965e-07,
+      "loss": 0.2679,
+      "step": 568
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.824576272766666e-07,
+      "loss": 0.2683,
+      "step": 569
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.6856144280904967e-07,
+      "loss": 0.3101,
+      "step": 570
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.550120528676841e-07,
+      "loss": 0.2749,
+      "step": 571
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.4180984161460004e-07,
+      "loss": 0.2455,
+      "step": 572
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.2895518336836923e-07,
+      "loss": 0.2607,
+      "step": 573
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.164484425934879e-07,
+      "loss": 0.2729,
+      "step": 574
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 2.0428997389004972e-07,
+      "loss": 0.2669,
+      "step": 575
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.9248012198368748e-07,
+      "loss": 0.3026,
+      "step": 576
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.8101922171580022e-07,
+      "loss": 0.2394,
+      "step": 577
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.699075980340581e-07,
+      "loss": 0.2578,
+      "step": 578
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.5914556598319307e-07,
+      "loss": 0.252,
+      "step": 579
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.4873343069606305e-07,
+      "loss": 0.2478,
+      "step": 580
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.3867148738500313e-07,
+      "loss": 0.3517,
+      "step": 581
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.289600213334505e-07,
+      "loss": 0.285,
+      "step": 582
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.195993078878646e-07,
+      "loss": 0.2673,
+      "step": 583
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.1058961244991144e-07,
+      "loss": 0.2644,
+      "step": 584
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.0193119046894295e-07,
+      "loss": 0.2689,
+      "step": 585
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 9.362428743475565e-08,
+      "loss": 0.2699,
+      "step": 586
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 8.566913887062683e-08,
+      "loss": 0.2677,
+      "step": 587
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.806597032663925e-08,
+      "loss": 0.2846,
+      "step": 588
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 7.081499737328634e-08,
+      "loss": 0.2686,
+      "step": 589
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 6.391642559535616e-08,
+      "loss": 0.2542,
+      "step": 590
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.7370450586109737e-08,
+      "loss": 0.2678,
+      "step": 591
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.117725794172995e-08,
+      "loss": 0.237,
+      "step": 592
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 4.533702325605904e-08,
+      "loss": 0.2847,
+      "step": 593
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.9849912115623446e-08,
+      "loss": 0.2397,
+      "step": 594
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 3.471608009493754e-08,
+      "loss": 0.2672,
+      "step": 595
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.9935672752090525e-08,
+      "loss": 0.2767,
+      "step": 596
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 2.5508825624626088e-08,
+      "loss": 0.2758,
+      "step": 597
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 2.1435664225688547e-08,
+      "loss": 0.2576,
+      "step": 598
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.7716304040475697e-08,
+      "loss": 0.3037,
+      "step": 599
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.4350850522956705e-08,
+      "loss": 0.271,
+      "step": 600
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.1339399092885616e-08,
+      "loss": 0.2347,
+      "step": 601
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 8.682035133096566e-09,
+      "loss": 0.2924,
+      "step": 602
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 6.378833987077948e-09,
+      "loss": 0.2847,
+      "step": 603
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 4.429860956842169e-09,
+      "loss": 0.2594,
+      "step": 604
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.8351713010743573e-09,
+      "loss": 0.2613,
+      "step": 605
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.5948102335572313e-09,
+      "loss": 0.2603,
+      "step": 606
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 7.088129218985052e-10,
+      "loss": 0.2915,
+      "step": 607
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.772044865316902e-10,
+      "loss": 0.2903,
+      "step": 608
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.2426,
+      "step": 609
+    },
+    {
+      "epoch": 3.0,
+      "step": 609,
+      "total_flos": 7.120623193701745e+17,
+      "train_loss": 0.6601732866517429,
+      "train_runtime": 5691.3236,
+      "train_samples_per_second": 27.41,
+      "train_steps_per_second": 0.107
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 609,
+  "num_train_epochs": 3,
+  "save_steps": -609,
+  "total_flos": 7.120623193701745e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352d15a68911002e728d452d615d17736a6cb8e85caf8e0aead9183648824d33
+size 5947

training_log.txt

@@ -0,0 +1,689 @@
+[2024-01-10 03:41:18,555] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-01-10 03:41:20,266] [WARNING] [runner.py:203:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only.
+[2024-01-10 03:41:20,266] [INFO] [runner.py:570:main] cmd = /root/anaconda3/envs/dj_comp/bin/python -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbMCwgMSwgMiwgMywgNCwgNSwgNiwgN119 --master_addr=127.0.0.1 --master_port=50000 --enable_each_rank_log=None train.py --model_name_or_path /home/baaidial/models/llama-2-13b-hf/ --tokenizer /home/baaidial/models/llama-2-13b-hf/ --data_path /home/baaidial/fengduanyu/lima_code/code/data/alpaca/alpaca_predata.jsonl --output_dir /home/baaidial/fengduanyu/lima_code/code/model_save/after_sft/alpaca_Llama-2-13b_all/ --per_device_train_batch_size 8 --gradient_accumulation_steps 4 --lang en --bf16 True --gradient_checkpointing_enable True --num_train_epochs 3 --model_max_length 1024 --learning_rate 2.5e-5 --weight_decay 0 --warmup_ratio 0.03 --evaluation_strategy no --save_strategy no --save_steps -1 --save_total_limit 999 --lr_scheduler_type cosine --logging_steps 1 --tf32 True --deepspeed /home/baaidial/fengduanyu/FT-Data-Ranker/competition_kit/lm-training/train_scripts/deepspeed_configs/ds_config_stage3.json
+[2024-01-10 03:41:21,810] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-01-10 03:41:23,124] [INFO] [launch.py:138:main] 0 NCCL_VERSION=2.18.1
+[2024-01-10 03:41:23,124] [INFO] [launch.py:145:main] WORLD INFO DICT: {'localhost': [0, 1, 2, 3, 4, 5, 6, 7]}
+[2024-01-10 03:41:23,124] [INFO] [launch.py:151:main] nnodes=1, num_local_procs=8, node_rank=0
+[2024-01-10 03:41:23,124] [INFO] [launch.py:162:main] global_rank_mapping=defaultdict(<class 'list'>, {'localhost': [0, 1, 2, 3, 4, 5, 6, 7]})
+[2024-01-10 03:41:23,124] [INFO] [launch.py:163:main] dist_world_size=8
+[2024-01-10 03:41:23,124] [INFO] [launch.py:165:main] Setting CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
+[2024-01-10 03:41:25,938] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-01-10 03:41:26,237] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-01-10 03:41:26,239] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-01-10 03:41:26,338] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-01-10 03:41:26,339] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-01-10 03:41:26,351] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-01-10 03:41:26,353] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-01-10 03:41:26,357] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-01-10 03:41:27,429] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-01-10 03:41:27,429] [INFO] [comm.py:668:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
+[2024-01-10 03:41:27,709] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-01-10 03:41:27,773] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-01-10 03:41:27,835] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-01-10 03:41:27,866] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-01-10 03:41:27,867] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-01-10 03:41:27,894] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-01-10 03:41:27,933] [INFO] [comm.py:637:init_distributed] cdb=None
+Loading model from /home/baaidial/models/llama-2-13b-hf/
+[2024-01-10 03:41:30,329] [INFO] [partition_parameters.py:347:__exit__] finished initializing model - num_params = 363, num_elems = 13.02B
+gradient_checkpointing_enable
+Model class: <class 'transformers.models.llama.modeling_llama.LlamaForCausalLM'>
+Tokenizer class: <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>
++---------+---------+------------+---------+------------+---------+------------+---------+------------+----------------+
+|         |pad_token|pad_token_id|bos_token|bos_token_id|eos_token|eos_token_id|unk_token|unk_token_id|model_max_length|
++---------+---------+------------+---------+------------+---------+------------+---------+------------+----------------+
+|tokenizer|  <unk>  |     0      |   <s>   |     1      |   </s>  |     2      |  <unk>  |     0      |      1024      |
++---------+---------+------------+---------+------------+---------+------------+---------+------------+----------------+
+|  model  |    -    |     0      |    -    |     1      |    -    |     2      |    -    |     -      |       -        |
++---------+---------+------------+---------+------------+---------+------------+---------+------------+----------------+
+There are 52002 training samples in data path
+Formatting inputs...
+Tokenizing inputs... This may take some time...
+PROMPT:
+'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nWhen did the Second World War end?\n\n### Response:'
+RESPONSE:
+'The Second World War ended on September 2, 1945 with the official surrender of Japan. The Allies officially declared victory over Germany on May 8, 1945, which is known as V-E Day, or Victory in Europe Day.</s>'
+====================================================================================================
+PROMPT:
+'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nExplain why the following statement is wrong: "Cloud computing stores your data on the Internet."\n\n### Response:'
+RESPONSE:
+'The statement is incorrect because cloud computing does not store data on the Internet. Instead, cloud computing stores data in a remote server which is usually connected to the Internet. Data can be accessed and retrieved from the remote server through the Internet using an application.</s>'
+====================================================================================================
+PROMPT:
+'Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nIdentify 5 major differences between two similar items.\n\n### Input:\nBlackberry and Raspberry\n\n### Response:'
+RESPONSE:
+'1. Blackberries have a rounded shape, while raspberries have a distinct hollow core when picked off the plant.\n2. Raspberries have a rich and intense flavor profile, while blackberries are sweeter and less tart.\n3. Blackberries typically have very tiny seeds that are barely noticeable when eaten, while raspberries have larger, more noticeable seeds.\n4. Blackberries tend to be darker in color than raspberries, which tend to be a pinkish-red.\n5. Raspberries are generally more fragile, and can spoil or bruise more easily than blackberries.</s>'
+====================================================================================================
+PROMPT:
+'Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nClassify the following text as opinion, fact, or non-credible\n\n### Input:\nThis new book is amazing!\n\n### Response:'
+RESPONSE:
+'Opinion.</s>'
+====================================================================================================
+PROMPT:
+'Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nClean the HTML code by removing all the unnecessary tags.\n\n### Input:\n<html><head><title>Website</title></head><body><p>This is a paragraph.</p><p>This is the second paragraph.</p></body></html>\n\n### Response:'
+RESPONSE:
+'<html><head><title>Website</title></head><body>This is a paragraph.<p>This is the second paragraph.</p></body></html></s>'
+====================================================================================================
+ORI NUMBER: 52002, AFTER FILETER: 52000, DROP NUMBER: 2
+Total 52000 samples [ 6.56M tokens] in training!
+Parameter Offload: Total persistent parameters: 414720 in 81 params
+{'loss': 1.3013, 'learning_rate': 1.3157894736842106e-06, 'epoch': 0.0}
+{'loss': 1.2825, 'learning_rate': 2.631578947368421e-06, 'epoch': 0.01}
+{'loss': 1.3755, 'learning_rate': 3.9473684210526315e-06, 'epoch': 0.01}
+{'loss': 1.2644, 'learning_rate': 5.263157894736842e-06, 'epoch': 0.02}
+{'loss': 1.2507, 'learning_rate': 6.578947368421053e-06, 'epoch': 0.02}
+{'loss': 1.1368, 'learning_rate': 7.894736842105263e-06, 'epoch': 0.03}
+{'loss': 1.1033, 'learning_rate': 9.210526315789474e-06, 'epoch': 0.03}
+{'loss': 1.0729, 'learning_rate': 1.0526315789473684e-05, 'epoch': 0.04}
+{'loss': 1.0756, 'learning_rate': 1.1842105263157895e-05, 'epoch': 0.04}
+{'loss': 1.0396, 'learning_rate': 1.3157894736842106e-05, 'epoch': 0.05}
+{'loss': 1.0539, 'learning_rate': 1.4473684210526317e-05, 'epoch': 0.05}
+{'loss': 1.085, 'learning_rate': 1.5789473684210526e-05, 'epoch': 0.06}
+{'loss': 1.0104, 'learning_rate': 1.7105263157894737e-05, 'epoch': 0.06}
+{'loss': 1.0773, 'learning_rate': 1.8421052631578947e-05, 'epoch': 0.07}
+{'loss': 1.0052, 'learning_rate': 1.9736842105263158e-05, 'epoch': 0.07}
+{'loss': 1.0603, 'learning_rate': 2.105263157894737e-05, 'epoch': 0.08}
+{'loss': 1.0628, 'learning_rate': 2.236842105263158e-05, 'epoch': 0.08}
+{'loss': 1.0233, 'learning_rate': 2.368421052631579e-05, 'epoch': 0.09}
+{'loss': 1.0953, 'learning_rate': 2.5e-05, 'epoch': 0.09}
+{'loss': 1.0786, 'learning_rate': 2.499982279551347e-05, 'epoch': 0.1}
+{'loss': 1.0389, 'learning_rate': 2.4999291187078104e-05, 'epoch': 0.1}
+{'loss': 1.0168, 'learning_rate': 2.4998405189766444e-05, 'epoch': 0.11}
+{'loss': 1.036, 'learning_rate': 2.4997164828698926e-05, 'epoch': 0.11}
+{'loss': 1.0171, 'learning_rate': 2.4995570139043158e-05, 'epoch': 0.12}
+{'loss': 1.0811, 'learning_rate': 2.4993621166012923e-05, 'epoch': 0.12}
+{'loss': 1.0955, 'learning_rate': 2.4991317964866905e-05, 'epoch': 0.13}
+{'loss': 1.0038, 'learning_rate': 2.4988660600907115e-05, 'epoch': 0.13}
+{'loss': 1.0558, 'learning_rate': 2.4985649149477043e-05, 'epoch': 0.14}
+{'loss': 1.0707, 'learning_rate': 2.4982283695959525e-05, 'epoch': 0.14}
+{'loss': 1.1162, 'learning_rate': 2.4978564335774313e-05, 'epoch': 0.15}
+{'loss': 1.006, 'learning_rate': 2.4974491174375374e-05, 'epoch': 0.15}
+{'loss': 1.0481, 'learning_rate': 2.497006432724791e-05, 'epoch': 0.16}
+{'loss': 1.0609, 'learning_rate': 2.4965283919905065e-05, 'epoch': 0.16}
+{'loss': 1.0946, 'learning_rate': 2.4960150087884376e-05, 'epoch': 0.17}
+{'loss': 1.0222, 'learning_rate': 2.4954662976743944e-05, 'epoch': 0.17}
+{'loss': 1.0427, 'learning_rate': 2.494882274205827e-05, 'epoch': 0.18}
+{'loss': 1.0987, 'learning_rate': 2.4942629549413894e-05, 'epoch': 0.18}
+{'loss': 1.1212, 'learning_rate': 2.4936083574404646e-05, 'epoch': 0.19}
+{'loss': 1.0986, 'learning_rate': 2.4929185002626714e-05, 'epoch': 0.19}
+{'loss': 1.05, 'learning_rate': 2.492193402967336e-05, 'epoch': 0.2}
+{'loss': 1.0784, 'learning_rate': 2.4914330861129376e-05, 'epoch': 0.2}
+{'loss': 1.0997, 'learning_rate': 2.4906375712565245e-05, 'epoch': 0.21}
+{'loss': 1.0774, 'learning_rate': 2.489806880953106e-05, 'epoch': 0.21}
+{'loss': 1.0832, 'learning_rate': 2.4889410387550093e-05, 'epoch': 0.22}
+{'loss': 1.0649, 'learning_rate': 2.488040069211214e-05, 'epoch': 0.22}
+{'loss': 1.0684, 'learning_rate': 2.487103997866655e-05, 'epoch': 0.23}
+{'loss': 1.0857, 'learning_rate': 2.4861328512615e-05, 'epoch': 0.23}
+{'loss': 1.0896, 'learning_rate': 2.485126656930394e-05, 'epoch': 0.24}
+{'loss': 1.0719, 'learning_rate': 2.4840854434016808e-05, 'epoch': 0.24}
+{'loss': 1.0917, 'learning_rate': 2.4830092401965942e-05, 'epoch': 0.25}
+{'loss': 1.0893, 'learning_rate': 2.4818980778284202e-05, 'epoch': 0.25}
+{'loss': 1.0136, 'learning_rate': 2.4807519878016313e-05, 'epoch': 0.26}
+{'loss': 1.0472, 'learning_rate': 2.4795710026109954e-05, 'epoch': 0.26}
+{'loss': 1.0625, 'learning_rate': 2.4783551557406515e-05, 'epoch': 0.27}
+{'loss': 1.1197, 'learning_rate': 2.4771044816631635e-05, 'epoch': 0.27}
+{'loss': 1.0531, 'learning_rate': 2.4758190158385402e-05, 'epoch': 0.28}
+{'loss': 1.0767, 'learning_rate': 2.4744987947132318e-05, 'epoch': 0.28}
+{'loss': 1.0852, 'learning_rate': 2.473143855719095e-05, 'epoch': 0.29}
+{'loss': 1.093, 'learning_rate': 2.4717542372723333e-05, 'epoch': 0.29}
+{'loss': 1.0991, 'learning_rate': 2.4703299787724065e-05, 'epoch': 0.3}
+{'loss': 1.0982, 'learning_rate': 2.468871120600913e-05, 'epoch': 0.3}
+{'loss': 1.1232, 'learning_rate': 2.4673777041204478e-05, 'epoch': 0.31}
+{'loss': 1.0692, 'learning_rate': 2.465849771673427e-05, 'epoch': 0.31}
+{'loss': 1.1136, 'learning_rate': 2.4642873665808873e-05, 'epoch': 0.31}
+{'loss': 1.0771, 'learning_rate': 2.4626905331412608e-05, 'epoch': 0.32}
+{'loss': 1.0464, 'learning_rate': 2.4610593166291143e-05, 'epoch': 0.32}
+{'loss': 1.0578, 'learning_rate': 2.4593937632938695e-05, 'epoch': 0.33}
+{'loss': 1.0322, 'learning_rate': 2.457693920358491e-05, 'epoch': 0.33}
+{'loss': 1.0573, 'learning_rate': 2.455959836018145e-05, 'epoch': 0.34}
+{'loss': 1.083, 'learning_rate': 2.454191559438836e-05, 'epoch': 0.34}
+{'loss': 1.0426, 'learning_rate': 2.4523891407560107e-05, 'epoch': 0.35}
+{'loss': 1.0706, 'learning_rate': 2.4505526310731376e-05, 'epoch': 0.35}
+{'loss': 1.089, 'learning_rate': 2.448682082460257e-05, 'epoch': 0.36}
+{'loss': 1.0918, 'learning_rate': 2.446777547952507e-05, 'epoch': 0.36}
+{'loss': 1.0869, 'learning_rate': 2.4448390815486165e-05, 'epoch': 0.37}
+{'loss': 1.0751, 'learning_rate': 2.4428667382093762e-05, 'epoch': 0.37}
+{'loss': 1.0684, 'learning_rate': 2.440860573856081e-05, 'epoch': 0.38}
+{'loss': 1.0704, 'learning_rate': 2.438820645368942e-05, 'epoch': 0.38}
+{'loss': 1.0671, 'learning_rate': 2.4367470105854766e-05, 'epoch': 0.39}
+{'loss': 1.0434, 'learning_rate': 2.4346397282988666e-05, 'epoch': 0.39}
+{'loss': 1.0605, 'learning_rate': 2.432498858256292e-05, 'epoch': 0.4}
+{'loss': 1.0536, 'learning_rate': 2.4303244611572372e-05, 'epoch': 0.4}
+{'loss': 1.0807, 'learning_rate': 2.4281165986517696e-05, 'epoch': 0.41}
+{'loss': 1.0605, 'learning_rate': 2.425875333338792e-05, 'epoch': 0.41}
+{'loss': 1.056, 'learning_rate': 2.4236007287642664e-05, 'epoch': 0.42}
+{'loss': 1.0294, 'learning_rate': 2.421292849419416e-05, 'epoch': 0.42}
+{'loss': 1.0571, 'learning_rate': 2.4189517607388918e-05, 'epoch': 0.43}
+{'loss': 1.1025, 'learning_rate': 2.416577529098921e-05, 'epoch': 0.43}
+{'loss': 1.1459, 'learning_rate': 2.4141702218154232e-05, 'epoch': 0.44}
+{'loss': 1.0755, 'learning_rate': 2.4117299071421023e-05, 'epoch': 0.44}
+{'loss': 1.0686, 'learning_rate': 2.4092566542685123e-05, 'epoch': 0.45}
+{'loss': 1.0586, 'learning_rate': 2.4067505333180938e-05, 'epoch': 0.45}
+{'loss': 1.1033, 'learning_rate': 2.404211615346187e-05, 'epoch': 0.46}
+{'loss': 1.0253, 'learning_rate': 2.401639972338016e-05, 'epoch': 0.46}
+{'loss': 1.0888, 'learning_rate': 2.399035677206651e-05, 'epoch': 0.47}
+{'loss': 1.0677, 'learning_rate': 2.396398803790936e-05, 'epoch': 0.47}
+{'loss': 1.0582, 'learning_rate': 2.393729426853399e-05, 'epoch': 0.48}
+{'loss': 1.0223, 'learning_rate': 2.3910276220781314e-05, 'epoch': 0.48}
+{'loss': 1.0885, 'learning_rate': 2.3882934660686418e-05, 'epoch': 0.49}
+{'loss': 1.0553, 'learning_rate': 2.3855270363456833e-05, 'epoch': 0.49}
+{'loss': 1.1293, 'learning_rate': 2.382728411345058e-05, 'epoch': 0.5}
+{'loss': 1.1106, 'learning_rate': 2.3798976704153906e-05, 'epoch': 0.5}
+{'loss': 1.0647, 'learning_rate': 2.3770348938158805e-05, 'epoch': 0.51}
+{'loss': 1.078, 'learning_rate': 2.3741401627140242e-05, 'epoch': 0.51}
+{'loss': 1.0344, 'learning_rate': 2.371213559183316e-05, 'epoch': 0.52}
+{'loss': 1.095, 'learning_rate': 2.3682551662009203e-05, 'epoch': 0.52}
+{'loss': 1.0794, 'learning_rate': 2.3652650676453188e-05, 'epoch': 0.53}
+{'loss': 0.9938, 'learning_rate': 2.362243348293931e-05, 'epoch': 0.53}
+{'loss': 1.1374, 'learning_rate': 2.3591900938207147e-05, 'epoch': 0.54}
+{'loss': 1.0443, 'learning_rate': 2.3561053907937315e-05, 'epoch': 0.54}
+{'loss': 1.0452, 'learning_rate': 2.352989326672696e-05, 'epoch': 0.55}
+{'loss': 1.0359, 'learning_rate': 2.349841989806495e-05, 'epoch': 0.55}
+{'loss': 1.0973, 'learning_rate': 2.346663469430683e-05, 'epoch': 0.56}
+{'loss': 1.138, 'learning_rate': 2.3434538556649515e-05, 'epoch': 0.56}
+{'loss': 1.0806, 'learning_rate': 2.3402132395105737e-05, 'epoch': 0.57}
+{'loss': 1.1112, 'learning_rate': 2.336941712847825e-05, 'epoch': 0.57}
+{'loss': 1.0837, 'learning_rate': 2.3336393684333778e-05, 'epoch': 0.58}
+{'loss': 1.0794, 'learning_rate': 2.3303062998976712e-05, 'epoch': 0.58}
+{'loss': 1.0757, 'learning_rate': 2.3269426017422576e-05, 'epoch': 0.59}
+{'loss': 0.9923, 'learning_rate': 2.3235483693371214e-05, 'epoch': 0.59}
+{'loss': 1.0442, 'learning_rate': 2.3201236989179766e-05, 'epoch': 0.6}
+{'loss': 1.0608, 'learning_rate': 2.3166686875835365e-05, 'epoch': 0.6}
+{'loss': 1.0806, 'learning_rate': 2.313183433292764e-05, 'epoch': 0.61}
+{'loss': 1.0728, 'learning_rate': 2.3096680348620886e-05, 'epoch': 0.61}
+{'loss': 1.0979, 'learning_rate': 2.3061225919626124e-05, 'epoch': 0.62}
+{'loss': 1.0827, 'learning_rate': 2.3025472051172755e-05, 'epoch': 0.62}
+{'loss': 1.0715, 'learning_rate': 2.2989419756980134e-05, 'epoch': 0.62}
+{'loss': 1.0668, 'learning_rate': 2.295307005922879e-05, 'epoch': 0.63}
+{'loss': 1.0726, 'learning_rate': 2.2916423988531437e-05, 'epoch': 0.63}
+{'loss': 1.1038, 'learning_rate': 2.2879482583903783e-05, 'epoch': 0.64}
+{'loss': 1.0698, 'learning_rate': 2.2842246892735053e-05, 'epoch': 0.64}
+{'loss': 1.0782, 'learning_rate': 2.2804717970758286e-05, 'epoch': 0.65}
+{'loss': 1.0834, 'learning_rate': 2.2766896882020422e-05, 'epoch': 0.65}
+{'loss': 1.0536, 'learning_rate': 2.2728784698852114e-05, 'epoch': 0.66}
+{'loss': 1.0867, 'learning_rate': 2.2690382501837344e-05, 'epoch': 0.66}
+{'loss': 1.0369, 'learning_rate': 2.2651691379782764e-05, 'epoch': 0.67}
+{'loss': 1.0474, 'learning_rate': 2.2612712429686845e-05, 'epoch': 0.67}
+{'loss': 1.129, 'learning_rate': 2.2573446756708754e-05, 'epoch': 0.68}
+{'loss': 1.0561, 'learning_rate': 2.2533895474137047e-05, 'epoch': 0.68}
+{'loss': 1.1228, 'learning_rate': 2.2494059703358073e-05, 'epoch': 0.69}
+{'loss': 1.1673, 'learning_rate': 2.24539405738242e-05, 'epoch': 0.69}
+{'loss': 1.0184, 'learning_rate': 2.2413539223021794e-05, 'epoch': 0.7}
+{'loss': 1.0699, 'learning_rate': 2.237285679643895e-05, 'epoch': 0.7}
+{'loss': 1.0924, 'learning_rate': 2.2331894447533035e-05, 'epoch': 0.71}
+{'loss': 1.0106, 'learning_rate': 2.229065333769796e-05, 'epoch': 0.71}
+{'loss': 1.0525, 'learning_rate': 2.2249134636231285e-05, 'epoch': 0.72}
+{'loss': 1.1001, 'learning_rate': 2.2207339520301033e-05, 'epoch': 0.72}
+{'loss': 1.0832, 'learning_rate': 2.216526917491234e-05, 'epoch': 0.73}
+{'loss': 0.9838, 'learning_rate': 2.2122924792873827e-05, 'epoch': 0.73}
+{'loss': 1.0705, 'learning_rate': 2.2080307574763824e-05, 'epoch': 0.74}
+{'loss': 1.1082, 'learning_rate': 2.2037418728896282e-05, 'epoch': 0.74}
+{'loss': 1.0794, 'learning_rate': 2.1994259471286545e-05, 'epoch': 0.75}
+{'loss': 1.0738, 'learning_rate': 2.1950831025616873e-05, 'epoch': 0.75}
+{'loss': 1.0687, 'learning_rate': 2.190713462320173e-05, 'epoch': 0.76}
+{'loss': 0.9987, 'learning_rate': 2.186317150295289e-05, 'epoch': 0.76}
+{'loss': 1.0749, 'learning_rate': 2.1818942911344283e-05, 'epoch': 0.77}
+{'loss': 1.053, 'learning_rate': 2.17744501023767e-05, 'epoch': 0.77}
+{'loss': 1.0967, 'learning_rate': 2.1729694337542196e-05, 'epoch': 0.78}
+{'loss': 1.1154, 'learning_rate': 2.168467688578834e-05, 'epoch': 0.78}
+{'loss': 1.0552, 'learning_rate': 2.163939902348225e-05, 'epoch': 0.79}
+{'loss': 1.0798, 'learning_rate': 2.1593862034374365e-05, 'epoch': 0.79}
+{'loss': 1.073, 'learning_rate': 2.15480672095621e-05, 'epoch': 0.8}
+{'loss': 1.0787, 'learning_rate': 2.15020158474532e-05, 'epoch': 0.8}
+{'loss': 1.034, 'learning_rate': 2.145570925372894e-05, 'epoch': 0.81}
+{'loss': 1.0699, 'learning_rate': 2.1409148741307107e-05, 'epoch': 0.81}
+{'loss': 0.9939, 'learning_rate': 2.1362335630304768e-05, 'epoch': 0.82}
+{'loss': 1.0616, 'learning_rate': 2.131527124800086e-05, 'epoch': 0.82}
+{'loss': 0.992, 'learning_rate': 2.1267956928798525e-05, 'epoch': 0.83}
+{'loss': 1.0463, 'learning_rate': 2.1220394014187312e-05, 'epoch': 0.83}
+{'loss': 1.071, 'learning_rate': 2.1172583852705115e-05, 'epoch': 0.84}
+{'loss': 1.0274, 'learning_rate': 2.1124527799899953e-05, 'epoch': 0.84}
+{'loss': 1.0593, 'learning_rate': 2.1076227218291535e-05, 'epoch': 0.85}
+{'loss': 1.0286, 'learning_rate': 2.1027683477332623e-05, 'epoch': 0.85}
+{'loss': 1.0657, 'learning_rate': 2.0978897953370204e-05, 'epoch': 0.86}
+{'loss': 1.0616, 'learning_rate': 2.0929872029606472e-05, 'epoch': 0.86}
+{'loss': 1.0425, 'learning_rate': 2.088060709605962e-05, 'epoch': 0.87}
+{'loss': 1.0024, 'learning_rate': 2.08311045495244e-05, 'epoch': 0.87}
+{'loss': 1.0252, 'learning_rate': 2.078136579353255e-05, 'epoch': 0.88}
+{'loss': 1.0623, 'learning_rate': 2.0731392238312985e-05, 'epoch': 0.88}
+{'loss': 1.0712, 'learning_rate': 2.0681185300751814e-05, 'epoch': 0.89}
+{'loss': 1.0976, 'learning_rate': 2.0630746404352168e-05, 'epoch': 0.89}
+{'loss': 1.0481, 'learning_rate': 2.058007697919386e-05, 'epoch': 0.9}
+{'loss': 1.0502, 'learning_rate': 2.0529178461892785e-05, 'epoch': 0.9}
+{'loss': 1.0707, 'learning_rate': 2.0478052295560253e-05, 'epoch': 0.91}
+{'loss': 1.0669, 'learning_rate': 2.0426699929762035e-05, 'epoch': 0.91}
+{'loss': 1.0067, 'learning_rate': 2.037512282047726e-05, 'epoch': 0.92}
+{'loss': 1.1202, 'learning_rate': 2.0323322430057166e-05, 'epoch': 0.92}
+{'loss': 1.074, 'learning_rate': 2.0271300227183598e-05, 'epoch': 0.92}
+{'loss': 1.0394, 'learning_rate': 2.02190576868274e-05, 'epoch': 0.93}
+{'loss': 1.0368, 'learning_rate': 2.016659629020658e-05, 'epoch': 0.93}
+{'loss': 1.0733, 'learning_rate': 2.0113917524744308e-05, 'epoch': 0.94}
+{'loss': 1.0594, 'learning_rate': 2.0061022884026762e-05, 'epoch': 0.94}
+{'loss': 1.0401, 'learning_rate': 2.0007913867760763e-05, 'epoch': 0.95}
+{'loss': 1.0903, 'learning_rate': 1.995459198173127e-05, 'epoch': 0.95}
+{'loss': 1.1046, 'learning_rate': 1.9901058737758667e-05, 'epoch': 0.96}
+{'loss': 1.0478, 'learning_rate': 1.9847315653655915e-05, 'epoch': 0.96}
+{'loss': 1.0747, 'learning_rate': 1.9793364253185518e-05, 'epoch': 0.97}
+{'loss': 1.0484, 'learning_rate': 1.9739206066016307e-05, 'epoch': 0.97}
+{'loss': 1.0897, 'learning_rate': 1.9684842627680088e-05, 'epoch': 0.98}
+{'loss': 1.0715, 'learning_rate': 1.963027547952808e-05, 'epoch': 0.98}
+{'loss': 1.0671, 'learning_rate': 1.9575506168687247e-05, 'epoch': 0.99}
+{'loss': 0.9719, 'learning_rate': 1.9520536248016403e-05, 'epoch': 0.99}
+{'loss': 1.0384, 'learning_rate': 1.946536727606219e-05, 'epoch': 1.0}
+{'loss': 0.7968, 'learning_rate': 1.941000081701492e-05, 'epoch': 1.0}
+{'loss': 0.6873, 'learning_rate': 1.9354438440664167e-05, 'epoch': 1.01}
+{'loss': 0.6435, 'learning_rate': 1.929868172235433e-05, 'epoch': 1.01}
+{'loss': 0.6083, 'learning_rate': 1.9242732242939893e-05, 'epoch': 1.02}
+{'loss': 0.6499, 'learning_rate': 1.9186591588740667e-05, 'epoch': 1.02}
+{'loss': 0.6342, 'learning_rate': 1.913026135149678e-05, 'epoch': 1.03}
+{'loss': 0.6186, 'learning_rate': 1.9073743128323558e-05, 'epoch': 1.03}
+{'loss': 0.6751, 'learning_rate': 1.9017038521666232e-05, 'epoch': 1.04}
+{'loss': 0.6175, 'learning_rate': 1.8960149139254513e-05, 'epoch': 1.04}
+{'loss': 0.5863, 'learning_rate': 1.8903076594057013e-05, 'epoch': 1.05}
+{'loss': 0.6271, 'learning_rate': 1.88458225042355e-05, 'epoch': 1.05}
+{'loss': 0.6416, 'learning_rate': 1.8788388493099033e-05, 'epoch': 1.06}
+{'loss': 0.653, 'learning_rate': 1.8730776189057918e-05, 'epoch': 1.06}
+{'loss': 0.6631, 'learning_rate': 1.8672987225577552e-05, 'epoch': 1.07}
+{'loss': 0.6022, 'learning_rate': 1.8615023241132127e-05, 'epoch': 1.07}
+{'loss': 0.645, 'learning_rate': 1.855688587915813e-05, 'epoch': 1.08}
+{'loss': 0.6546, 'learning_rate': 1.8498576788007775e-05, 'epoch': 1.08}
+{'loss': 0.6453, 'learning_rate': 1.8440097620902284e-05, 'epoch': 1.09}
+{'loss': 0.6509, 'learning_rate': 1.838145003588497e-05, 'epoch': 1.09}
+{'loss': 0.5689, 'learning_rate': 1.832263569577427e-05, 'epoch': 1.1}
+{'loss': 0.5919, 'learning_rate': 1.8263656268116576e-05, 'epoch': 1.1}
+{'loss': 0.6308, 'learning_rate': 1.8204513425138952e-05, 'epoch': 1.11}
+{'loss': 0.6666, 'learning_rate': 1.8145208843701742e-05, 'epoch': 1.11}
+{'loss': 0.584, 'learning_rate': 1.808574420525101e-05, 'epoch': 1.12}
+{'loss': 0.5634, 'learning_rate': 1.8026121195770874e-05, 'epoch': 1.12}
+{'loss': 0.5975, 'learning_rate': 1.7966341505735695e-05, 'epoch': 1.13}
+{'loss': 0.6015, 'learning_rate': 1.7906406830062156e-05, 'epoch': 1.13}
+{'loss': 0.5879, 'learning_rate': 1.7846318868061212e-05, 'epoch': 1.14}
+{'loss': 0.6187, 'learning_rate': 1.7786079323389893e-05, 'epoch': 1.14}
+{'loss': 0.617, 'learning_rate': 1.7725689904003006e-05, 'epoch': 1.15}
+{'loss': 0.6135, 'learning_rate': 1.766515232210473e-05, 'epoch': 1.15}
+{'loss': 0.6676, 'learning_rate': 1.7604468294100034e-05, 'epoch': 1.16}
+{'loss': 0.6294, 'learning_rate': 1.754363954054605e-05, 'epoch': 1.16}
+{'loss': 0.6308, 'learning_rate': 1.7482667786103256e-05, 'epoch': 1.17}
+{'loss': 0.5851, 'learning_rate': 1.7421554759486614e-05, 'epoch': 1.17}
+{'loss': 0.6303, 'learning_rate': 1.736030219341651e-05, 'epoch': 1.18}
+{'loss': 0.6124, 'learning_rate': 1.7298911824569676e-05, 'epoch': 1.18}
+{'loss': 0.6291, 'learning_rate': 1.7237385393529916e-05, 'epoch': 1.19}
+{'loss': 0.6457, 'learning_rate': 1.7175724644738773e-05, 'epoch': 1.19}
+{'loss': 0.6475, 'learning_rate': 1.7113931326446054e-05, 'epoch': 1.2}
+{'loss': 0.6723, 'learning_rate': 1.705200719066028e-05, 'epoch': 1.2}
+{'loss': 0.6456, 'learning_rate': 1.6989953993098998e-05, 'epoch': 1.21}
+{'loss': 0.613, 'learning_rate': 1.6927773493139014e-05, 'epoch': 1.21}
+{'loss': 0.6202, 'learning_rate': 1.68654674537665e-05, 'epoch': 1.22}
+{'loss': 0.5821, 'learning_rate': 1.6803037641527002e-05, 'epoch': 1.22}
+{'loss': 0.6698, 'learning_rate': 1.674048582647538e-05, 'epoch': 1.23}
+{'loss': 0.6762, 'learning_rate': 1.6677813782125592e-05, 'epoch': 1.23}
+{'loss': 0.6087, 'learning_rate': 1.6615023285400432e-05, 'epoch': 1.23}
+{'loss': 0.6154, 'learning_rate': 1.6552116116581133e-05, 'epoch': 1.24}
+{'loss': 0.6162, 'learning_rate': 1.648909405925691e-05, 'epoch': 1.24}
+{'loss': 0.624, 'learning_rate': 1.6425958900274362e-05, 'epoch': 1.25}
+{'loss': 0.5986, 'learning_rate': 1.6362712429686846e-05, 'epoch': 1.25}
+{'loss': 0.6152, 'learning_rate': 1.629935644070369e-05, 'epoch': 1.26}
+{'loss': 0.6114, 'learning_rate': 1.6235892729639378e-05, 'epoch': 1.26}
+{'loss': 0.603, 'learning_rate': 1.617232309586261e-05, 'epoch': 1.27}
+{'loss': 0.6791, 'learning_rate': 1.6108649341745262e-05, 'epoch': 1.27}
+{'loss': 0.6662, 'learning_rate': 1.604487327261133e-05, 'epoch': 1.28}
+{'loss': 0.6407, 'learning_rate': 1.59809966966857e-05, 'epoch': 1.28}
+{'loss': 0.629, 'learning_rate': 1.591702142504291e-05, 'epoch': 1.29}
+{'loss': 0.6191, 'learning_rate': 1.5852949271555787e-05, 'epoch': 1.29}
+{'loss': 0.6332, 'learning_rate': 1.5788782052844015e-05, 'epoch': 1.3}
+{'loss': 0.642, 'learning_rate': 1.572452158822265e-05, 'epoch': 1.3}
+{'loss': 0.6257, 'learning_rate': 1.5660169699650503e-05, 'epoch': 1.31}
+{'loss': 0.6622, 'learning_rate': 1.5595728211678525e-05, 'epoch': 1.31}
+{'loss': 0.6221, 'learning_rate': 1.553119895139803e-05, 'epoch': 1.32}
+{'loss': 0.641, 'learning_rate': 1.546658374838894e-05, 'epoch': 1.32}
+{'loss': 0.6199, 'learning_rate': 1.5401884434667864e-05, 'epoch': 1.33}
+{'loss': 0.6204, 'learning_rate': 1.5337102844636188e-05, 'epoch': 1.33}
+{'loss': 0.6315, 'learning_rate': 1.5272240815028067e-05, 'epoch': 1.34}
+{'loss': 0.6727, 'learning_rate': 1.520730018485832e-05, 'epoch': 1.34}
+{'loss': 0.6628, 'learning_rate': 1.5142282795370305e-05, 'epoch': 1.35}
+{'loss': 0.6742, 'learning_rate': 1.5077190489983728e-05, 'epoch': 1.35}
+{'loss': 0.6381, 'learning_rate': 1.5012025114242355e-05, 'epoch': 1.36}
+{'loss': 0.6467, 'learning_rate': 1.49467885157617e-05, 'epoch': 1.36}
+{'loss': 0.6497, 'learning_rate': 1.4881482544176627e-05, 'epoch': 1.37}
+{'loss': 0.6165, 'learning_rate': 1.4816109051088931e-05, 'epoch': 1.37}
+{'loss': 0.6183, 'learning_rate': 1.4750669890014807e-05, 'epoch': 1.38}
+{'loss': 0.6557, 'learning_rate': 1.468516691633233e-05, 'epoch': 1.38}
+{'loss': 0.6581, 'learning_rate': 1.4619601987228832e-05, 'epoch': 1.39}
+{'loss': 0.6562, 'learning_rate': 1.4553976961648244e-05, 'epoch': 1.39}
+{'loss': 0.6587, 'learning_rate': 1.4488293700238401e-05, 'epoch': 1.4}
+{'loss': 0.6124, 'learning_rate': 1.4422554065298286e-05, 'epoch': 1.4}
+{'loss': 0.6168, 'learning_rate': 1.435675992072521e-05, 'epoch': 1.41}
+{'loss': 0.6346, 'learning_rate': 1.4290913131961997e-05, 'epoch': 1.41}
+{'loss': 0.6851, 'learning_rate': 1.4225015565944072e-05, 'epoch': 1.42}
+{'loss': 0.652, 'learning_rate': 1.4159069091046526e-05, 'epoch': 1.42}
+{'loss': 0.6331, 'learning_rate': 1.4093075577031157e-05, 'epoch': 1.43}
+{'loss': 0.6402, 'learning_rate': 1.4027036894993442e-05, 'epoch': 1.43}
+{'loss': 0.6072, 'learning_rate': 1.396095491730951e-05, 'epoch': 1.44}
+{'loss': 0.6314, 'learning_rate': 1.3894831517583017e-05, 'epoch': 1.44}
+{'loss': 0.5981, 'learning_rate': 1.3828668570592069e-05, 'epoch': 1.45}
+{'loss': 0.6045, 'learning_rate': 1.3762467952236027e-05, 'epoch': 1.45}
+{'loss': 0.6773, 'learning_rate': 1.369623153948235e-05, 'epoch': 1.46}
+{'loss': 0.6185, 'learning_rate': 1.3629961210313353e-05, 'epoch': 1.46}
+{'loss': 0.6684, 'learning_rate': 1.3563658843672985e-05, 'epoch': 1.47}
+{'loss': 0.5952, 'learning_rate': 1.3497326319413539e-05, 'epoch': 1.47}
+{'loss': 0.6146, 'learning_rate': 1.3430965518242362e-05, 'epoch': 1.48}
+{'loss': 0.6532, 'learning_rate': 1.336457832166852e-05, 'epoch': 1.48}
+{'loss': 0.6521, 'learning_rate': 1.3298166611949467e-05, 'epoch': 1.49}
+{'loss': 0.6157, 'learning_rate': 1.3231732272037672e-05, 'epoch': 1.49}
+{'loss': 0.6474, 'learning_rate': 1.3165277185527234e-05, 'epoch': 1.5}
+{'loss': 0.5977, 'learning_rate': 1.3098803236600462e-05, 'epoch': 1.5}
+{'loss': 0.624, 'learning_rate': 1.3032312309974482e-05, 'epoch': 1.51}
+{'loss': 0.6255, 'learning_rate': 1.2965806290847768e-05, 'epoch': 1.51}
+{'loss': 0.6181, 'learning_rate': 1.2899287064846725e-05, 'epoch': 1.52}
+{'loss': 0.6159, 'learning_rate': 1.2832756517972185e-05, 'epoch': 1.52}
+{'loss': 0.6414, 'learning_rate': 1.2766216536545984e-05, 'epoch': 1.53}
+{'loss': 0.5773, 'learning_rate': 1.2699669007157435e-05, 'epoch': 1.53}
+{'loss': 0.627, 'learning_rate': 1.2633115816609867e-05, 'epoch': 1.54}
+{'loss': 0.5812, 'learning_rate': 1.2566558851867106e-05, 'epoch': 1.54}
+{'loss': 0.6219, 'learning_rate': 1.25e-05, 'epoch': 1.54}
+{'loss': 0.6287, 'learning_rate': 1.2433441148132897e-05, 'epoch': 1.55}
+{'loss': 0.5863, 'learning_rate': 1.236688418339014e-05, 'epoch': 1.55}
+{'loss': 0.5904, 'learning_rate': 1.2300330992842566e-05, 'epoch': 1.56}
+{'loss': 0.6398, 'learning_rate': 1.223378346345402e-05, 'epoch': 1.56}
+{'loss': 0.6025, 'learning_rate': 1.2167243482027816e-05, 'epoch': 1.57}
+{'loss': 0.6047, 'learning_rate': 1.2100712935153283e-05, 'epoch': 1.57}
+{'loss': 0.6134, 'learning_rate': 1.2034193709152231e-05, 'epoch': 1.58}
+{'loss': 0.6624, 'learning_rate': 1.196768769002552e-05, 'epoch': 1.58}
+{'loss': 0.6065, 'learning_rate': 1.190119676339954e-05, 'epoch': 1.59}
+{'loss': 0.6245, 'learning_rate': 1.1834722814472771e-05, 'epoch': 1.59}
+{'loss': 0.6223, 'learning_rate': 1.1768267727962328e-05, 'epoch': 1.6}
+{'loss': 0.638, 'learning_rate': 1.1701833388050536e-05, 'epoch': 1.6}
+{'loss': 0.6685, 'learning_rate': 1.1635421678331485e-05, 'epoch': 1.61}
+{'loss': 0.6236, 'learning_rate': 1.1569034481757644e-05, 'epoch': 1.61}
+{'loss': 0.6174, 'learning_rate': 1.150267368058646e-05, 'epoch': 1.62}
+{'loss': 0.6431, 'learning_rate': 1.1436341156327016e-05, 'epoch': 1.62}
+{'loss': 0.6326, 'learning_rate': 1.137003878968665e-05, 'epoch': 1.63}
+{'loss': 0.6585, 'learning_rate': 1.1303768460517657e-05, 'epoch': 1.63}
+{'loss': 0.653, 'learning_rate': 1.1237532047763974e-05, 'epoch': 1.64}
+{'loss': 0.6169, 'learning_rate': 1.1171331429407934e-05, 'epoch': 1.64}
+{'loss': 0.5823, 'learning_rate': 1.1105168482416984e-05, 'epoch': 1.65}
+{'loss': 0.6307, 'learning_rate': 1.1039045082690496e-05, 'epoch': 1.65}
+{'loss': 0.6119, 'learning_rate': 1.0972963105006556e-05, 'epoch': 1.66}
+{'loss': 0.6236, 'learning_rate': 1.0906924422968846e-05, 'epoch': 1.66}
+{'loss': 0.5794, 'learning_rate': 1.0840930908953477e-05, 'epoch': 1.67}
+{'loss': 0.6227, 'learning_rate': 1.0774984434055932e-05, 'epoch': 1.67}
+{'loss': 0.6367, 'learning_rate': 1.0709086868038005e-05, 'epoch': 1.68}
+{'loss': 0.6325, 'learning_rate': 1.064324007927479e-05, 'epoch': 1.68}
+{'loss': 0.6073, 'learning_rate': 1.0577445934701717e-05, 'epoch': 1.69}
+{'loss': 0.6616, 'learning_rate': 1.0511706299761602e-05, 'epoch': 1.69}
+{'loss': 0.6514, 'learning_rate': 1.044602303835176e-05, 'epoch': 1.7}
+{'loss': 0.6421, 'learning_rate': 1.0380398012771169e-05, 'epoch': 1.7}
+{'loss': 0.6286, 'learning_rate': 1.0314833083667672e-05, 'epoch': 1.71}
+{'loss': 0.6372, 'learning_rate': 1.0249330109985198e-05, 'epoch': 1.71}
+{'loss': 0.6379, 'learning_rate': 1.0183890948911074e-05, 'epoch': 1.72}
+{'loss': 0.6726, 'learning_rate': 1.0118517455823374e-05, 'epoch': 1.72}
+{'loss': 0.6715, 'learning_rate': 1.0053211484238303e-05, 'epoch': 1.73}
+{'loss': 0.6376, 'learning_rate': 9.987974885757647e-06, 'epoch': 1.73}
+{'loss': 0.6052, 'learning_rate': 9.922809510016277e-06, 'epoch': 1.74}
+{'loss': 0.6083, 'learning_rate': 9.857717204629696e-06, 'epoch': 1.74}
+{'loss': 0.6343, 'learning_rate': 9.792699815141685e-06, 'epoch': 1.75}
+{'loss': 0.631, 'learning_rate': 9.727759184971936e-06, 'epoch': 1.75}
+{'loss': 0.6598, 'learning_rate': 9.662897155363814e-06, 'epoch': 1.76}
+{'loss': 0.6396, 'learning_rate': 9.598115565332142e-06, 'epoch': 1.76}
+{'loss': 0.6778, 'learning_rate': 9.533416251611064e-06, 'epoch': 1.77}
+{'loss': 0.6252, 'learning_rate': 9.468801048601972e-06, 'epoch': 1.77}
+{'loss': 0.6119, 'learning_rate': 9.404271788321482e-06, 'epoch': 1.78}
+{'loss': 0.6523, 'learning_rate': 9.339830300349498e-06, 'epoch': 1.78}
+{'loss': 0.6336, 'learning_rate': 9.275478411777354e-06, 'epoch': 1.79}
+{'loss': 0.592, 'learning_rate': 9.211217947155986e-06, 'epoch': 1.79}
+{'loss': 0.6204, 'learning_rate': 9.147050728444215e-06, 'epoch': 1.8}
+{'loss': 0.6273, 'learning_rate': 9.08297857495709e-06, 'epoch': 1.8}
+{'loss': 0.5883, 'learning_rate': 9.0190033033143e-06, 'epoch': 1.81}
+{'loss': 0.6282, 'learning_rate': 8.955126727388672e-06, 'epoch': 1.81}
+{'loss': 0.6745, 'learning_rate': 8.89135065825474e-06, 'epoch': 1.82}
+{'loss': 0.6146, 'learning_rate': 8.827676904137397e-06, 'epoch': 1.82}
+{'loss': 0.5944, 'learning_rate': 8.76410727036062e-06, 'epoch': 1.83}
+{'loss': 0.6359, 'learning_rate': 8.700643559296313e-06, 'epoch': 1.83}
+{'loss': 0.5846, 'learning_rate': 8.637287570313159e-06, 'epoch': 1.84}
+{'loss': 0.6315, 'learning_rate': 8.574041099725644e-06, 'epoch': 1.84}
+{'loss': 0.5993, 'learning_rate': 8.510905940743093e-06, 'epoch': 1.85}
+{'loss': 0.652, 'learning_rate': 8.447883883418866e-06, 'epoch': 1.85}
+{'loss': 0.6542, 'learning_rate': 8.38497671459957e-06, 'epoch': 1.85}
+{'loss': 0.6168, 'learning_rate': 8.32218621787441e-06, 'epoch': 1.86}
+{'loss': 0.632, 'learning_rate': 8.25951417352462e-06, 'epoch': 1.86}
+{'loss': 0.6016, 'learning_rate': 8.196962358473e-06, 'epoch': 1.87}
+{'loss': 0.5967, 'learning_rate': 8.134532546233505e-06, 'epoch': 1.87}
+{'loss': 0.6398, 'learning_rate': 8.072226506860988e-06, 'epoch': 1.88}
+{'loss': 0.6485, 'learning_rate': 8.010046006901001e-06, 'epoch': 1.88}
+{'loss': 0.588, 'learning_rate': 7.947992809339723e-06, 'epoch': 1.89}
+{'loss': 0.6784, 'learning_rate': 7.88606867355395e-06, 'epoch': 1.89}
+{'loss': 0.6223, 'learning_rate': 7.824275355261233e-06, 'epoch': 1.9}
+{'loss': 0.5966, 'learning_rate': 7.762614606470084e-06, 'epoch': 1.9}
+{'loss': 0.6124, 'learning_rate': 7.701088175430327e-06, 'epoch': 1.91}
+{'loss': 0.637, 'learning_rate': 7.639697806583493e-06, 'epoch': 1.91}
+{'loss': 0.6198, 'learning_rate': 7.578445240513393e-06, 'epoch': 1.92}
+{'loss': 0.6397, 'learning_rate': 7.517332213896743e-06, 'epoch': 1.92}
+{'loss': 0.6308, 'learning_rate': 7.456360459453952e-06, 'epoch': 1.93}
+{'loss': 0.5814, 'learning_rate': 7.395531705899969e-06, 'epoch': 1.93}
+{'loss': 0.5953, 'learning_rate': 7.334847677895276e-06, 'epoch': 1.94}
+{'loss': 0.6071, 'learning_rate': 7.274310095997e-06, 'epoch': 1.94}
+{'loss': 0.6304, 'learning_rate': 7.213920676610112e-06, 'epoch': 1.95}
+{'loss': 0.6411, 'learning_rate': 7.153681131938791e-06, 'epoch': 1.95}
+{'loss': 0.6012, 'learning_rate': 7.093593169937849e-06, 'epoch': 1.96}
+{'loss': 0.6503, 'learning_rate': 7.033658494264309e-06, 'epoch': 1.96}
+{'loss': 0.6363, 'learning_rate': 6.973878804229131e-06, 'epoch': 1.97}
+{'loss': 0.6212, 'learning_rate': 6.914255794748989e-06, 'epoch': 1.97}
+{'loss': 0.6694, 'learning_rate': 6.8547911562982595e-06, 'epoch': 1.98}
+{'loss': 0.6147, 'learning_rate': 6.7954865748610515e-06, 'epoch': 1.98}
+{'loss': 0.6615, 'learning_rate': 6.736343731883425e-06, 'epoch': 1.99}
+{'loss': 0.602, 'learning_rate': 6.677364304225731e-06, 'epoch': 1.99}
+{'loss': 0.604, 'learning_rate': 6.618549964115033e-06, 'epoch': 2.0}
+{'loss': 0.4458, 'learning_rate': 6.559902379097721e-06, 'epoch': 2.0}
+{'loss': 0.3383, 'learning_rate': 6.501423211992224e-06, 'epoch': 2.01}
+{'loss': 0.3288, 'learning_rate': 6.443114120841874e-06, 'epoch': 2.01}
+{'loss': 0.3252, 'learning_rate': 6.384976758867875e-06, 'epoch': 2.02}
+{'loss': 0.3226, 'learning_rate': 6.32701277442245e-06, 'epoch': 2.02}
+{'loss': 0.3122, 'learning_rate': 6.269223810942086e-06, 'epoch': 2.03}
+{'loss': 0.2519, 'learning_rate': 6.211611506900973e-06, 'epoch': 2.03}
+{'loss': 0.3158, 'learning_rate': 6.1541774957645045e-06, 'epoch': 2.04}
+{'loss': 0.2846, 'learning_rate': 6.096923405942989e-06, 'epoch': 2.04}
+{'loss': 0.2747, 'learning_rate': 6.03985086074549e-06, 'epoch': 2.05}
+{'loss': 0.2876, 'learning_rate': 5.982961478333768e-06, 'epoch': 2.05}
+{'loss': 0.2596, 'learning_rate': 5.926256871676443e-06, 'epoch': 2.06}
+{'loss': 0.28, 'learning_rate': 5.86973864850322e-06, 'epoch': 2.06}
+{'loss': 0.2694, 'learning_rate': 5.813408411259331e-06, 'epoch': 2.07}
+{'loss': 0.2707, 'learning_rate': 5.757267757060109e-06, 'epoch': 2.07}
+{'loss': 0.2814, 'learning_rate': 5.701318277645675e-06, 'epoch': 2.08}
+{'loss': 0.2916, 'learning_rate': 5.645561559335832e-06, 'epoch': 2.08}
+{'loss': 0.3062, 'learning_rate': 5.589999182985087e-06, 'epoch': 2.09}
+{'loss': 0.2818, 'learning_rate': 5.534632723937809e-06, 'epoch': 2.09}
+{'loss': 0.263, 'learning_rate': 5.479463751983603e-06, 'epoch': 2.1}
+{'loss': 0.2992, 'learning_rate': 5.424493831312757e-06, 'epoch': 2.1}
+{'loss': 0.2966, 'learning_rate': 5.369724520471925e-06, 'epoch': 2.11}
+{'loss': 0.2803, 'learning_rate': 5.315157372319915e-06, 'epoch': 2.11}
+{'loss': 0.2749, 'learning_rate': 5.2607939339836945e-06, 'epoch': 2.12}
+{'loss': 0.2728, 'learning_rate': 5.2066357468144824e-06, 'epoch': 2.12}
+{'loss': 0.2545, 'learning_rate': 5.152684346344087e-06, 'epoch': 2.13}
+{'loss': 0.2722, 'learning_rate': 5.0989412622413345e-06, 'epoch': 2.13}
+{'loss': 0.3021, 'learning_rate': 5.0454080182687314e-06, 'epoch': 2.14}
+{'loss': 0.2483, 'learning_rate': 4.992086132239238e-06, 'epoch': 2.14}
+{'loss': 0.2703, 'learning_rate': 4.938977115973242e-06, 'epoch': 2.15}
+{'loss': 0.2829, 'learning_rate': 4.886082475255694e-06, 'epoch': 2.15}
+{'loss': 0.2634, 'learning_rate': 4.833403709793424e-06, 'epoch': 2.15}
+{'loss': 0.2684, 'learning_rate': 4.780942313172602e-06, 'epoch': 2.16}
+{'loss': 0.3123, 'learning_rate': 4.728699772816407e-06, 'epoch': 2.16}
+{'loss': 0.2837, 'learning_rate': 4.6766775699428365e-06, 'epoch': 2.17}
+{'loss': 0.2915, 'learning_rate': 4.624877179522742e-06, 'epoch': 2.17}
+{'loss': 0.305, 'learning_rate': 4.573300070237973e-06, 'epoch': 2.18}
+{'loss': 0.2537, 'learning_rate': 4.5219477044397525e-06, 'epoch': 2.18}
+{'loss': 0.2782, 'learning_rate': 4.470821538107219e-06, 'epoch': 2.19}
+{'loss': 0.3202, 'learning_rate': 4.419923020806148e-06, 'epoch': 2.19}
+{'loss': 0.2547, 'learning_rate': 4.36925359564783e-06, 'epoch': 2.2}
+{'loss': 0.2707, 'learning_rate': 4.318814699248188e-06, 'epoch': 2.2}
+{'loss': 0.246, 'learning_rate': 4.268607761687019e-06, 'epoch': 2.21}
+{'loss': 0.2737, 'learning_rate': 4.218634206467449e-06, 'epoch': 2.21}
+{'loss': 0.2921, 'learning_rate': 4.1688954504756e-06, 'epoch': 2.22}
+{'loss': 0.2677, 'learning_rate': 4.119392903940384e-06, 'epoch': 2.22}
+{'loss': 0.2979, 'learning_rate': 4.07012797039353e-06, 'epoch': 2.23}
+{'loss': 0.2459, 'learning_rate': 4.021102046629799e-06, 'epoch': 2.23}
+{'loss': 0.2745, 'learning_rate': 3.972316522667381e-06, 'epoch': 2.24}
+{'loss': 0.2943, 'learning_rate': 3.923772781708468e-06, 'epoch': 2.24}
+{'loss': 0.2403, 'learning_rate': 3.875472200100051e-06, 'epoch': 2.25}
+{'loss': 0.2781, 'learning_rate': 3.827416147294888e-06, 'epoch': 2.25}
+{'loss': 0.2766, 'learning_rate': 3.7796059858126927e-06, 'epoch': 2.26}
+{'loss': 0.2738, 'learning_rate': 3.7320430712014796e-06, 'epoch': 2.26}
+{'loss': 0.3136, 'learning_rate': 3.6847287519991434e-06, 'epoch': 2.27}
+{'loss': 0.2902, 'learning_rate': 3.637664369695233e-06, 'epoch': 2.27}
+{'loss': 0.2516, 'learning_rate': 3.590851258692894e-06, 'epoch': 2.28}
+{'loss': 0.2668, 'learning_rate': 3.5442907462710605e-06, 'epoch': 2.28}
+{'loss': 0.2789, 'learning_rate': 3.4979841525468016e-06, 'epoch': 2.29}
+{'loss': 0.2794, 'learning_rate': 3.451932790437898e-06, 'epoch': 2.29}
+{'loss': 0.273, 'learning_rate': 3.4061379656256345e-06, 'epoch': 2.3}
+{'loss': 0.2828, 'learning_rate': 3.3606009765177555e-06, 'epoch': 2.3}
+{'loss': 0.2836, 'learning_rate': 3.3153231142116617e-06, 'epoch': 2.31}
+{'loss': 0.2781, 'learning_rate': 3.270305662457805e-06, 'epoch': 2.31}
+{'loss': 0.2911, 'learning_rate': 3.225549897623302e-06, 'epoch': 2.32}
+{'loss': 0.3071, 'learning_rate': 3.181057088655719e-06, 'epoch': 2.32}
+{'loss': 0.2583, 'learning_rate': 3.136828497047116e-06, 'epoch': 2.33}
+{'loss': 0.2976, 'learning_rate': 3.0928653767982695e-06, 'epoch': 2.33}
+{'loss': 0.2727, 'learning_rate': 3.0491689743831277e-06, 'epoch': 2.34}
+{'loss': 0.2843, 'learning_rate': 3.005740528713458e-06, 'epoch': 2.34}
+{'loss': 0.2655, 'learning_rate': 2.9625812711037206e-06, 'epoch': 2.35}
+{'loss': 0.2759, 'learning_rate': 2.91969242523618e-06, 'epoch': 2.35}
+{'loss': 0.272, 'learning_rate': 2.87707520712617e-06, 'epoch': 2.36}
+{'loss': 0.2734, 'learning_rate': 2.834730825087663e-06, 'epoch': 2.36}
+{'loss': 0.312, 'learning_rate': 2.7926604796989676e-06, 'epoch': 2.37}
+{'loss': 0.2608, 'learning_rate': 2.7508653637687176e-06, 'epoch': 2.37}
+{'loss': 0.3084, 'learning_rate': 2.709346662302041e-06, 'epoch': 2.38}
+{'loss': 0.3209, 'learning_rate': 2.6681055524669694e-06, 'epoch': 2.38}
+{'loss': 0.2781, 'learning_rate': 2.6271432035610513e-06, 'epoch': 2.39}
+{'loss': 0.2379, 'learning_rate': 2.5864607769782084e-06, 'epoch': 2.39}
+{'loss': 0.2945, 'learning_rate': 2.5460594261757996e-06, 'epoch': 2.4}
+{'loss': 0.2545, 'learning_rate': 2.5059402966419303e-06, 'epoch': 2.4}
+{'loss': 0.285, 'learning_rate': 2.466104525862957e-06, 'epoch': 2.41}
+{'loss': 0.2818, 'learning_rate': 2.426553243291249e-06, 'epoch': 2.41}
+{'loss': 0.2743, 'learning_rate': 2.3872875703131583e-06, 'epoch': 2.42}
+{'loss': 0.2991, 'learning_rate': 2.3483086202172377e-06, 'epoch': 2.42}
+{'loss': 0.2778, 'learning_rate': 2.309617498162657e-06, 'epoch': 2.43}
+{'loss': 0.2723, 'learning_rate': 2.271215301147887e-06, 'epoch': 2.43}
+{'loss': 0.2684, 'learning_rate': 2.2331031179795792e-06, 'epoch': 2.44}
+{'loss': 0.2818, 'learning_rate': 2.1952820292417143e-06, 'epoch': 2.44}
+{'loss': 0.2658, 'learning_rate': 2.1577531072649495e-06, 'epoch': 2.45}
+{'loss': 0.2865, 'learning_rate': 2.120517416096217e-06, 'epoch': 2.45}
+{'loss': 0.2744, 'learning_rate': 2.083576011468562e-06, 'epoch': 2.46}
+{'loss': 0.2939, 'learning_rate': 2.0469299407712112e-06, 'epoch': 2.46}
+{'loss': 0.3174, 'learning_rate': 2.010580243019865e-06, 'epoch': 2.46}
+{'loss': 0.2805, 'learning_rate': 1.9745279488272484e-06, 'epoch': 2.47}
+{'loss': 0.2587, 'learning_rate': 1.938774080373884e-06, 'epoch': 2.47}
+{'loss': 0.2591, 'learning_rate': 1.9033196513791138e-06, 'epoch': 2.48}
+{'loss': 0.28, 'learning_rate': 1.8681656670723663e-06, 'epoch': 2.48}
+{'loss': 0.2757, 'learning_rate': 1.833313124164636e-06, 'epoch': 2.49}
+{'loss': 0.2684, 'learning_rate': 1.7987630108202355e-06, 'epoch': 2.49}
+{'loss': 0.3003, 'learning_rate': 1.764516306628787e-06, 'epoch': 2.5}
+{'loss': 0.2826, 'learning_rate': 1.7305739825774228e-06, 'epoch': 2.5}
+{'loss': 0.2531, 'learning_rate': 1.6969370010232882e-06, 'epoch': 2.51}
+{'loss': 0.277, 'learning_rate': 1.663606315666226e-06, 'epoch': 2.51}
+{'loss': 0.2838, 'learning_rate': 1.6305828715217506e-06, 'epoch': 2.52}
+{'loss': 0.3017, 'learning_rate': 1.597867604894264e-06, 'epoch': 2.52}
+{'loss': 0.2695, 'learning_rate': 1.5654614433504841e-06, 'epoch': 2.53}
+{'loss': 0.3005, 'learning_rate': 1.5333653056931684e-06, 'epoch': 2.53}
+{'loss': 0.259, 'learning_rate': 1.5015801019350476e-06, 'epoch': 2.54}
+{'loss': 0.276, 'learning_rate': 1.4701067332730426e-06, 'epoch': 2.54}
+{'loss': 0.2706, 'learning_rate': 1.4389460920626887e-06, 'epoch': 2.55}
+{'loss': 0.2808, 'learning_rate': 1.4080990617928571e-06, 'epoch': 2.55}
+{'loss': 0.2925, 'learning_rate': 1.3775665170606896e-06, 'epoch': 2.56}
+{'loss': 0.2644, 'learning_rate': 1.3473493235468177e-06, 'epoch': 2.56}
+{'loss': 0.2484, 'learning_rate': 1.3174483379907996e-06, 'epoch': 2.57}
+{'loss': 0.3012, 'learning_rate': 1.2878644081668403e-06, 'epoch': 2.57}
+{'loss': 0.3033, 'learning_rate': 1.2585983728597608e-06, 'epoch': 2.58}
+{'loss': 0.33, 'learning_rate': 1.2296510618411957e-06, 'epoch': 2.58}
+{'loss': 0.2513, 'learning_rate': 1.201023295846093e-06, 'epoch': 2.59}
+{'loss': 0.2871, 'learning_rate': 1.1727158865494206e-06, 'epoch': 2.59}
+{'loss': 0.2592, 'learning_rate': 1.1447296365431668e-06, 'epoch': 2.6}
+{'loss': 0.2672, 'learning_rate': 1.1170653393135847e-06, 'epoch': 2.6}
+{'loss': 0.2589, 'learning_rate': 1.0897237792186862e-06, 'epoch': 2.61}
+{'loss': 0.2851, 'learning_rate': 1.0627057314660114e-06, 'epoch': 2.61}
+{'loss': 0.2319, 'learning_rate': 1.0360119620906426e-06, 'epoch': 2.62}
+{'loss': 0.2757, 'learning_rate': 1.0096432279334905e-06, 'epoch': 2.62}
+{'loss': 0.2742, 'learning_rate': 9.836002766198379e-07, 'epoch': 2.63}
+{'loss': 0.324, 'learning_rate': 9.57883846538135e-07, 'epoch': 2.63}
+{'loss': 0.2435, 'learning_rate': 9.324946668190657e-07, 'epoch': 2.64}
+{'loss': 0.2795, 'learning_rate': 9.074334573148783e-07, 'epoch': 2.64}
+{'loss': 0.3012, 'learning_rate': 8.827009285789778e-07, 'epoch': 2.65}
+{'loss': 0.2663, 'learning_rate': 8.582977818457696e-07, 'epoch': 2.65}
+{'loss': 0.2469, 'learning_rate': 8.342247090107919e-07, 'epoch': 2.66}
+{'loss': 0.2835, 'learning_rate': 8.104823926110811e-07, 'epoch': 2.66}
+{'loss': 0.2554, 'learning_rate': 7.870715058058406e-07, 'epoch': 2.67}
+{'loss': 0.2571, 'learning_rate': 7.639927123573351e-07, 'epoch': 2.67}
+{'loss': 0.2679, 'learning_rate': 7.412466666120846e-07, 'epoch': 2.68}
+{'loss': 0.2569, 'learning_rate': 7.188340134823043e-07, 'epoch': 2.68}
+{'loss': 0.2704, 'learning_rate': 6.967553884276279e-07, 'epoch': 2.69}
+{'loss': 0.3005, 'learning_rate': 6.750114174370797e-07, 'epoch': 2.69}
+{'loss': 0.2542, 'learning_rate': 6.536027170113354e-07, 'epoch': 2.7}
+{'loss': 0.2783, 'learning_rate': 6.32529894145234e-07, 'epoch': 2.7}
+{'loss': 0.2264, 'learning_rate': 6.117935463105809e-07, 'epoch': 2.71}
+{'loss': 0.2635, 'learning_rate': 5.913942614391931e-07, 'epoch': 2.71}
+{'loss': 0.2658, 'learning_rate': 5.713326179062409e-07, 'epoch': 2.72}
+{'loss': 0.2681, 'learning_rate': 5.516091845138377e-07, 'epoch': 2.72}
+{'loss': 0.3189, 'learning_rate': 5.322245204749319e-07, 'epoch': 2.73}
+{'loss': 0.2983, 'learning_rate': 5.131791753974296e-07, 'epoch': 2.73}
+{'loss': 0.2887, 'learning_rate': 4.944736892686278e-07, 'epoch': 2.74}
+{'loss': 0.2594, 'learning_rate': 4.761085924398959e-07, 'epoch': 2.74}
+{'loss': 0.2366, 'learning_rate': 4.580844056116418e-07, 'epoch': 2.75}
+{'loss': 0.3332, 'learning_rate': 4.4040163981855095e-07, 'epoch': 2.75}
+{'loss': 0.2593, 'learning_rate': 4.2306079641509094e-07, 'epoch': 2.76}
+{'loss': 0.2825, 'learning_rate': 4.0606236706130367e-07, 'epoch': 2.76}
+{'loss': 0.2865, 'learning_rate': 3.89406833708858e-07, 'epoch': 2.77}
+{'loss': 0.3002, 'learning_rate': 3.73094668587394e-07, 'epoch': 2.77}
+{'loss': 0.2941, 'learning_rate': 3.5712633419112686e-07, 'epoch': 2.77}
+{'loss': 0.3138, 'learning_rate': 3.4150228326573356e-07, 'epoch': 2.78}
+{'loss': 0.3054, 'learning_rate': 3.262229587955232e-07, 'epoch': 2.78}
+{'loss': 0.2502, 'learning_rate': 3.112887939908715e-07, 'epoch': 2.79}
+{'loss': 0.2679, 'learning_rate': 2.9670021227593965e-07, 'epoch': 2.79}
+{'loss': 0.2683, 'learning_rate': 2.824576272766666e-07, 'epoch': 2.8}
+{'loss': 0.3101, 'learning_rate': 2.6856144280904967e-07, 'epoch': 2.8}
+{'loss': 0.2749, 'learning_rate': 2.550120528676841e-07, 'epoch': 2.81}
+{'loss': 0.2455, 'learning_rate': 2.4180984161460004e-07, 'epoch': 2.81}
+{'loss': 0.2607, 'learning_rate': 2.2895518336836923e-07, 'epoch': 2.82}
+{'loss': 0.2729, 'learning_rate': 2.164484425934879e-07, 'epoch': 2.82}
+{'loss': 0.2669, 'learning_rate': 2.0428997389004972e-07, 'epoch': 2.83}
+{'loss': 0.3026, 'learning_rate': 1.9248012198368748e-07, 'epoch': 2.83}
+{'loss': 0.2394, 'learning_rate': 1.8101922171580022e-07, 'epoch': 2.84}
+{'loss': 0.2578, 'learning_rate': 1.699075980340581e-07, 'epoch': 2.84}
+{'loss': 0.252, 'learning_rate': 1.5914556598319307e-07, 'epoch': 2.85}
+{'loss': 0.2478, 'learning_rate': 1.4873343069606305e-07, 'epoch': 2.85}
+{'loss': 0.3517, 'learning_rate': 1.3867148738500313e-07, 'epoch': 2.86}
+{'loss': 0.285, 'learning_rate': 1.289600213334505e-07, 'epoch': 2.86}
+{'loss': 0.2673, 'learning_rate': 1.195993078878646e-07, 'epoch': 2.87}
+{'loss': 0.2644, 'learning_rate': 1.1058961244991144e-07, 'epoch': 2.87}
+{'loss': 0.2689, 'learning_rate': 1.0193119046894295e-07, 'epoch': 2.88}
+{'loss': 0.2699, 'learning_rate': 9.362428743475565e-08, 'epoch': 2.88}
+{'loss': 0.2677, 'learning_rate': 8.566913887062683e-08, 'epoch': 2.89}
+{'loss': 0.2846, 'learning_rate': 7.806597032663925e-08, 'epoch': 2.89}
+{'loss': 0.2686, 'learning_rate': 7.081499737328634e-08, 'epoch': 2.9}
+{'loss': 0.2542, 'learning_rate': 6.391642559535616e-08, 'epoch': 2.9}
+{'loss': 0.2678, 'learning_rate': 5.7370450586109737e-08, 'epoch': 2.91}
+{'loss': 0.237, 'learning_rate': 5.117725794172995e-08, 'epoch': 2.91}
+{'loss': 0.2847, 'learning_rate': 4.533702325605904e-08, 'epoch': 2.92}
+{'loss': 0.2397, 'learning_rate': 3.9849912115623446e-08, 'epoch': 2.92}
+{'loss': 0.2672, 'learning_rate': 3.471608009493754e-08, 'epoch': 2.93}
+{'loss': 0.2767, 'learning_rate': 2.9935672752090525e-08, 'epoch': 2.93}
+{'loss': 0.2758, 'learning_rate': 2.5508825624626088e-08, 'epoch': 2.94}
+{'loss': 0.2576, 'learning_rate': 2.1435664225688547e-08, 'epoch': 2.94}
+{'loss': 0.3037, 'learning_rate': 1.7716304040475697e-08, 'epoch': 2.95}
+{'loss': 0.271, 'learning_rate': 1.4350850522956705e-08, 'epoch': 2.95}
+{'loss': 0.2347, 'learning_rate': 1.1339399092885616e-08, 'epoch': 2.96}
+{'loss': 0.2924, 'learning_rate': 8.682035133096566e-09, 'epoch': 2.96}
+{'loss': 0.2847, 'learning_rate': 6.378833987077948e-09, 'epoch': 2.97}
+{'loss': 0.2594, 'learning_rate': 4.429860956842169e-09, 'epoch': 2.97}
+{'loss': 0.2613, 'learning_rate': 2.8351713010743573e-09, 'epoch': 2.98}
+{'loss': 0.2603, 'learning_rate': 1.5948102335572313e-09, 'epoch': 2.98}
+{'loss': 0.2915, 'learning_rate': 7.088129218985052e-10, 'epoch': 2.99}
+{'loss': 0.2903, 'learning_rate': 1.772044865316902e-10, 'epoch': 2.99}
+{'loss': 0.2426, 'learning_rate': 0.0, 'epoch': 3.0}
+{'train_runtime': 5691.3236, 'train_samples_per_second': 27.41, 'train_steps_per_second': 0.107, 'train_loss': 0.6601732866517429, 'epoch': 3.0}
+[2024-01-10 05:17:55,050] [INFO] [launch.py:347:main] Process 63171 exits successfully.
+[2024-01-10 05:17:55,050] [INFO] [launch.py:347:main] Process 63167 exits successfully.
+[2024-01-10 05:17:55,051] [INFO] [launch.py:347:main] Process 63166 exits successfully.
+[2024-01-10 05:17:56,052] [INFO] [launch.py:347:main] Process 63169 exits successfully.
+[2024-01-10 05:17:56,052] [INFO] [launch.py:347:main] Process 63168 exits successfully.
+[2024-01-10 05:17:56,052] [INFO] [launch.py:347:main] Process 63165 exits successfully.
+[2024-01-10 05:17:56,053] [INFO] [launch.py:347:main] Process 63170 exits successfully.
+Finish training...
+[2024-01-10 05:18:11,068] [INFO] [launch.py:347:main] Process 63164 exits successfully.