Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "airoboros-l2-7b-gpt4-2.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f9122fd1dc300b363217b41600b3075727a2f8550c1c62e0550590277e0c4a
+size 9976631486

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:317303be7108891ad5af49ca35da4f7b849e17bbbbd996176f9eab4ef082334f
+size 3500314451

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 13476835328
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "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 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,4255 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 705,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.896551724137931e-07,
+      "loss": 1.0556,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3793103448275862e-06,
+      "loss": 0.9993,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0689655172413796e-06,
+      "loss": 1.1975,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.7586206896551725e-06,
+      "loss": 1.0112,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 1.0039,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.137931034482759e-06,
+      "loss": 1.0945,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.8275862068965525e-06,
+      "loss": 1.1241,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.517241379310345e-06,
+      "loss": 0.9879,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.206896551724138e-06,
+      "loss": 0.9382,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 1.1059,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.586206896551724e-06,
+      "loss": 0.95,
+      "step": 11
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.275862068965518e-06,
+      "loss": 1.1367,
+      "step": 12
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.965517241379312e-06,
+      "loss": 1.0448,
+      "step": 13
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.655172413793105e-06,
+      "loss": 0.9436,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.0344827586206898e-05,
+      "loss": 1.0325,
+      "step": 15
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.103448275862069e-05,
+      "loss": 0.9429,
+      "step": 16
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.1724137931034483e-05,
+      "loss": 0.8973,
+      "step": 17
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2413793103448277e-05,
+      "loss": 0.869,
+      "step": 18
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.310344827586207e-05,
+      "loss": 0.8624,
+      "step": 19
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3793103448275863e-05,
+      "loss": 0.9881,
+      "step": 20
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4482758620689657e-05,
+      "loss": 0.9931,
+      "step": 21
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5172413793103448e-05,
+      "loss": 0.8976,
+      "step": 22
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.586206896551724e-05,
+      "loss": 0.9156,
+      "step": 23
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.6551724137931037e-05,
+      "loss": 0.8633,
+      "step": 24
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.7241379310344828e-05,
+      "loss": 0.7874,
+      "step": 25
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.7931034482758623e-05,
+      "loss": 0.8164,
+      "step": 26
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.8620689655172415e-05,
+      "loss": 0.8524,
+      "step": 27
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.931034482758621e-05,
+      "loss": 0.894,
+      "step": 28
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2e-05,
+      "loss": 0.8133,
+      "step": 29
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9999892011980525e-05,
+      "loss": 0.9563,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9999568050254373e-05,
+      "loss": 0.9272,
+      "step": 31
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.999902812181835e-05,
+      "loss": 0.9408,
+      "step": 32
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9998272238333606e-05,
+      "loss": 0.9658,
+      "step": 33
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9997300416125426e-05,
+      "loss": 0.7818,
+      "step": 34
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.999611267618283e-05,
+      "loss": 0.8793,
+      "step": 35
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9994709044158157e-05,
+      "loss": 0.866,
+      "step": 36
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.99930895503665e-05,
+      "loss": 0.8059,
+      "step": 37
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9991254229785043e-05,
+      "loss": 0.8789,
+      "step": 38
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.998920312205231e-05,
+      "loss": 0.7708,
+      "step": 39
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9986936271467316e-05,
+      "loss": 0.9485,
+      "step": 40
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.99844537269886e-05,
+      "loss": 0.8965,
+      "step": 41
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9981755542233175e-05,
+      "loss": 0.8373,
+      "step": 42
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9978841775475368e-05,
+      "loss": 0.8836,
+      "step": 43
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.997571248964556e-05,
+      "loss": 0.8743,
+      "step": 44
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9972367752328824e-05,
+      "loss": 0.9257,
+      "step": 45
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9968807635763472e-05,
+      "loss": 0.798,
+      "step": 46
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9965032216839493e-05,
+      "loss": 0.8669,
+      "step": 47
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.996104157709689e-05,
+      "loss": 0.8556,
+      "step": 48
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9956835802723916e-05,
+      "loss": 0.8955,
+      "step": 49
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9952414984555225e-05,
+      "loss": 0.8271,
+      "step": 50
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.994777921806989e-05,
+      "loss": 0.8648,
+      "step": 51
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9942928603389366e-05,
+      "loss": 0.8252,
+      "step": 52
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9937863245275303e-05,
+      "loss": 0.9669,
+      "step": 53
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9932583253127302e-05,
+      "loss": 0.9514,
+      "step": 54
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.992708874098054e-05,
+      "loss": 0.6726,
+      "step": 55
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9921379827503316e-05,
+      "loss": 0.98,
+      "step": 56
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.991545663599448e-05,
+      "loss": 0.8068,
+      "step": 57
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.990931929438078e-05,
+      "loss": 0.8543,
+      "step": 58
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.990296793521408e-05,
+      "loss": 0.7887,
+      "step": 59
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.989640269566853e-05,
+      "loss": 0.913,
+      "step": 60
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9889623717537564e-05,
+      "loss": 0.861,
+      "step": 61
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9882631147230874e-05,
+      "loss": 0.8665,
+      "step": 62
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.987542513577122e-05,
+      "loss": 0.751,
+      "step": 63
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9868005838791185e-05,
+      "loss": 0.9501,
+      "step": 64
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9860373416529804e-05,
+      "loss": 0.8143,
+      "step": 65
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.985252803382911e-05,
+      "loss": 0.8382,
+      "step": 66
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.984446986013057e-05,
+      "loss": 0.8425,
+      "step": 67
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.983619906947144e-05,
+      "loss": 0.9864,
+      "step": 68
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9827715840480962e-05,
+      "loss": 0.7999,
+      "step": 69
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9819020356376562e-05,
+      "loss": 0.8034,
+      "step": 70
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9810112804959867e-05,
+      "loss": 0.8757,
+      "step": 71
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.980099337861264e-05,
+      "loss": 0.8238,
+      "step": 72
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9791662274292638e-05,
+      "loss": 0.7679,
+      "step": 73
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9782119693529358e-05,
+      "loss": 0.8648,
+      "step": 74
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.977236584241968e-05,
+      "loss": 0.8542,
+      "step": 75
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9762400931623413e-05,
+      "loss": 0.8768,
+      "step": 76
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9752225176358757e-05,
+      "loss": 0.8488,
+      "step": 77
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9741838796397638e-05,
+      "loss": 0.8567,
+      "step": 78
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9731242016060985e-05,
+      "loss": 0.8294,
+      "step": 79
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.972043506421386e-05,
+      "loss": 0.9739,
+      "step": 80
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 0.8278,
+      "step": 81
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9698191584139402e-05,
+      "loss": 0.784,
+      "step": 82
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9686755536317945e-05,
+      "loss": 0.9227,
+      "step": 83
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.967511027778738e-05,
+      "loss": 0.9461,
+      "step": 84
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9663256060057395e-05,
+      "loss": 0.8601,
+      "step": 85
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.965119313915068e-05,
+      "loss": 0.8871,
+      "step": 86
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9638921775597428e-05,
+      "loss": 0.8098,
+      "step": 87
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9626442234429684e-05,
+      "loss": 0.8745,
+      "step": 88
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.961375478517564e-05,
+      "loss": 0.8038,
+      "step": 89
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9600859701853796e-05,
+      "loss": 0.9424,
+      "step": 90
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.958775726296706e-05,
+      "loss": 0.7904,
+      "step": 91
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9574447751496706e-05,
+      "loss": 0.847,
+      "step": 92
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.95609314548963e-05,
+      "loss": 0.7736,
+      "step": 93
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.954720866508546e-05,
+      "loss": 0.8309,
+      "step": 94
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.953327967844356e-05,
+      "loss": 0.8444,
+      "step": 95
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9519144795803342e-05,
+      "loss": 0.8134,
+      "step": 96
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.95048043224444e-05,
+      "loss": 0.7407,
+      "step": 97
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.94902585680866e-05,
+      "loss": 0.8738,
+      "step": 98
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9475507846883377e-05,
+      "loss": 0.8814,
+      "step": 99
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9460552477414972e-05,
+      "loss": 0.7871,
+      "step": 100
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9445392782681523e-05,
+      "loss": 0.7779,
+      "step": 101
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9430029090096118e-05,
+      "loss": 0.7519,
+      "step": 102
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.94144617314777e-05,
+      "loss": 0.672,
+      "step": 103
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.939869104304392e-05,
+      "loss": 0.7215,
+      "step": 104
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9382717365403854e-05,
+      "loss": 0.7851,
+      "step": 105
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9366541043550667e-05,
+      "loss": 0.9791,
+      "step": 106
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9350162426854152e-05,
+      "loss": 0.7955,
+      "step": 107
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.933358186905318e-05,
+      "loss": 0.8314,
+      "step": 108
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9316799728248074e-05,
+      "loss": 0.846,
+      "step": 109
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9299816366892865e-05,
+      "loss": 0.7835,
+      "step": 110
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9282632151787462e-05,
+      "loss": 0.7168,
+      "step": 111
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9265247454069736e-05,
+      "loss": 0.8363,
+      "step": 112
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.924766264920751e-05,
+      "loss": 0.8531,
+      "step": 113
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.922987811699042e-05,
+      "loss": 0.8557,
+      "step": 114
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9211894241521757e-05,
+      "loss": 0.8472,
+      "step": 115
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9193711411210138e-05,
+      "loss": 0.8157,
+      "step": 116
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.917533001876113e-05,
+      "loss": 0.8511,
+      "step": 117
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9156750461168768e-05,
+      "loss": 0.8258,
+      "step": 118
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9137973139706973e-05,
+      "loss": 0.8866,
+      "step": 119
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.91189984599209e-05,
+      "loss": 0.8754,
+      "step": 120
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9099826831618168e-05,
+      "loss": 0.8098,
+      "step": 121
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.908045866886001e-05,
+      "loss": 0.8266,
+      "step": 122
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.9060894389952328e-05,
+      "loss": 0.7875,
+      "step": 123
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9041134417436674e-05,
+      "loss": 0.8081,
+      "step": 124
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9021179178081107e-05,
+      "loss": 0.9198,
+      "step": 125
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.9001029102870982e-05,
+      "loss": 0.8103,
+      "step": 126
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.898068462699964e-05,
+      "loss": 0.7414,
+      "step": 127
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8960146189859014e-05,
+      "loss": 0.8528,
+      "step": 128
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8939414235030137e-05,
+      "loss": 0.7691,
+      "step": 129
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.891848921027355e-05,
+      "loss": 0.8529,
+      "step": 130
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.889737156751965e-05,
+      "loss": 0.7345,
+      "step": 131
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.887606176285893e-05,
+      "loss": 0.8487,
+      "step": 132
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 0.8229,
+      "step": 133
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.883286751292018e-05,
+      "loss": 0.8455,
+      "step": 134
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8810984000534457e-05,
+      "loss": 0.8394,
+      "step": 135
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8788910192006363e-05,
+      "loss": 0.8168,
+      "step": 136
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8766646564077265e-05,
+      "loss": 0.8928,
+      "step": 137
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8744193597588185e-05,
+      "loss": 0.8795,
+      "step": 138
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8721551777469397e-05,
+      "loss": 0.8805,
+      "step": 139
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.869872159272997e-05,
+      "loss": 0.7191,
+      "step": 140
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8675703536447178e-05,
+      "loss": 0.7595,
+      "step": 141
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8652498105755898e-05,
+      "loss": 0.791,
+      "step": 142
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.862910580183782e-05,
+      "loss": 0.7942,
+      "step": 143
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8605527129910663e-05,
+      "loss": 0.9044,
+      "step": 144
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.858176259921724e-05,
+      "loss": 0.7326,
+      "step": 145
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8557812723014476e-05,
+      "loss": 0.7109,
+      "step": 146
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.853367801856231e-05,
+      "loss": 0.925,
+      "step": 147
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8509359007112523e-05,
+      "loss": 0.861,
+      "step": 148
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8484856213897496e-05,
+      "loss": 0.8349,
+      "step": 149
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8460170168118857e-05,
+      "loss": 0.7501,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.843530140293603e-05,
+      "loss": 0.7858,
+      "step": 151
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.841025045545477e-05,
+      "loss": 0.9079,
+      "step": 152
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8385017866715507e-05,
+      "loss": 0.8215,
+      "step": 153
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8359604181681703e-05,
+      "loss": 0.7239,
+      "step": 154
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.833400994922806e-05,
+      "loss": 0.8738,
+      "step": 155
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8308235722128674e-05,
+      "loss": 0.791,
+      "step": 156
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8282282057045087e-05,
+      "loss": 0.8576,
+      "step": 157
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8256149514514284e-05,
+      "loss": 0.7068,
+      "step": 158
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 0.8253,
+      "step": 159
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8203350058563366e-05,
+      "loss": 0.7616,
+      "step": 160
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8176684285484985e-05,
+      "loss": 0.8861,
+      "step": 161
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.814984191561823e-05,
+      "loss": 0.9356,
+      "step": 162
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8122823528693966e-05,
+      "loss": 0.9105,
+      "step": 163
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.809562970824462e-05,
+      "loss": 0.728,
+      "step": 164
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.8068261041591548e-05,
+      "loss": 0.8131,
+      "step": 165
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.8040718119832378e-05,
+      "loss": 0.8395,
+      "step": 166
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.8013001537828213e-05,
+      "loss": 0.8104,
+      "step": 167
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7985111894190827e-05,
+      "loss": 0.8057,
+      "step": 168
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7957049791269684e-05,
+      "loss": 0.7177,
+      "step": 169
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7928815835138976e-05,
+      "loss": 0.739,
+      "step": 170
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.79004106355845e-05,
+      "loss": 0.7761,
+      "step": 171
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7871834806090502e-05,
+      "loss": 0.8598,
+      "step": 172
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7843088963826437e-05,
+      "loss": 0.8409,
+      "step": 173
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7814173729633607e-05,
+      "loss": 0.8533,
+      "step": 174
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7785089728011798e-05,
+      "loss": 0.8996,
+      "step": 175
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.775583758710575e-05,
+      "loss": 0.8081,
+      "step": 176
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.772641793869162e-05,
+      "loss": 0.8117,
+      "step": 177
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7696831418163318e-05,
+      "loss": 0.747,
+      "step": 178
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7667078664518796e-05,
+      "loss": 0.7996,
+      "step": 179
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.763716032034624e-05,
+      "loss": 0.8214,
+      "step": 180
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7607077031810204e-05,
+      "loss": 0.7476,
+      "step": 181
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7576829448637628e-05,
+      "loss": 0.784,
+      "step": 182
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7546418224103838e-05,
+      "loss": 0.86,
+      "step": 183
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7515844015018416e-05,
+      "loss": 0.8152,
+      "step": 184
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 0.8515,
+      "step": 185
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7454209288017105e-05,
+      "loss": 0.9277,
+      "step": 186
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7423150101263645e-05,
+      "loss": 0.7664,
+      "step": 187
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7391930592254636e-05,
+      "loss": 0.8191,
+      "step": 188
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7360551435256673e-05,
+      "loss": 0.8272,
+      "step": 189
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7329013307984363e-05,
+      "loss": 0.853,
+      "step": 190
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.729731689158568e-05,
+      "loss": 0.7301,
+      "step": 191
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.726546287062727e-05,
+      "loss": 0.6555,
+      "step": 192
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7233451933079663e-05,
+      "loss": 0.7224,
+      "step": 193
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.720128477030241e-05,
+      "loss": 0.8356,
+      "step": 194
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7168962077029146e-05,
+      "loss": 0.8095,
+      "step": 195
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7136484551352608e-05,
+      "loss": 0.7775,
+      "step": 196
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.7103852894709517e-05,
+      "loss": 0.8879,
+      "step": 197
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.831,
+      "step": 198
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7038130010899716e-05,
+      "loss": 0.7259,
+      "step": 199
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7005040203189818e-05,
+      "loss": 0.838,
+      "step": 200
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6971799103396332e-05,
+      "loss": 0.9048,
+      "step": 201
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.693840742944738e-05,
+      "loss": 0.6758,
+      "step": 202
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6904865902523098e-05,
+      "loss": 0.8217,
+      "step": 203
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.68711752470401e-05,
+      "loss": 0.8234,
+      "step": 204
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6837336190635824e-05,
+      "loss": 0.8661,
+      "step": 205
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6803349464152798e-05,
+      "loss": 0.8949,
+      "step": 206
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6769215801622884e-05,
+      "loss": 0.868,
+      "step": 207
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6734935940251404e-05,
+      "loss": 0.7001,
+      "step": 208
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6700510620401223e-05,
+      "loss": 0.8748,
+      "step": 209
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.666594058557677e-05,
+      "loss": 0.9121,
+      "step": 210
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6631226582407954e-05,
+      "loss": 0.6578,
+      "step": 211
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.659636936063407e-05,
+      "loss": 0.8304,
+      "step": 212
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6561369673087588e-05,
+      "loss": 0.7084,
+      "step": 213
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6526228275677892e-05,
+      "loss": 0.7908,
+      "step": 214
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.649094592737497e-05,
+      "loss": 0.7269,
+      "step": 215
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6455523390193e-05,
+      "loss": 0.8374,
+      "step": 216
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.641996142917391e-05,
+      "loss": 0.7641,
+      "step": 217
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.638426081237085e-05,
+      "loss": 0.8521,
+      "step": 218
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.63484223108316e-05,
+      "loss": 0.775,
+      "step": 219
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6312446698581915e-05,
+      "loss": 0.7633,
+      "step": 220
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6276334752608823e-05,
+      "loss": 0.7295,
+      "step": 221
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.624008725284383e-05,
+      "loss": 0.736,
+      "step": 222
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6203704982146073e-05,
+      "loss": 0.8085,
+      "step": 223
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6167188726285433e-05,
+      "loss": 0.8149,
+      "step": 224
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.613053927392553e-05,
+      "loss": 0.7756,
+      "step": 225
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.6093757416606725e-05,
+      "loss": 0.7207,
+      "step": 226
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6056843948729e-05,
+      "loss": 0.7413,
+      "step": 227
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6019799667534813e-05,
+      "loss": 0.783,
+      "step": 228
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5982625373091877e-05,
+      "loss": 0.8023,
+      "step": 229
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.594532186827588e-05,
+      "loss": 0.7778,
+      "step": 230
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5907889958753134e-05,
+      "loss": 0.7979,
+      "step": 231
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5870330452963206e-05,
+      "loss": 0.8487,
+      "step": 232
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5832644162101417e-05,
+      "loss": 0.7952,
+      "step": 233
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5794831900101352e-05,
+      "loss": 0.7541,
+      "step": 234
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5756894483617268e-05,
+      "loss": 0.7278,
+      "step": 235
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.571883273200646e-05,
+      "loss": 0.5169,
+      "step": 236
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 0.4145,
+      "step": 237
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.564233951424279e-05,
+      "loss": 0.3865,
+      "step": 238
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.560390970016015e-05,
+      "loss": 0.3764,
+      "step": 239
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5565358855055535e-05,
+      "loss": 0.4023,
+      "step": 240
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.552668781153484e-05,
+      "loss": 0.4175,
+      "step": 241
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5487897404799932e-05,
+      "loss": 0.4575,
+      "step": 242
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5448988472630654e-05,
+      "loss": 0.4268,
+      "step": 243
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5409961855366718e-05,
+      "loss": 0.3674,
+      "step": 244
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5370818395889536e-05,
+      "loss": 0.4569,
+      "step": 245
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.533155893960405e-05,
+      "loss": 0.343,
+      "step": 246
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5292184334420434e-05,
+      "loss": 0.4214,
+      "step": 247
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5252695430735824e-05,
+      "loss": 0.4253,
+      "step": 248
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.521309308141592e-05,
+      "loss": 0.4986,
+      "step": 249
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5173378141776569e-05,
+      "loss": 0.4427,
+      "step": 250
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5133551469565313e-05,
+      "loss": 0.4853,
+      "step": 251
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5093613924942837e-05,
+      "loss": 0.4006,
+      "step": 252
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.5053566370464416e-05,
+      "loss": 0.393,
+      "step": 253
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.5013409671061267e-05,
+      "loss": 0.3967,
+      "step": 254
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4973144694021874e-05,
+      "loss": 0.4475,
+      "step": 255
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4932772308973267e-05,
+      "loss": 0.4239,
+      "step": 256
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4892293387862221e-05,
+      "loss": 0.3879,
+      "step": 257
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4851708804936449e-05,
+      "loss": 0.3502,
+      "step": 258
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4811019436725684e-05,
+      "loss": 0.3811,
+      "step": 259
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4770226162022799e-05,
+      "loss": 0.4026,
+      "step": 260
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.472932986186477e-05,
+      "loss": 0.4133,
+      "step": 261
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4688331419513693e-05,
+      "loss": 0.3756,
+      "step": 262
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4647231720437687e-05,
+      "loss": 0.4085,
+      "step": 263
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4606031652291772e-05,
+      "loss": 0.4229,
+      "step": 264
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4564732104898702e-05,
+      "loss": 0.4504,
+      "step": 265
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4523333970229741e-05,
+      "loss": 0.3545,
+      "step": 266
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4481838142385403e-05,
+      "loss": 0.4073,
+      "step": 267
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4440245517576141e-05,
+      "loss": 0.3949,
+      "step": 268
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4398556994102996e-05,
+      "loss": 0.322,
+      "step": 269
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4356773472338174e-05,
+      "loss": 0.4292,
+      "step": 270
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4314895854705641e-05,
+      "loss": 0.3601,
+      "step": 271
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4272925045661583e-05,
+      "loss": 0.3876,
+      "step": 272
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4230861951674914e-05,
+      "loss": 0.4648,
+      "step": 273
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4188707481207677e-05,
+      "loss": 0.503,
+      "step": 274
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4146462544695428e-05,
+      "loss": 0.4014,
+      "step": 275
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.410412805452757e-05,
+      "loss": 0.4109,
+      "step": 276
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4061704925027653e-05,
+      "loss": 0.4546,
+      "step": 277
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4019194072433626e-05,
+      "loss": 0.3948,
+      "step": 278
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3976596414878044e-05,
+      "loss": 0.3586,
+      "step": 279
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.393391287236824e-05,
+      "loss": 0.3491,
+      "step": 280
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3891144366766457e-05,
+      "loss": 0.4553,
+      "step": 281
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3848291821769944e-05,
+      "loss": 0.3746,
+      "step": 282
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.380535616289099e-05,
+      "loss": 0.4339,
+      "step": 283
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3762338317436948e-05,
+      "loss": 0.397,
+      "step": 284
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3719239214490203e-05,
+      "loss": 0.3991,
+      "step": 285
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3676059784888112e-05,
+      "loss": 0.338,
+      "step": 286
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.363280096120289e-05,
+      "loss": 0.4,
+      "step": 287
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.358946367772148e-05,
+      "loss": 0.416,
+      "step": 288
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 0.4365,
+      "step": 289
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3502557476970339e-05,
+      "loss": 0.457,
+      "step": 290
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3458990436666313e-05,
+      "loss": 0.3775,
+      "step": 291
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3415348690456955e-05,
+      "loss": 0.3901,
+      "step": 292
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3371633180899417e-05,
+      "loss": 0.4182,
+      "step": 293
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3327844852143956e-05,
+      "loss": 0.392,
+      "step": 294
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3283984649913552e-05,
+      "loss": 0.4251,
+      "step": 295
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3240053521483483e-05,
+      "loss": 0.5068,
+      "step": 296
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3196052415660856e-05,
+      "loss": 0.4059,
+      "step": 297
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.3151982282764126e-05,
+      "loss": 0.4494,
+      "step": 298
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.3107844074602566e-05,
+      "loss": 0.4198,
+      "step": 299
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.3063638744455713e-05,
+      "loss": 0.4468,
+      "step": 300
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.3019367247052781e-05,
+      "loss": 0.4488,
+      "step": 301
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.297503053855203e-05,
+      "loss": 0.4342,
+      "step": 302
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2930629576520133e-05,
+      "loss": 0.3845,
+      "step": 303
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2886165319911474e-05,
+      "loss": 0.491,
+      "step": 304
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2841638729047463e-05,
+      "loss": 0.4247,
+      "step": 305
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2797050765595767e-05,
+      "loss": 0.3906,
+      "step": 306
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2752402392549556e-05,
+      "loss": 0.4656,
+      "step": 307
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2707694574206712e-05,
+      "loss": 0.4146,
+      "step": 308
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2662928276148985e-05,
+      "loss": 0.3697,
+      "step": 309
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2618104465221148e-05,
+      "loss": 0.4642,
+      "step": 310
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2573224109510112e-05,
+      "loss": 0.4204,
+      "step": 311
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2528288178324029e-05,
+      "loss": 0.4163,
+      "step": 312
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2483297642171332e-05,
+      "loss": 0.4105,
+      "step": 313
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2438253472739805e-05,
+      "loss": 0.4201,
+      "step": 314
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2393156642875579e-05,
+      "loss": 0.3702,
+      "step": 315
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.234800812656212e-05,
+      "loss": 0.3873,
+      "step": 316
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.23028088988992e-05,
+      "loss": 0.358,
+      "step": 317
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2257559936081833e-05,
+      "loss": 0.3724,
+      "step": 318
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2212262215379199e-05,
+      "loss": 0.4344,
+      "step": 319
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2166916715113521e-05,
+      "loss": 0.3401,
+      "step": 320
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2121524414638958e-05,
+      "loss": 0.409,
+      "step": 321
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.207608629432043e-05,
+      "loss": 0.3675,
+      "step": 322
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2030603335512467e-05,
+      "loss": 0.4337,
+      "step": 323
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1985076520537995e-05,
+      "loss": 0.4217,
+      "step": 324
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1939506832667129e-05,
+      "loss": 0.4079,
+      "step": 325
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1893895256095937e-05,
+      "loss": 0.4238,
+      "step": 326
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1848242775925188e-05,
+      "loss": 0.3728,
+      "step": 327
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.180255037813906e-05,
+      "loss": 0.3322,
+      "step": 328
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1756819049583861e-05,
+      "loss": 0.3924,
+      "step": 329
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1711049777946717e-05,
+      "loss": 0.359,
+      "step": 330
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.166524355173422e-05,
+      "loss": 0.4221,
+      "step": 331
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1619401360251104e-05,
+      "loss": 0.3991,
+      "step": 332
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1573524193578863e-05,
+      "loss": 0.3751,
+      "step": 333
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1527613042554368e-05,
+      "loss": 0.418,
+      "step": 334
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1481668898748474e-05,
+      "loss": 0.3781,
+      "step": 335
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1435692754444604e-05,
+      "loss": 0.4351,
+      "step": 336
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1389685602617302e-05,
+      "loss": 0.3812,
+      "step": 337
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.134364843691082e-05,
+      "loss": 0.4037,
+      "step": 338
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1297582251617618e-05,
+      "loss": 0.3658,
+      "step": 339
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1251488041656929e-05,
+      "loss": 0.314,
+      "step": 340
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1205366802553231e-05,
+      "loss": 0.413,
+      "step": 341
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.1159219530414786e-05,
+      "loss": 0.3253,
+      "step": 342
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.1113047221912097e-05,
+      "loss": 0.4194,
+      "step": 343
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.1066850874256387e-05,
+      "loss": 0.3512,
+      "step": 344
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.1020631485178084e-05,
+      "loss": 0.3433,
+      "step": 345
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0974390052905238e-05,
+      "loss": 0.3814,
+      "step": 346
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0928127576141992e-05,
+      "loss": 0.3646,
+      "step": 347
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0881845054046988e-05,
+      "loss": 0.3764,
+      "step": 348
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0835543486211815e-05,
+      "loss": 0.3887,
+      "step": 349
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0789223872639385e-05,
+      "loss": 0.3568,
+      "step": 350
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0742887213722372e-05,
+      "loss": 0.4169,
+      "step": 351
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0696534510221575e-05,
+      "loss": 0.3632,
+      "step": 352
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.065016676324433e-05,
+      "loss": 0.3772,
+      "step": 353
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0603784974222862e-05,
+      "loss": 0.3774,
+      "step": 354
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0557390144892684e-05,
+      "loss": 0.4081,
+      "step": 355
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0510983277270945e-05,
+      "loss": 0.4279,
+      "step": 356
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0464565373634784e-05,
+      "loss": 0.3909,
+      "step": 357
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0418137436499699e-05,
+      "loss": 0.4582,
+      "step": 358
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0371700468597886e-05,
+      "loss": 0.3604,
+      "step": 359
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0325255472856586e-05,
+      "loss": 0.4578,
+      "step": 360
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0278803452376416e-05,
+      "loss": 0.344,
+      "step": 361
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0232345410409718e-05,
+      "loss": 0.423,
+      "step": 362
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.018588235033888e-05,
+      "loss": 0.4646,
+      "step": 363
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.0139415275654671e-05,
+      "loss": 0.4006,
+      "step": 364
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.0092945189934558e-05,
+      "loss": 0.3914,
+      "step": 365
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.0046473096821047e-05,
+      "loss": 0.4569,
+      "step": 366
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1e-05,
+      "loss": 0.4319,
+      "step": 367
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.953526903178956e-06,
+      "loss": 0.3823,
+      "step": 368
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.907054810065446e-06,
+      "loss": 0.3727,
+      "step": 369
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.860584724345334e-06,
+      "loss": 0.4394,
+      "step": 370
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.81411764966112e-06,
+      "loss": 0.3997,
+      "step": 371
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.767654589590284e-06,
+      "loss": 0.3709,
+      "step": 372
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.721196547623585e-06,
+      "loss": 0.3902,
+      "step": 373
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.674744527143419e-06,
+      "loss": 0.4024,
+      "step": 374
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.628299531402118e-06,
+      "loss": 0.3344,
+      "step": 375
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.581862563500305e-06,
+      "loss": 0.4133,
+      "step": 376
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.535434626365221e-06,
+      "loss": 0.3944,
+      "step": 377
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.489016722729059e-06,
+      "loss": 0.4255,
+      "step": 378
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.442609855107317e-06,
+      "loss": 0.4397,
+      "step": 379
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.39621502577714e-06,
+      "loss": 0.4233,
+      "step": 380
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.349833236755675e-06,
+      "loss": 0.406,
+      "step": 381
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.30346548977843e-06,
+      "loss": 0.3947,
+      "step": 382
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.257112786277631e-06,
+      "loss": 0.3919,
+      "step": 383
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.21077612736062e-06,
+      "loss": 0.3988,
+      "step": 384
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.164456513788186e-06,
+      "loss": 0.4032,
+      "step": 385
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.118154945953015e-06,
+      "loss": 0.3705,
+      "step": 386
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.07187242385801e-06,
+      "loss": 0.4593,
+      "step": 387
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.025609947094765e-06,
+      "loss": 0.3875,
+      "step": 388
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.979368514821917e-06,
+      "loss": 0.39,
+      "step": 389
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.933149125743615e-06,
+      "loss": 0.3489,
+      "step": 390
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.88695277808791e-06,
+      "loss": 0.4281,
+      "step": 391
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.840780469585215e-06,
+      "loss": 0.3569,
+      "step": 392
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.79463319744677e-06,
+      "loss": 0.3989,
+      "step": 393
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.748511958343076e-06,
+      "loss": 0.4173,
+      "step": 394
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.702417748382384e-06,
+      "loss": 0.4769,
+      "step": 395
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.656351563089185e-06,
+      "loss": 0.4492,
+      "step": 396
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.610314397382701e-06,
+      "loss": 0.4701,
+      "step": 397
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.564307245555403e-06,
+      "loss": 0.3428,
+      "step": 398
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.51833110125153e-06,
+      "loss": 0.3531,
+      "step": 399
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.472386957445635e-06,
+      "loss": 0.4825,
+      "step": 400
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.426475806421139e-06,
+      "loss": 0.4124,
+      "step": 401
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.380598639748898e-06,
+      "loss": 0.4105,
+      "step": 402
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.334756448265782e-06,
+      "loss": 0.4428,
+      "step": 403
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.288950222053287e-06,
+      "loss": 0.3888,
+      "step": 404
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.243180950416142e-06,
+      "loss": 0.4337,
+      "step": 405
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.197449621860944e-06,
+      "loss": 0.3817,
+      "step": 406
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.151757224074815e-06,
+      "loss": 0.3433,
+      "step": 407
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.106104743904065e-06,
+      "loss": 0.389,
+      "step": 408
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.060493167332874e-06,
+      "loss": 0.4383,
+      "step": 409
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.014923479462007e-06,
+      "loss": 0.4008,
+      "step": 410
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.969396664487534e-06,
+      "loss": 0.4414,
+      "step": 411
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.923913705679573e-06,
+      "loss": 0.4482,
+      "step": 412
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.878475585361045e-06,
+      "loss": 0.3578,
+      "step": 413
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.833083284886484e-06,
+      "loss": 0.3494,
+      "step": 414
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.787737784620803e-06,
+      "loss": 0.4014,
+      "step": 415
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.74244006391817e-06,
+      "loss": 0.4584,
+      "step": 416
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.697191101100802e-06,
+      "loss": 0.4022,
+      "step": 417
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.651991873437884e-06,
+      "loss": 0.4109,
+      "step": 418
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.606843357124426e-06,
+      "loss": 0.3888,
+      "step": 419
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.561746527260197e-06,
+      "loss": 0.4091,
+      "step": 420
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.516702357828672e-06,
+      "loss": 0.4448,
+      "step": 421
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.471711821675973e-06,
+      "loss": 0.3347,
+      "step": 422
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.42677589048989e-06,
+      "loss": 0.3981,
+      "step": 423
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.381895534778852e-06,
+      "loss": 0.3709,
+      "step": 424
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.337071723851018e-06,
+      "loss": 0.3948,
+      "step": 425
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.292305425793291e-06,
+      "loss": 0.4119,
+      "step": 426
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.247597607450446e-06,
+      "loss": 0.3571,
+      "step": 427
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.2029492344042395e-06,
+      "loss": 0.4062,
+      "step": 428
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.1583612709525405e-06,
+      "loss": 0.3755,
+      "step": 429
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.113834680088527e-06,
+      "loss": 0.3411,
+      "step": 430
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.06937042347987e-06,
+      "loss": 0.3953,
+      "step": 431
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.024969461447973e-06,
+      "loss": 0.366,
+      "step": 432
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.980632752947221e-06,
+      "loss": 0.364,
+      "step": 433
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.936361255544288e-06,
+      "loss": 0.4228,
+      "step": 434
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.892155925397437e-06,
+      "loss": 0.4475,
+      "step": 435
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.848017717235878e-06,
+      "loss": 0.4409,
+      "step": 436
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.803947584339148e-06,
+      "loss": 0.3453,
+      "step": 437
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.7599464785165195e-06,
+      "loss": 0.3838,
+      "step": 438
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.716015350086449e-06,
+      "loss": 0.4468,
+      "step": 439
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.672155147856046e-06,
+      "loss": 0.3543,
+      "step": 440
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.628366819100586e-06,
+      "loss": 0.3939,
+      "step": 441
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.584651309543049e-06,
+      "loss": 0.4118,
+      "step": 442
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.54100956333369e-06,
+      "loss": 0.4251,
+      "step": 443
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.497442523029663e-06,
+      "loss": 0.4066,
+      "step": 444
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.453951129574644e-06,
+      "loss": 0.3796,
+      "step": 445
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.410536322278523e-06,
+      "loss": 0.3173,
+      "step": 446
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.3671990387971096e-06,
+      "loss": 0.4103,
+      "step": 447
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.32394021511189e-06,
+      "loss": 0.3294,
+      "step": 448
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.280760785509802e-06,
+      "loss": 0.2833,
+      "step": 449
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.237661682563055e-06,
+      "loss": 0.4353,
+      "step": 450
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.194643837109015e-06,
+      "loss": 0.4327,
+      "step": 451
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.151708178230057e-06,
+      "loss": 0.4058,
+      "step": 452
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.108855633233546e-06,
+      "loss": 0.3903,
+      "step": 453
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.066087127631761e-06,
+      "loss": 0.3309,
+      "step": 454
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 6.0234035851219604e-06,
+      "loss": 0.4039,
+      "step": 455
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.9808059275663775e-06,
+      "loss": 0.3229,
+      "step": 456
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.93829507497235e-06,
+      "loss": 0.3629,
+      "step": 457
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.895871945472434e-06,
+      "loss": 0.3984,
+      "step": 458
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.853537455304575e-06,
+      "loss": 0.3687,
+      "step": 459
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.811292518792324e-06,
+      "loss": 0.4559,
+      "step": 460
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.769138048325087e-06,
+      "loss": 0.3706,
+      "step": 461
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.72707495433842e-06,
+      "loss": 0.3619,
+      "step": 462
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.685104145294364e-06,
+      "loss": 0.3548,
+      "step": 463
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.643226527661825e-06,
+      "loss": 0.3747,
+      "step": 464
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.601443005897012e-06,
+      "loss": 0.3947,
+      "step": 465
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.55975448242386e-06,
+      "loss": 0.3825,
+      "step": 466
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.5181618576146e-06,
+      "loss": 0.3305,
+      "step": 467
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.476666029770259e-06,
+      "loss": 0.3734,
+      "step": 468
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.435267895101303e-06,
+      "loss": 0.3654,
+      "step": 469
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.393968347708233e-06,
+      "loss": 0.2649,
+      "step": 470
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.352768279562315e-06,
+      "loss": 0.1648,
+      "step": 471
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.311668580486311e-06,
+      "loss": 0.1886,
+      "step": 472
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.270670138135234e-06,
+      "loss": 0.1455,
+      "step": 473
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.229773837977208e-06,
+      "loss": 0.1814,
+      "step": 474
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.188980563274315e-06,
+      "loss": 0.1445,
+      "step": 475
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.148291195063555e-06,
+      "loss": 0.1541,
+      "step": 476
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.107706612137776e-06,
+      "loss": 0.1464,
+      "step": 477
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.067227691026737e-06,
+      "loss": 0.1418,
+      "step": 478
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 5.026855305978129e-06,
+      "loss": 0.1584,
+      "step": 479
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.986590328938734e-06,
+      "loss": 0.179,
+      "step": 480
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.946433629535585e-06,
+      "loss": 0.1933,
+      "step": 481
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.906386075057164e-06,
+      "loss": 0.162,
+      "step": 482
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.866448530434692e-06,
+      "loss": 0.1683,
+      "step": 483
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.826621858223431e-06,
+      "loss": 0.1719,
+      "step": 484
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.786906918584083e-06,
+      "loss": 0.1477,
+      "step": 485
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.747304569264179e-06,
+      "loss": 0.1379,
+      "step": 486
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.707815665579569e-06,
+      "loss": 0.1305,
+      "step": 487
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.668441060395958e-06,
+      "loss": 0.1361,
+      "step": 488
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.629181604110464e-06,
+      "loss": 0.1265,
+      "step": 489
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.5900381446332854e-06,
+      "loss": 0.1801,
+      "step": 490
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.551011527369348e-06,
+      "loss": 0.1571,
+      "step": 491
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.512102595200073e-06,
+      "loss": 0.141,
+      "step": 492
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.4733121884651665e-06,
+      "loss": 0.163,
+      "step": 493
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.434641144944464e-06,
+      "loss": 0.1676,
+      "step": 494
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.3960902998398524e-06,
+      "loss": 0.1739,
+      "step": 495
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.357660485757211e-06,
+      "loss": 0.1653,
+      "step": 496
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.319352532688444e-06,
+      "loss": 0.1626,
+      "step": 497
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.281167267993541e-06,
+      "loss": 0.1511,
+      "step": 498
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.243105516382732e-06,
+      "loss": 0.1153,
+      "step": 499
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.205168099898652e-06,
+      "loss": 0.1379,
+      "step": 500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.167355837898585e-06,
+      "loss": 0.1297,
+      "step": 501
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.129669547036798e-06,
+      "loss": 0.1431,
+      "step": 502
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.092110041246865e-06,
+      "loss": 0.1109,
+      "step": 503
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.054678131724128e-06,
+      "loss": 0.1187,
+      "step": 504
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 4.017374626908125e-06,
+      "loss": 0.1856,
+      "step": 505
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.980200332465189e-06,
+      "loss": 0.1316,
+      "step": 506
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.943156051271003e-06,
+      "loss": 0.1143,
+      "step": 507
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.906242583393279e-06,
+      "loss": 0.1162,
+      "step": 508
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.8694607260744745e-06,
+      "loss": 0.1558,
+      "step": 509
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.832811273714569e-06,
+      "loss": 0.107,
+      "step": 510
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.7962950178539282e-06,
+      "loss": 0.1239,
+      "step": 511
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.7599127471561746e-06,
+      "loss": 0.141,
+      "step": 512
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.7236652473911817e-06,
+      "loss": 0.1367,
+      "step": 513
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.687553301418092e-06,
+      "loss": 0.1409,
+      "step": 514
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.651577689168405e-06,
+      "loss": 0.1405,
+      "step": 515
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.6157391876291535e-06,
+      "loss": 0.1343,
+      "step": 516
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.580038570826093e-06,
+      "loss": 0.1493,
+      "step": 517
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.5444766098070037e-06,
+      "loss": 0.1462,
+      "step": 518
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.509054072625031e-06,
+      "loss": 0.14,
+      "step": 519
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.473771724322108e-06,
+      "loss": 0.1457,
+      "step": 520
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.4386303269124142e-06,
+      "loss": 0.1498,
+      "step": 521
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.4036306393659324e-06,
+      "loss": 0.1735,
+      "step": 522
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.3687734175920505e-06,
+      "loss": 0.1287,
+      "step": 523
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.334059414423233e-06,
+      "loss": 0.1682,
+      "step": 524
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.299489379598777e-06,
+      "loss": 0.1804,
+      "step": 525
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.265064059748597e-06,
+      "loss": 0.1589,
+      "step": 526
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.2307841983771182e-06,
+      "loss": 0.1428,
+      "step": 527
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.196650535847201e-06,
+      "loss": 0.1431,
+      "step": 528
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.162663809364178e-06,
+      "loss": 0.1294,
+      "step": 529
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.1288247529599035e-06,
+      "loss": 0.1373,
+      "step": 530
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.095134097476904e-06,
+      "loss": 0.1675,
+      "step": 531
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.061592570552623e-06,
+      "loss": 0.1602,
+      "step": 532
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 3.0282008966036647e-06,
+      "loss": 0.1776,
+      "step": 533
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.9949597968101883e-06,
+      "loss": 0.1608,
+      "step": 534
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.9618699891002843e-06,
+      "loss": 0.1943,
+      "step": 535
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.1459,
+      "step": 536
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.8961471052904855e-06,
+      "loss": 0.1249,
+      "step": 537
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.8635154486473935e-06,
+      "loss": 0.1058,
+      "step": 538
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.831037922970855e-06,
+      "loss": 0.1808,
+      "step": 539
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.798715229697592e-06,
+      "loss": 0.1406,
+      "step": 540
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.7665480669203383e-06,
+      "loss": 0.1745,
+      "step": 541
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.7345371293727306e-06,
+      "loss": 0.1375,
+      "step": 542
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.702683108414326e-06,
+      "loss": 0.1344,
+      "step": 543
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.6709866920156434e-06,
+      "loss": 0.1554,
+      "step": 544
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.639448564743328e-06,
+      "loss": 0.1234,
+      "step": 545
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.6080694077453663e-06,
+      "loss": 0.1719,
+      "step": 546
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.57684989873636e-06,
+      "loss": 0.1456,
+      "step": 547
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.545790711982897e-06,
+      "loss": 0.128,
+      "step": 548
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.514892518288988e-06,
+      "loss": 0.1508,
+      "step": 549
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.484155984981588e-06,
+      "loss": 0.1462,
+      "step": 550
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.4535817758961644e-06,
+      "loss": 0.117,
+      "step": 551
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.423170551362375e-06,
+      "loss": 0.1447,
+      "step": 552
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.3929229681898005e-06,
+      "loss": 0.1402,
+      "step": 553
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.3628396796537588e-06,
+      "loss": 0.1313,
+      "step": 554
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.332921335481205e-06,
+      "loss": 0.1748,
+      "step": 555
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.3031685818366844e-06,
+      "loss": 0.1387,
+      "step": 556
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.2735820613083837e-06,
+      "loss": 0.1872,
+      "step": 557
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.2441624128942496e-06,
+      "loss": 0.1656,
+      "step": 558
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.2149102719882044e-06,
+      "loss": 0.1874,
+      "step": 559
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.185826270366395e-06,
+      "loss": 0.1391,
+      "step": 560
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.156911036173568e-06,
+      "loss": 0.165,
+      "step": 561
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.1281651939094996e-06,
+      "loss": 0.1778,
+      "step": 562
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0995893644155007e-06,
+      "loss": 0.1456,
+      "step": 563
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0711841648610254e-06,
+      "loss": 0.143,
+      "step": 564
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0429502087303164e-06,
+      "loss": 0.1334,
+      "step": 565
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.0148881058091764e-06,
+      "loss": 0.1659,
+      "step": 566
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9869984621717888e-06,
+      "loss": 0.1135,
+      "step": 567
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.959281880167626e-06,
+      "loss": 0.1448,
+      "step": 568
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.931738958408457e-06,
+      "loss": 0.1865,
+      "step": 569
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.904370291755383e-06,
+      "loss": 0.1379,
+      "step": 570
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.8771764713060359e-06,
+      "loss": 0.1535,
+      "step": 571
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.8501580843817724e-06,
+      "loss": 0.1386,
+      "step": 572
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.8233157145150183e-06,
+      "loss": 0.155,
+      "step": 573
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.796649941436638e-06,
+      "loss": 0.1363,
+      "step": 574
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.7701613410634367e-06,
+      "loss": 0.1379,
+      "step": 575
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.7438504854857164e-06,
+      "loss": 0.1445,
+      "step": 576
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.717717942954914e-06,
+      "loss": 0.1618,
+      "step": 577
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6917642778713294e-06,
+      "loss": 0.129,
+      "step": 578
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6659900507719406e-06,
+      "loss": 0.1778,
+      "step": 579
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.6403958183182977e-06,
+      "loss": 0.1854,
+      "step": 580
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.614982133284495e-06,
+      "loss": 0.1292,
+      "step": 581
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.5897495445452338e-06,
+      "loss": 0.15,
+      "step": 582
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.5646985970639717e-06,
+      "loss": 0.1487,
+      "step": 583
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.5398298318811467e-06,
+      "loss": 0.131,
+      "step": 584
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.5151437861025032e-06,
+      "loss": 0.1523,
+      "step": 585
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4906409928874788e-06,
+      "loss": 0.152,
+      "step": 586
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.466321981437694e-06,
+      "loss": 0.1813,
+      "step": 587
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.4421872769855262e-06,
+      "loss": 0.1607,
+      "step": 588
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.4182374007827605e-06,
+      "loss": 0.146,
+      "step": 589
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.3944728700893395e-06,
+      "loss": 0.1594,
+      "step": 590
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.3708941981621814e-06,
+      "loss": 0.1139,
+      "step": 591
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.3475018942441055e-06,
+      "loss": 0.1454,
+      "step": 592
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.324296463552821e-06,
+      "loss": 0.2033,
+      "step": 593
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.3012784072700335e-06,
+      "loss": 0.1267,
+      "step": 594
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.2784482225306061e-06,
+      "loss": 0.137,
+      "step": 595
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.2558064024118177e-06,
+      "loss": 0.1498,
+      "step": 596
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.2333534359227383e-06,
+      "loss": 0.1589,
+      "step": 597
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.2110898079936394e-06,
+      "loss": 0.1616,
+      "step": 598
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1890159994655425e-06,
+      "loss": 0.1386,
+      "step": 599
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1671324870798195e-06,
+      "loss": 0.1585,
+      "step": 600
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.1454397434679022e-06,
+      "loss": 0.1269,
+      "step": 601
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.1239382371410713e-06,
+      "loss": 0.1359,
+      "step": 602
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.1026284324803493e-06,
+      "loss": 0.1192,
+      "step": 603
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.0815107897264555e-06,
+      "loss": 0.1424,
+      "step": 604
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.060585764969867e-06,
+      "loss": 0.1356,
+      "step": 605
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.039853810140987e-06,
+      "loss": 0.1317,
+      "step": 606
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.0193153730003603e-06,
+      "loss": 0.1435,
+      "step": 607
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.989708971290212e-07,
+      "loss": 0.1533,
+      "step": 608
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.788208219188932e-07,
+      "loss": 0.1429,
+      "step": 609
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.588655825633274e-07,
+      "loss": 0.1542,
+      "step": 610
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.391056100476736e-07,
+      "loss": 0.1616,
+      "step": 611
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.195413311399948e-07,
+      "loss": 0.1174,
+      "step": 612
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 9.001731683818338e-07,
+      "loss": 0.1189,
+      "step": 613
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.810015400790994e-07,
+      "loss": 0.1506,
+      "step": 614
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.620268602930271e-07,
+      "loss": 0.141,
+      "step": 615
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.432495388312345e-07,
+      "loss": 0.163,
+      "step": 616
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 8.246699812388714e-07,
+      "loss": 0.1604,
+      "step": 617
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 8.062885887898642e-07,
+      "loss": 0.1456,
+      "step": 618
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.881057584782448e-07,
+      "loss": 0.1496,
+      "step": 619
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.701218830095825e-07,
+      "loss": 0.1611,
+      "step": 620
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.523373507924947e-07,
+      "loss": 0.1322,
+      "step": 621
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 7.34752545930264e-07,
+      "loss": 0.1302,
+      "step": 622
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 7.17367848212539e-07,
+      "loss": 0.1238,
+      "step": 623
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 7.001836331071365e-07,
+      "loss": 0.1323,
+      "step": 624
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.83200271751927e-07,
+      "loss": 0.1152,
+      "step": 625
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.664181309468232e-07,
+      "loss": 0.1776,
+      "step": 626
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.498375731458529e-07,
+      "loss": 0.1557,
+      "step": 627
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.334589564493343e-07,
+      "loss": 0.1417,
+      "step": 628
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.17282634596148e-07,
+      "loss": 0.136,
+      "step": 629
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.013089569560826e-07,
+      "loss": 0.1206,
+      "step": 630
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.85538268522301e-07,
+      "loss": 0.1803,
+      "step": 631
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.699709099038852e-07,
+      "loss": 0.1088,
+      "step": 632
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.546072173184791e-07,
+      "loss": 0.1331,
+      "step": 633
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.394475225850338e-07,
+      "loss": 0.1435,
+      "step": 634
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.244921531166247e-07,
+      "loss": 0.1254,
+      "step": 635
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 5.097414319134042e-07,
+      "loss": 0.1448,
+      "step": 636
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.951956775556e-07,
+      "loss": 0.1569,
+      "step": 637
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.808552041966608e-07,
+      "loss": 0.1358,
+      "step": 638
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.667203215564431e-07,
+      "loss": 0.1435,
+      "step": 639
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.5279133491454406e-07,
+      "loss": 0.1346,
+      "step": 640
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.3906854510370245e-07,
+      "loss": 0.149,
+      "step": 641
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.255522485032959e-07,
+      "loss": 0.1687,
+      "step": 642
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.1224273703294515e-07,
+      "loss": 0.1358,
+      "step": 643
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.991402981462045e-07,
+      "loss": 0.1531,
+      "step": 644
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.862452148243623e-07,
+      "loss": 0.1652,
+      "step": 645
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.735577655703171e-07,
+      "loss": 0.1416,
+      "step": 646
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.610782244025768e-07,
+      "loss": 0.1496,
+      "step": 647
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.488068608493245e-07,
+      "loss": 0.1486,
+      "step": 648
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.367439399426087e-07,
+      "loss": 0.1397,
+      "step": 649
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.2488972221262125e-07,
+      "loss": 0.1442,
+      "step": 650
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.132444636820575e-07,
+      "loss": 0.1545,
+      "step": 651
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.018084158606005e-07,
+      "loss": 0.1433,
+      "step": 652
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.905818257394799e-07,
+      "loss": 0.1841,
+      "step": 653
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.79564935786143e-07,
+      "loss": 0.148,
+      "step": 654
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.687579839390153e-07,
+      "loss": 0.1281,
+      "step": 655
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.5816120360236176e-07,
+      "loss": 0.1471,
+      "step": 656
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.4777482364124695e-07,
+      "loss": 0.1107,
+      "step": 657
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.375990683765894e-07,
+      "loss": 0.158,
+      "step": 658
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.2763415758032316e-07,
+      "loss": 0.148,
+      "step": 659
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.1788030647064363e-07,
+      "loss": 0.1229,
+      "step": 660
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.0833772570736376e-07,
+      "loss": 0.1347,
+      "step": 661
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.9900662138736204e-07,
+      "loss": 0.138,
+      "step": 662
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.8988719504013375e-07,
+      "loss": 0.1785,
+      "step": 663
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.809796436234379e-07,
+      "loss": 0.1733,
+      "step": 664
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.7228415951904165e-07,
+      "loss": 0.1038,
+      "step": 665
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.6380093052856482e-07,
+      "loss": 0.144,
+      "step": 666
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.5553013986942645e-07,
+      "loss": 0.1385,
+      "step": 667
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.474719661708901e-07,
+      "loss": 0.1455,
+      "step": 668
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.3962658347019819e-07,
+      "loss": 0.1549,
+      "step": 669
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.3199416120881714e-07,
+      "loss": 0.1426,
+      "step": 670
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.245748642287814e-07,
+      "loss": 0.1548,
+      "step": 671
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.1736885276912747e-07,
+      "loss": 0.1268,
+      "step": 672
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.103762824624377e-07,
+      "loss": 0.1476,
+      "step": 673
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.0359730433147308e-07,
+      "loss": 0.1396,
+      "step": 674
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 9.70320647859213e-08,
+      "loss": 0.1452,
+      "step": 675
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 9.068070561922382e-08,
+      "loss": 0.1542,
+      "step": 676
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 8.454336400552154e-08,
+      "loss": 0.1389,
+      "step": 677
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.862017249668507e-08,
+      "loss": 0.1681,
+      "step": 678
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.291125901946027e-08,
+      "loss": 0.1092,
+      "step": 679
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 6.741674687269828e-08,
+      "loss": 0.1285,
+      "step": 680
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 6.21367547246976e-08,
+      "loss": 0.097,
+      "step": 681
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.70713966106351e-08,
+      "loss": 0.1334,
+      "step": 682
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.2220781930111263e-08,
+      "loss": 0.1443,
+      "step": 683
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.758501544477767e-08,
+      "loss": 0.1253,
+      "step": 684
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.316419727608434e-08,
+      "loss": 0.1677,
+      "step": 685
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.895842290311147e-08,
+      "loss": 0.1542,
+      "step": 686
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.4967783160507753e-08,
+      "loss": 0.1224,
+      "step": 687
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 3.1192364236528606e-08,
+      "loss": 0.1057,
+      "step": 688
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.763224767117767e-08,
+      "loss": 0.1408,
+      "step": 689
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 2.4287510354441547e-08,
+      "loss": 0.1383,
+      "step": 690
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 2.115822452463223e-08,
+      "loss": 0.1298,
+      "step": 691
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.824445776682504e-08,
+      "loss": 0.1436,
+      "step": 692
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.554627301140199e-08,
+      "loss": 0.1469,
+      "step": 693
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.3063728532686225e-08,
+      "loss": 0.1431,
+      "step": 694
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.0796877947691909e-08,
+      "loss": 0.144,
+      "step": 695
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 8.745770214959592e-09,
+      "loss": 0.1355,
+      "step": 696
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 6.910449633501515e-09,
+      "loss": 0.1436,
+      "step": 697
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.290955841843471e-09,
+      "loss": 0.1425,
+      "step": 698
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 3.887323817173272e-09,
+      "loss": 0.1147,
+      "step": 699
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.699583874578027e-09,
+      "loss": 0.1229,
+      "step": 700
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.7277616663946562e-09,
+      "loss": 0.1241,
+      "step": 701
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 9.718781816536738e-10,
+      "loss": 0.1708,
+      "step": 702
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 4.319497456273247e-10,
+      "loss": 0.1162,
+      "step": 703
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.0798801947764503e-10,
+      "loss": 0.1337,
+      "step": 704
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1004,
+      "step": 705
+    },
+    {
+      "epoch": 3.0,
+      "step": 705,
+      "total_flos": 295225314508800.0,
+      "train_loss": 0.46274450019741736,
+      "train_runtime": 35730.3838,
+      "train_samples_per_second": 1.259,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "max_steps": 705,
+  "num_train_epochs": 3,
+  "total_flos": 295225314508800.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b050710e6d2896b07c058a1916fbd2c47e8408fef3ad91774f293a9cf735f15d
+size 5627