init

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "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-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550cb75ef521cf3a6e0fee951f740b95561de7a9f4f718cac46ed0d44c04ded9
+size 9878004434

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5981e914fe3936a1fc143c682c2ff7c1380144fb619d25814bb91d5472217d3f
+size 9894799542

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed319ee5c7ca784e6ee6f9feecc4d277ea0e1ea706a3e26e0cf76c73ba13a02b
+size 7181006073

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953699328
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "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": 512,
+  "pad_token": null,
+  "padding_side": "right",
+  "special_tokens_map_file": "/home/cs2175/.cache/huggingface/hub/models--meta-llama--Llama-2-7b-chat-hf/snapshots/08751db2aca9bf2f7f80d2e516117a53d7450235/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,2905 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 29.767441860465116,
+  "global_step": 480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 2.1574,
+      "step": 1
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 2.1101,
+      "step": 2
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.074,
+      "step": 3
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 1.9878,
+      "step": 4
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.5101,
+      "step": 5
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3858,
+      "step": 6
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 1.1866,
+      "step": 7
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 1.0788,
+      "step": 8
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.2e-05,
+      "loss": 0.8755,
+      "step": 9
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8617,
+      "step": 10
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.8315,
+      "step": 11
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.8335,
+      "step": 12
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.7985,
+      "step": 13
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.799,
+      "step": 14
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2e-05,
+      "loss": 0.722,
+      "step": 15
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.999977177553799e-05,
+      "loss": 0.7152,
+      "step": 16
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.9999087112569246e-05,
+      "loss": 0.6966,
+      "step": 17
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.9997946042345128e-05,
+      "loss": 0.5921,
+      "step": 18
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.9996348616949673e-05,
+      "loss": 0.5473,
+      "step": 19
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.999429490929718e-05,
+      "loss": 0.5623,
+      "step": 20
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.9991785013128922e-05,
+      "loss": 0.5566,
+      "step": 21
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.998881904300884e-05,
+      "loss": 0.5882,
+      "step": 22
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.998539713431832e-05,
+      "loss": 0.5511,
+      "step": 23
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.998151944325001e-05,
+      "loss": 0.5052,
+      "step": 24
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.9977186146800707e-05,
+      "loss": 0.4874,
+      "step": 25
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.997239744276326e-05,
+      "loss": 0.5485,
+      "step": 26
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.996715354971755e-05,
+      "loss": 0.5021,
+      "step": 27
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.9961454707020515e-05,
+      "loss": 0.5273,
+      "step": 28
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.995530117479521e-05,
+      "loss": 0.4885,
+      "step": 29
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.994869323391895e-05,
+      "loss": 0.4381,
+      "step": 30
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.9941631186010496e-05,
+      "loss": 0.5024,
+      "step": 31
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.993411535341625e-05,
+      "loss": 0.4849,
+      "step": 32
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.9926146079195597e-05,
+      "loss": 0.3431,
+      "step": 33
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.991772372710519e-05,
+      "loss": 0.2722,
+      "step": 34
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.990884868158239e-05,
+      "loss": 0.2383,
+      "step": 35
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.989952134772769e-05,
+      "loss": 0.2314,
+      "step": 36
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.988974215128625e-05,
+      "loss": 0.2271,
+      "step": 37
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.987951153862843e-05,
+      "loss": 0.2152,
+      "step": 38
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.9868829976729444e-05,
+      "loss": 0.2366,
+      "step": 39
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.985769795314804e-05,
+      "loss": 0.1924,
+      "step": 40
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.9846115976004234e-05,
+      "loss": 0.2124,
+      "step": 41
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.983408457395613e-05,
+      "loss": 0.2282,
+      "step": 42
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 1.9821604296175774e-05,
+      "loss": 0.2015,
+      "step": 43
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.9808675712324108e-05,
+      "loss": 0.2275,
+      "step": 44
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.9795299412524948e-05,
+      "loss": 0.2298,
+      "step": 45
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.2037,
+      "step": 46
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.9767206127731283e-05,
+      "loss": 0.2217,
+      "step": 47
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.975249042505174e-05,
+      "loss": 0.2081,
+      "step": 48
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 1.9737329570996098e-05,
+      "loss": 0.1353,
+      "step": 49
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 1.9721724257579907e-05,
+      "loss": 0.0982,
+      "step": 50
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 1.970567519710602e-05,
+      "loss": 0.0934,
+      "step": 51
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 1.968918312213207e-05,
+      "loss": 0.0848,
+      "step": 52
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 1.9672248785437053e-05,
+      "loss": 0.0722,
+      "step": 53
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 1.9654872959986936e-05,
+      "loss": 0.0873,
+      "step": 54
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 1.963705643889941e-05,
+      "loss": 0.0786,
+      "step": 55
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 1.961880003540766e-05,
+      "loss": 0.0693,
+      "step": 56
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 1.960010458282326e-05,
+      "loss": 0.0728,
+      "step": 57
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 1.958097093449813e-05,
+      "loss": 0.0767,
+      "step": 58
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.9561399963785586e-05,
+      "loss": 0.0873,
+      "step": 59
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 1.954139256400049e-05,
+      "loss": 0.0961,
+      "step": 60
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 1.9520949648378444e-05,
+      "loss": 0.0868,
+      "step": 61
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 1.9500072150034136e-05,
+      "loss": 0.0814,
+      "step": 62
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 1.947876102191873e-05,
+      "loss": 0.0829,
+      "step": 63
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 1.945701723677637e-05,
+      "loss": 0.0857,
+      "step": 64
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 1.9434841787099804e-05,
+      "loss": 0.06,
+      "step": 65
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 1.9412235685085034e-05,
+      "loss": 0.0401,
+      "step": 66
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 1.9389199962585156e-05,
+      "loss": 0.03,
+      "step": 67
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 1.9365735671063247e-05,
+      "loss": 0.0312,
+      "step": 68
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 1.9341843881544372e-05,
+      "loss": 0.0344,
+      "step": 69
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 1.9317525684566686e-05,
+      "loss": 0.0255,
+      "step": 70
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 1.9292782190131677e-05,
+      "loss": 0.031,
+      "step": 71
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 1.926761452765349e-05,
+      "loss": 0.033,
+      "step": 72
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 1.9242023845907362e-05,
+      "loss": 0.0361,
+      "step": 73
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 1.921601131297721e-05,
+      "loss": 0.0337,
+      "step": 74
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 1.918957811620231e-05,
+      "loss": 0.0301,
+      "step": 75
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 1.9162725462123074e-05,
+      "loss": 0.0346,
+      "step": 76
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.0289,
+      "step": 77
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 1.9107766703887764e-05,
+      "loss": 0.0358,
+      "step": 78
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 1.9079663108318304e-05,
+      "loss": 0.0399,
+      "step": 79
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 1.9051145072503216e-05,
+      "loss": 0.0366,
+      "step": 80
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 1.9022213898145176e-05,
+      "loss": 0.0236,
+      "step": 81
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 1.8992870905804535e-05,
+      "loss": 0.0133,
+      "step": 82
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 1.896311743483901e-05,
+      "loss": 0.0128,
+      "step": 83
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 1.893295484334259e-05,
+      "loss": 0.0137,
+      "step": 84
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 1.8902384508083518e-05,
+      "loss": 0.0113,
+      "step": 85
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 1.8871407824441453e-05,
+      "loss": 0.0156,
+      "step": 86
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 1.8840026206343786e-05,
+      "loss": 0.0202,
+      "step": 87
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 1.8808241086201106e-05,
+      "loss": 0.0152,
+      "step": 88
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 1.877605391484179e-05,
+      "loss": 0.0162,
+      "step": 89
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 1.8743466161445823e-05,
+      "loss": 0.0161,
+      "step": 90
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 1.8710479313477697e-05,
+      "loss": 0.0133,
+      "step": 91
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 1.867709487661854e-05,
+      "loss": 0.0154,
+      "step": 92
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 1.8643314374697377e-05,
+      "loss": 0.0203,
+      "step": 93
+    },
+    {
+      "epoch": 5.83,
+      "learning_rate": 1.8609139349621588e-05,
+      "loss": 0.0151,
+      "step": 94
+    },
+    {
+      "epoch": 5.89,
+      "learning_rate": 1.857457136130651e-05,
+      "loss": 0.0146,
+      "step": 95
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 1.853961198760426e-05,
+      "loss": 0.0199,
+      "step": 96
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 1.8504262824231675e-05,
+      "loss": 0.0148,
+      "step": 97
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 1.8468525484697527e-05,
+      "loss": 0.0069,
+      "step": 98
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 1.8432401600228823e-05,
+      "loss": 0.0073,
+      "step": 99
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 1.839589281969639e-05,
+      "loss": 0.0076,
+      "step": 100
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 1.8359000809539584e-05,
+      "loss": 0.008,
+      "step": 101
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 1.832172725369024e-05,
+      "loss": 0.0074,
+      "step": 102
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 1.8284073853495808e-05,
+      "loss": 0.0078,
+      "step": 103
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 1.8246042327641678e-05,
+      "loss": 0.0079,
+      "step": 104
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 1.8207634412072765e-05,
+      "loss": 0.0092,
+      "step": 105
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 1.816885185991424e-05,
+      "loss": 0.0093,
+      "step": 106
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 1.812969644139152e-05,
+      "loss": 0.0076,
+      "step": 107
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.0075,
+      "step": 108
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 1.8050274171170835e-05,
+      "loss": 0.0122,
+      "step": 109
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 1.8010010944693846e-05,
+      "loss": 0.0102,
+      "step": 110
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 1.7969382102129153e-05,
+      "loss": 0.0109,
+      "step": 111
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 1.7928389497975897e-05,
+      "loss": 0.0072,
+      "step": 112
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 1.7887035003337082e-05,
+      "loss": 0.0115,
+      "step": 113
+    },
+    {
+      "epoch": 7.07,
+      "learning_rate": 1.7845320505834176e-05,
+      "loss": 0.0077,
+      "step": 114
+    },
+    {
+      "epoch": 7.13,
+      "learning_rate": 1.780324790952092e-05,
+      "loss": 0.0047,
+      "step": 115
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 1.776081913479645e-05,
+      "loss": 0.005,
+      "step": 116
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 1.771803611831762e-05,
+      "loss": 0.0055,
+      "step": 117
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 1.767490081291062e-05,
+      "loss": 0.0043,
+      "step": 118
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 1.7631415187481818e-05,
+      "loss": 0.0056,
+      "step": 119
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 1.758758122692791e-05,
+      "loss": 0.005,
+      "step": 120
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 1.754340093204531e-05,
+      "loss": 0.0075,
+      "step": 121
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 1.749887631943882e-05,
+      "loss": 0.0068,
+      "step": 122
+    },
+    {
+      "epoch": 7.63,
+      "learning_rate": 1.74540094214296e-05,
+      "loss": 0.006,
+      "step": 123
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 1.740880228596237e-05,
+      "loss": 0.0067,
+      "step": 124
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 1.7363256976511972e-05,
+      "loss": 0.0056,
+      "step": 125
+    },
+    {
+      "epoch": 7.81,
+      "learning_rate": 1.7317375571989158e-05,
+      "loss": 0.0068,
+      "step": 126
+    },
+    {
+      "epoch": 7.88,
+      "learning_rate": 1.7271160166645695e-05,
+      "loss": 0.0061,
+      "step": 127
+    },
+    {
+      "epoch": 7.94,
+      "learning_rate": 1.722461286997879e-05,
+      "loss": 0.0061,
+      "step": 128
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.717773580663479e-05,
+      "loss": 0.0063,
+      "step": 129
+    },
+    {
+      "epoch": 8.06,
+      "learning_rate": 1.7130531116312202e-05,
+      "loss": 0.0032,
+      "step": 130
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 1.708300095366405e-05,
+      "loss": 0.003,
+      "step": 131
+    },
+    {
+      "epoch": 8.19,
+      "learning_rate": 1.703514748819948e-05,
+      "loss": 0.0046,
+      "step": 132
+    },
+    {
+      "epoch": 8.25,
+      "learning_rate": 1.6986972904184783e-05,
+      "loss": 0.0034,
+      "step": 133
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 1.693847940054366e-05,
+      "loss": 0.0033,
+      "step": 134
+    },
+    {
+      "epoch": 8.37,
+      "learning_rate": 1.688966919075687e-05,
+      "loss": 0.0028,
+      "step": 135
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 1.684054450276118e-05,
+      "loss": 0.0035,
+      "step": 136
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 1.6791107578847688e-05,
+      "loss": 0.0029,
+      "step": 137
+    },
+    {
+      "epoch": 8.56,
+      "learning_rate": 1.6741360675559475e-05,
+      "loss": 0.0056,
+      "step": 138
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.0047,
+      "step": 139
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 1.6640946027672395e-05,
+      "loss": 0.0052,
+      "step": 140
+    },
+    {
+      "epoch": 8.74,
+      "learning_rate": 1.659028286648932e-05,
+      "loss": 0.0045,
+      "step": 141
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 1.653931889255391e-05,
+      "loss": 0.0045,
+      "step": 142
+    },
+    {
+      "epoch": 8.87,
+      "learning_rate": 1.648805643211127e-05,
+      "loss": 0.0054,
+      "step": 143
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 1.6436497825030886e-05,
+      "loss": 0.0048,
+      "step": 144
+    },
+    {
+      "epoch": 8.99,
+      "learning_rate": 1.6384645424699835e-05,
+      "loss": 0.0056,
+      "step": 145
+    },
+    {
+      "epoch": 9.05,
+      "learning_rate": 1.6332501597915353e-05,
+      "loss": 0.0031,
+      "step": 146
+    },
+    {
+      "epoch": 9.12,
+      "learning_rate": 1.6280068724776795e-05,
+      "loss": 0.0026,
+      "step": 147
+    },
+    {
+      "epoch": 9.18,
+      "learning_rate": 1.622734919857702e-05,
+      "loss": 0.0022,
+      "step": 148
+    },
+    {
+      "epoch": 9.24,
+      "learning_rate": 1.617434542569313e-05,
+      "loss": 0.0023,
+      "step": 149
+    },
+    {
+      "epoch": 9.3,
+      "learning_rate": 1.612105982547663e-05,
+      "loss": 0.003,
+      "step": 150
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 1.6067494830143014e-05,
+      "loss": 0.0028,
+      "step": 151
+    },
+    {
+      "epoch": 9.43,
+      "learning_rate": 1.6013652884660723e-05,
+      "loss": 0.0028,
+      "step": 152
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 1.5959536446639572e-05,
+      "loss": 0.0025,
+      "step": 153
+    },
+    {
+      "epoch": 9.55,
+      "learning_rate": 1.5905147986218546e-05,
+      "loss": 0.0049,
+      "step": 154
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 1.5850489985953076e-05,
+      "loss": 0.0041,
+      "step": 155
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 1.57955649407017e-05,
+      "loss": 0.0039,
+      "step": 156
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 1.5740375357512198e-05,
+      "loss": 0.0041,
+      "step": 157
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 1.568492375550715e-05,
+      "loss": 0.0039,
+      "step": 158
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 1.562921266576898e-05,
+      "loss": 0.004,
+      "step": 159
+    },
+    {
+      "epoch": 9.92,
+      "learning_rate": 1.5573244631224364e-05,
+      "loss": 0.0049,
+      "step": 160
+    },
+    {
+      "epoch": 9.98,
+      "learning_rate": 1.5517022206528233e-05,
+      "loss": 0.0039,
+      "step": 161
+    },
+    {
+      "epoch": 10.05,
+      "learning_rate": 1.5460547957947105e-05,
+      "loss": 0.0029,
+      "step": 162
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 1.540382446324198e-05,
+      "loss": 0.0021,
+      "step": 163
+    },
+    {
+      "epoch": 10.17,
+      "learning_rate": 1.5346854311550673e-05,
+      "loss": 0.0018,
+      "step": 164
+    },
+    {
+      "epoch": 10.23,
+      "learning_rate": 1.5289640103269626e-05,
+      "loss": 0.0025,
+      "step": 165
+    },
+    {
+      "epoch": 10.29,
+      "learning_rate": 1.523218444993522e-05,
+      "loss": 0.0026,
+      "step": 166
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 1.5174489974104574e-05,
+      "loss": 0.0035,
+      "step": 167
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 1.5116559309235825e-05,
+      "loss": 0.0024,
+      "step": 168
+    },
+    {
+      "epoch": 10.48,
+      "learning_rate": 1.5058395099567935e-05,
+      "loss": 0.0042,
+      "step": 169
+    },
+    {
+      "epoch": 10.54,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0022,
+      "step": 170
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 1.4941376675970058e-05,
+      "loss": 0.0035,
+      "step": 171
+    },
+    {
+      "epoch": 10.67,
+      "learning_rate": 1.4882527803333422e-05,
+      "loss": 0.0032,
+      "step": 172
+    },
+    {
+      "epoch": 10.73,
+      "learning_rate": 1.4823456068240558e-05,
+      "loss": 0.0043,
+      "step": 173
+    },
+    {
+      "epoch": 10.79,
+      "learning_rate": 1.4764164167014451e-05,
+      "loss": 0.0029,
+      "step": 174
+    },
+    {
+      "epoch": 10.85,
+      "learning_rate": 1.4704654806027558e-05,
+      "loss": 0.005,
+      "step": 175
+    },
+    {
+      "epoch": 10.91,
+      "learning_rate": 1.4644930701578252e-05,
+      "loss": 0.0046,
+      "step": 176
+    },
+    {
+      "epoch": 10.98,
+      "learning_rate": 1.4584994579766865e-05,
+      "loss": 0.0044,
+      "step": 177
+    },
+    {
+      "epoch": 11.04,
+      "learning_rate": 1.4524849176371219e-05,
+      "loss": 0.0038,
+      "step": 178
+    },
+    {
+      "epoch": 11.1,
+      "learning_rate": 1.4464497236721779e-05,
+      "loss": 0.0028,
+      "step": 179
+    },
+    {
+      "epoch": 11.16,
+      "learning_rate": 1.4403941515576344e-05,
+      "loss": 0.0022,
+      "step": 180
+    },
+    {
+      "epoch": 11.22,
+      "learning_rate": 1.4343184776994288e-05,
+      "loss": 0.0017,
+      "step": 181
+    },
+    {
+      "epoch": 11.29,
+      "learning_rate": 1.4282229794210404e-05,
+      "loss": 0.0049,
+      "step": 182
+    },
+    {
+      "epoch": 11.35,
+      "learning_rate": 1.422107934950832e-05,
+      "loss": 0.0025,
+      "step": 183
+    },
+    {
+      "epoch": 11.41,
+      "learning_rate": 1.415973623409351e-05,
+      "loss": 0.0034,
+      "step": 184
+    },
+    {
+      "epoch": 11.47,
+      "learning_rate": 1.4098203247965876e-05,
+      "loss": 0.0029,
+      "step": 185
+    },
+    {
+      "epoch": 11.53,
+      "learning_rate": 1.4036483199791949e-05,
+      "loss": 0.0024,
+      "step": 186
+    },
+    {
+      "epoch": 11.6,
+      "learning_rate": 1.3974578906776683e-05,
+      "loss": 0.0033,
+      "step": 187
+    },
+    {
+      "epoch": 11.66,
+      "learning_rate": 1.3912493194534876e-05,
+      "loss": 0.0033,
+      "step": 188
+    },
+    {
+      "epoch": 11.72,
+      "learning_rate": 1.3850228896962178e-05,
+      "loss": 0.003,
+      "step": 189
+    },
+    {
+      "epoch": 11.78,
+      "learning_rate": 1.3787788856105762e-05,
+      "loss": 0.0026,
+      "step": 190
+    },
+    {
+      "epoch": 11.84,
+      "learning_rate": 1.3725175922034566e-05,
+      "loss": 0.0037,
+      "step": 191
+    },
+    {
+      "epoch": 11.91,
+      "learning_rate": 1.366239295270923e-05,
+      "loss": 0.004,
+      "step": 192
+    },
+    {
+      "epoch": 11.97,
+      "learning_rate": 1.3599442813851633e-05,
+      "loss": 0.0036,
+      "step": 193
+    },
+    {
+      "epoch": 12.03,
+      "learning_rate": 1.3536328378814094e-05,
+      "loss": 0.0029,
+      "step": 194
+    },
+    {
+      "epoch": 12.09,
+      "learning_rate": 1.3473052528448203e-05,
+      "loss": 0.0022,
+      "step": 195
+    },
+    {
+      "epoch": 12.16,
+      "learning_rate": 1.3409618150973349e-05,
+      "loss": 0.0033,
+      "step": 196
+    },
+    {
+      "epoch": 12.22,
+      "learning_rate": 1.334602814184486e-05,
+      "loss": 0.0022,
+      "step": 197
+    },
+    {
+      "epoch": 12.28,
+      "learning_rate": 1.3282285403621864e-05,
+      "loss": 0.0019,
+      "step": 198
+    },
+    {
+      "epoch": 12.34,
+      "learning_rate": 1.3218392845834789e-05,
+      "loss": 0.0016,
+      "step": 199
+    },
+    {
+      "epoch": 12.4,
+      "learning_rate": 1.3154353384852559e-05,
+      "loss": 0.0021,
+      "step": 200
+    },
+    {
+      "epoch": 12.47,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.0026,
+      "step": 201
+    },
+    {
+      "epoch": 12.53,
+      "learning_rate": 1.3025845452171808e-05,
+      "loss": 0.0022,
+      "step": 202
+    },
+    {
+      "epoch": 12.59,
+      "learning_rate": 1.2961382846204056e-05,
+      "loss": 0.0027,
+      "step": 203
+    },
+    {
+      "epoch": 12.65,
+      "learning_rate": 1.2896785068234925e-05,
+      "loss": 0.0023,
+      "step": 204
+    },
+    {
+      "epoch": 12.71,
+      "learning_rate": 1.283205506682304e-05,
+      "loss": 0.0027,
+      "step": 205
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 1.2767195796562359e-05,
+      "loss": 0.0031,
+      "step": 206
+    },
+    {
+      "epoch": 12.84,
+      "learning_rate": 1.2702210217947289e-05,
+      "loss": 0.0044,
+      "step": 207
+    },
+    {
+      "epoch": 12.9,
+      "learning_rate": 1.263710129723757e-05,
+      "loss": 0.0027,
+      "step": 208
+    },
+    {
+      "epoch": 12.96,
+      "learning_rate": 1.257187200632289e-05,
+      "loss": 0.0027,
+      "step": 209
+    },
+    {
+      "epoch": 13.02,
+      "learning_rate": 1.2506525322587207e-05,
+      "loss": 0.0019,
+      "step": 210
+    },
+    {
+      "epoch": 13.09,
+      "learning_rate": 1.2441064228772874e-05,
+      "loss": 0.0019,
+      "step": 211
+    },
+    {
+      "epoch": 13.15,
+      "learning_rate": 1.2375491712844472e-05,
+      "loss": 0.002,
+      "step": 212
+    },
+    {
+      "epoch": 13.21,
+      "learning_rate": 1.2309810767852435e-05,
+      "loss": 0.0021,
+      "step": 213
+    },
+    {
+      "epoch": 13.27,
+      "learning_rate": 1.2244024391796432e-05,
+      "loss": 0.0021,
+      "step": 214
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 1.2178135587488515e-05,
+      "loss": 0.0016,
+      "step": 215
+    },
+    {
+      "epoch": 13.4,
+      "learning_rate": 1.2112147362416076e-05,
+      "loss": 0.0022,
+      "step": 216
+    },
+    {
+      "epoch": 13.46,
+      "learning_rate": 1.204606272860454e-05,
+      "loss": 0.0027,
+      "step": 217
+    },
+    {
+      "epoch": 13.52,
+      "learning_rate": 1.1979884702479909e-05,
+      "loss": 0.0023,
+      "step": 218
+    },
+    {
+      "epoch": 13.58,
+      "learning_rate": 1.1913616304731064e-05,
+      "loss": 0.0028,
+      "step": 219
+    },
+    {
+      "epoch": 13.64,
+      "learning_rate": 1.1847260560171895e-05,
+      "loss": 0.0022,
+      "step": 220
+    },
+    {
+      "epoch": 13.71,
+      "learning_rate": 1.1780820497603215e-05,
+      "loss": 0.0021,
+      "step": 221
+    },
+    {
+      "epoch": 13.77,
+      "learning_rate": 1.1714299149674538e-05,
+      "loss": 0.002,
+      "step": 222
+    },
+    {
+      "epoch": 13.83,
+      "learning_rate": 1.1647699552745628e-05,
+      "loss": 0.0022,
+      "step": 223
+    },
+    {
+      "epoch": 13.89,
+      "learning_rate": 1.1581024746747925e-05,
+      "loss": 0.0022,
+      "step": 224
+    },
+    {
+      "epoch": 13.95,
+      "learning_rate": 1.1514277775045768e-05,
+      "loss": 0.0026,
+      "step": 225
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 1.1447461684297505e-05,
+      "loss": 0.0021,
+      "step": 226
+    },
+    {
+      "epoch": 14.08,
+      "learning_rate": 1.1380579524316406e-05,
+      "loss": 0.0016,
+      "step": 227
+    },
+    {
+      "epoch": 14.14,
+      "learning_rate": 1.1313634347931466e-05,
+      "loss": 0.0025,
+      "step": 228
+    },
+    {
+      "epoch": 14.2,
+      "learning_rate": 1.1246629210848062e-05,
+      "loss": 0.0016,
+      "step": 229
+    },
+    {
+      "epoch": 14.26,
+      "learning_rate": 1.1179567171508463e-05,
+      "loss": 0.0016,
+      "step": 230
+    },
+    {
+      "epoch": 14.33,
+      "learning_rate": 1.1112451290952238e-05,
+      "loss": 0.0017,
+      "step": 231
+    },
+    {
+      "epoch": 14.39,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0019,
+      "step": 232
+    },
+    {
+      "epoch": 14.45,
+      "learning_rate": 1.0978070262496248e-05,
+      "loss": 0.0018,
+      "step": 233
+    },
+    {
+      "epoch": 14.51,
+      "learning_rate": 1.0910811248404064e-05,
+      "loss": 0.0018,
+      "step": 234
+    },
+    {
+      "epoch": 14.57,
+      "learning_rate": 1.0843510660430447e-05,
+      "loss": 0.0022,
+      "step": 235
+    },
+    {
+      "epoch": 14.64,
+      "learning_rate": 1.07761715705035e-05,
+      "loss": 0.0023,
+      "step": 236
+    },
+    {
+      "epoch": 14.7,
+      "learning_rate": 1.070879705230873e-05,
+      "loss": 0.0022,
+      "step": 237
+    },
+    {
+      "epoch": 14.76,
+      "learning_rate": 1.0641390181148772e-05,
+      "loss": 0.0031,
+      "step": 238
+    },
+    {
+      "epoch": 14.82,
+      "learning_rate": 1.0573954033803006e-05,
+      "loss": 0.0021,
+      "step": 239
+    },
+    {
+      "epoch": 14.88,
+      "learning_rate": 1.0506491688387128e-05,
+      "loss": 0.0024,
+      "step": 240
+    },
+    {
+      "epoch": 14.95,
+      "learning_rate": 1.0439006224212629e-05,
+      "loss": 0.0028,
+      "step": 241
+    },
+    {
+      "epoch": 15.01,
+      "learning_rate": 1.037150072164626e-05,
+      "loss": 0.0023,
+      "step": 242
+    },
+    {
+      "epoch": 15.07,
+      "learning_rate": 1.030397826196943e-05,
+      "loss": 0.0017,
+      "step": 243
+    },
+    {
+      "epoch": 15.13,
+      "learning_rate": 1.0236441927237534e-05,
+      "loss": 0.0014,
+      "step": 244
+    },
+    {
+      "epoch": 15.19,
+      "learning_rate": 1.0168894800139311e-05,
+      "loss": 0.0015,
+      "step": 245
+    },
+    {
+      "epoch": 15.26,
+      "learning_rate": 1.0101339963856112e-05,
+      "loss": 0.0013,
+      "step": 246
+    },
+    {
+      "epoch": 15.32,
+      "learning_rate": 1.0033780501921164e-05,
+      "loss": 0.0022,
+      "step": 247
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 9.966219498078839e-06,
+      "loss": 0.002,
+      "step": 248
+    },
+    {
+      "epoch": 15.44,
+      "learning_rate": 9.898660036143893e-06,
+      "loss": 0.0015,
+      "step": 249
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 9.83110519986069e-06,
+      "loss": 0.0014,
+      "step": 250
+    },
+    {
+      "epoch": 15.57,
+      "learning_rate": 9.763558072762467e-06,
+      "loss": 0.0014,
+      "step": 251
+    },
+    {
+      "epoch": 15.63,
+      "learning_rate": 9.696021738030575e-06,
+      "loss": 0.0019,
+      "step": 252
+    },
+    {
+      "epoch": 15.69,
+      "learning_rate": 9.62849927835374e-06,
+      "loss": 0.0019,
+      "step": 253
+    },
+    {
+      "epoch": 15.75,
+      "learning_rate": 9.560993775787373e-06,
+      "loss": 0.0017,
+      "step": 254
+    },
+    {
+      "epoch": 15.81,
+      "learning_rate": 9.493508311612874e-06,
+      "loss": 0.0017,
+      "step": 255
+    },
+    {
+      "epoch": 15.88,
+      "learning_rate": 9.426045966196992e-06,
+      "loss": 0.0023,
+      "step": 256
+    },
+    {
+      "epoch": 15.94,
+      "learning_rate": 9.35860981885123e-06,
+      "loss": 0.0026,
+      "step": 257
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 9.291202947691272e-06,
+      "loss": 0.0025,
+      "step": 258
+    },
+    {
+      "epoch": 16.06,
+      "learning_rate": 9.2238284294965e-06,
+      "loss": 0.0018,
+      "step": 259
+    },
+    {
+      "epoch": 16.12,
+      "learning_rate": 9.156489339569555e-06,
+      "loss": 0.0011,
+      "step": 260
+    },
+    {
+      "epoch": 16.19,
+      "learning_rate": 9.089188751595937e-06,
+      "loss": 0.0017,
+      "step": 261
+    },
+    {
+      "epoch": 16.25,
+      "learning_rate": 9.021929737503757e-06,
+      "loss": 0.0014,
+      "step": 262
+    },
+    {
+      "epoch": 16.31,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.0016,
+      "step": 263
+    },
+    {
+      "epoch": 16.37,
+      "learning_rate": 8.887548709047765e-06,
+      "loss": 0.0019,
+      "step": 264
+    },
+    {
+      "epoch": 16.43,
+      "learning_rate": 8.820432828491542e-06,
+      "loss": 0.0015,
+      "step": 265
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 8.753370789151941e-06,
+      "loss": 0.0016,
+      "step": 266
+    },
+    {
+      "epoch": 16.56,
+      "learning_rate": 8.686365652068536e-06,
+      "loss": 0.0014,
+      "step": 267
+    },
+    {
+      "epoch": 16.62,
+      "learning_rate": 8.619420475683597e-06,
+      "loss": 0.0013,
+      "step": 268
+    },
+    {
+      "epoch": 16.68,
+      "learning_rate": 8.552538315702497e-06,
+      "loss": 0.0016,
+      "step": 269
+    },
+    {
+      "epoch": 16.74,
+      "learning_rate": 8.485722224954237e-06,
+      "loss": 0.0024,
+      "step": 270
+    },
+    {
+      "epoch": 16.81,
+      "learning_rate": 8.418975253252079e-06,
+      "loss": 0.0016,
+      "step": 271
+    },
+    {
+      "epoch": 16.87,
+      "learning_rate": 8.352300447254372e-06,
+      "loss": 0.0024,
+      "step": 272
+    },
+    {
+      "epoch": 16.93,
+      "learning_rate": 8.285700850325467e-06,
+      "loss": 0.0021,
+      "step": 273
+    },
+    {
+      "epoch": 16.99,
+      "learning_rate": 8.219179502396786e-06,
+      "loss": 0.0021,
+      "step": 274
+    },
+    {
+      "epoch": 17.05,
+      "learning_rate": 8.15273943982811e-06,
+      "loss": 0.0016,
+      "step": 275
+    },
+    {
+      "epoch": 17.12,
+      "learning_rate": 8.086383695268937e-06,
+      "loss": 0.0017,
+      "step": 276
+    },
+    {
+      "epoch": 17.18,
+      "learning_rate": 8.020115297520093e-06,
+      "loss": 0.0011,
+      "step": 277
+    },
+    {
+      "epoch": 17.24,
+      "learning_rate": 7.953937271395465e-06,
+      "loss": 0.0016,
+      "step": 278
+    },
+    {
+      "epoch": 17.3,
+      "learning_rate": 7.887852637583927e-06,
+      "loss": 0.0014,
+      "step": 279
+    },
+    {
+      "epoch": 17.36,
+      "learning_rate": 7.821864412511485e-06,
+      "loss": 0.0015,
+      "step": 280
+    },
+    {
+      "epoch": 17.43,
+      "learning_rate": 7.755975608203571e-06,
+      "loss": 0.0018,
+      "step": 281
+    },
+    {
+      "epoch": 17.49,
+      "learning_rate": 7.690189232147566e-06,
+      "loss": 0.0021,
+      "step": 282
+    },
+    {
+      "epoch": 17.55,
+      "learning_rate": 7.624508287155534e-06,
+      "loss": 0.0018,
+      "step": 283
+    },
+    {
+      "epoch": 17.61,
+      "learning_rate": 7.558935771227129e-06,
+      "loss": 0.0013,
+      "step": 284
+    },
+    {
+      "epoch": 17.67,
+      "learning_rate": 7.493474677412795e-06,
+      "loss": 0.0015,
+      "step": 285
+    },
+    {
+      "epoch": 17.74,
+      "learning_rate": 7.428127993677116e-06,
+      "loss": 0.0016,
+      "step": 286
+    },
+    {
+      "epoch": 17.8,
+      "learning_rate": 7.362898702762433e-06,
+      "loss": 0.0017,
+      "step": 287
+    },
+    {
+      "epoch": 17.86,
+      "learning_rate": 7.297789782052716e-06,
+      "loss": 0.0017,
+      "step": 288
+    },
+    {
+      "epoch": 17.92,
+      "learning_rate": 7.232804203437645e-06,
+      "loss": 0.0023,
+      "step": 289
+    },
+    {
+      "epoch": 17.98,
+      "learning_rate": 7.16794493317696e-06,
+      "loss": 0.0023,
+      "step": 290
+    },
+    {
+      "epoch": 18.05,
+      "learning_rate": 7.10321493176508e-06,
+      "loss": 0.0018,
+      "step": 291
+    },
+    {
+      "epoch": 18.11,
+      "learning_rate": 7.038617153795948e-06,
+      "loss": 0.0016,
+      "step": 292
+    },
+    {
+      "epoch": 18.17,
+      "learning_rate": 6.974154547828191e-06,
+      "loss": 0.0014,
+      "step": 293
+    },
+    {
+      "epoch": 18.23,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0018,
+      "step": 294
+    },
+    {
+      "epoch": 18.29,
+      "learning_rate": 6.845646615147445e-06,
+      "loss": 0.0017,
+      "step": 295
+    },
+    {
+      "epoch": 18.36,
+      "learning_rate": 6.781607154165217e-06,
+      "loss": 0.0014,
+      "step": 296
+    },
+    {
+      "epoch": 18.42,
+      "learning_rate": 6.717714596378138e-06,
+      "loss": 0.0013,
+      "step": 297
+    },
+    {
+      "epoch": 18.48,
+      "learning_rate": 6.65397185815514e-06,
+      "loss": 0.0009,
+      "step": 298
+    },
+    {
+      "epoch": 18.54,
+      "learning_rate": 6.5903818490266554e-06,
+      "loss": 0.0012,
+      "step": 299
+    },
+    {
+      "epoch": 18.6,
+      "learning_rate": 6.526947471551799e-06,
+      "loss": 0.0018,
+      "step": 300
+    },
+    {
+      "epoch": 18.67,
+      "learning_rate": 6.4636716211859076e-06,
+      "loss": 0.0017,
+      "step": 301
+    },
+    {
+      "epoch": 18.73,
+      "learning_rate": 6.400557186148371e-06,
+      "loss": 0.0019,
+      "step": 302
+    },
+    {
+      "epoch": 18.79,
+      "learning_rate": 6.337607047290774e-06,
+      "loss": 0.002,
+      "step": 303
+    },
+    {
+      "epoch": 18.85,
+      "learning_rate": 6.274824077965438e-06,
+      "loss": 0.0013,
+      "step": 304
+    },
+    {
+      "epoch": 18.91,
+      "learning_rate": 6.21221114389424e-06,
+      "loss": 0.0019,
+      "step": 305
+    },
+    {
+      "epoch": 18.98,
+      "learning_rate": 6.149771103037821e-06,
+      "loss": 0.0015,
+      "step": 306
+    },
+    {
+      "epoch": 19.04,
+      "learning_rate": 6.087506805465127e-06,
+      "loss": 0.0023,
+      "step": 307
+    },
+    {
+      "epoch": 19.1,
+      "learning_rate": 6.025421093223318e-06,
+      "loss": 0.0015,
+      "step": 308
+    },
+    {
+      "epoch": 19.16,
+      "learning_rate": 5.963516800208056e-06,
+      "loss": 0.0014,
+      "step": 309
+    },
+    {
+      "epoch": 19.22,
+      "learning_rate": 5.901796752034128e-06,
+      "loss": 0.0012,
+      "step": 310
+    },
+    {
+      "epoch": 19.29,
+      "learning_rate": 5.84026376590649e-06,
+      "loss": 0.0012,
+      "step": 311
+    },
+    {
+      "epoch": 19.35,
+      "learning_rate": 5.7789206504916815e-06,
+      "loss": 0.0019,
+      "step": 312
+    },
+    {
+      "epoch": 19.41,
+      "learning_rate": 5.7177702057896015e-06,
+      "loss": 0.0012,
+      "step": 313
+    },
+    {
+      "epoch": 19.47,
+      "learning_rate": 5.656815223005714e-06,
+      "loss": 0.0019,
+      "step": 314
+    },
+    {
+      "epoch": 19.53,
+      "learning_rate": 5.5960584844236565e-06,
+      "loss": 0.0013,
+      "step": 315
+    },
+    {
+      "epoch": 19.6,
+      "learning_rate": 5.535502763278222e-06,
+      "loss": 0.002,
+      "step": 316
+    },
+    {
+      "epoch": 19.66,
+      "learning_rate": 5.475150823628786e-06,
+      "loss": 0.0017,
+      "step": 317
+    },
+    {
+      "epoch": 19.72,
+      "learning_rate": 5.415005420233141e-06,
+      "loss": 0.0012,
+      "step": 318
+    },
+    {
+      "epoch": 19.78,
+      "learning_rate": 5.355069298421747e-06,
+      "loss": 0.0016,
+      "step": 319
+    },
+    {
+      "epoch": 19.84,
+      "learning_rate": 5.295345193972445e-06,
+      "loss": 0.002,
+      "step": 320
+    },
+    {
+      "epoch": 19.91,
+      "learning_rate": 5.235835832985552e-06,
+      "loss": 0.0013,
+      "step": 321
+    },
+    {
+      "epoch": 19.97,
+      "learning_rate": 5.176543931759447e-06,
+      "loss": 0.0018,
+      "step": 322
+    },
+    {
+      "epoch": 20.03,
+      "learning_rate": 5.117472196666578e-06,
+      "loss": 0.0017,
+      "step": 323
+    },
+    {
+      "epoch": 20.09,
+      "learning_rate": 5.058623324029944e-06,
+      "loss": 0.0013,
+      "step": 324
+    },
+    {
+      "epoch": 20.16,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0011,
+      "step": 325
+    },
+    {
+      "epoch": 20.22,
+      "learning_rate": 4.941604900432065e-06,
+      "loss": 0.0015,
+      "step": 326
+    },
+    {
+      "epoch": 20.28,
+      "learning_rate": 4.8834406907641784e-06,
+      "loss": 0.0013,
+      "step": 327
+    },
+    {
+      "epoch": 20.34,
+      "learning_rate": 4.825510025895429e-06,
+      "loss": 0.0012,
+      "step": 328
+    },
+    {
+      "epoch": 20.4,
+      "learning_rate": 4.767815550064778e-06,
+      "loss": 0.0014,
+      "step": 329
+    },
+    {
+      "epoch": 20.47,
+      "learning_rate": 4.710359896730379e-06,
+      "loss": 0.0014,
+      "step": 330
+    },
+    {
+      "epoch": 20.53,
+      "learning_rate": 4.65314568844933e-06,
+      "loss": 0.0014,
+      "step": 331
+    },
+    {
+      "epoch": 20.59,
+      "learning_rate": 4.596175536758024e-06,
+      "loss": 0.0018,
+      "step": 332
+    },
+    {
+      "epoch": 20.65,
+      "learning_rate": 4.539452042052901e-06,
+      "loss": 0.0018,
+      "step": 333
+    },
+    {
+      "epoch": 20.71,
+      "learning_rate": 4.482977793471769e-06,
+      "loss": 0.0013,
+      "step": 334
+    },
+    {
+      "epoch": 20.78,
+      "learning_rate": 4.426755368775637e-06,
+      "loss": 0.002,
+      "step": 335
+    },
+    {
+      "epoch": 20.84,
+      "learning_rate": 4.370787334231026e-06,
+      "loss": 0.0016,
+      "step": 336
+    },
+    {
+      "epoch": 20.9,
+      "learning_rate": 4.315076244492847e-06,
+      "loss": 0.0017,
+      "step": 337
+    },
+    {
+      "epoch": 20.96,
+      "learning_rate": 4.2596246424878055e-06,
+      "loss": 0.0014,
+      "step": 338
+    },
+    {
+      "epoch": 21.02,
+      "learning_rate": 4.204435059298303e-06,
+      "loss": 0.0019,
+      "step": 339
+    },
+    {
+      "epoch": 21.09,
+      "learning_rate": 4.149510014046922e-06,
+      "loss": 0.0013,
+      "step": 340
+    },
+    {
+      "epoch": 21.15,
+      "learning_rate": 4.094852013781456e-06,
+      "loss": 0.0015,
+      "step": 341
+    },
+    {
+      "epoch": 21.21,
+      "learning_rate": 4.040463553360431e-06,
+      "loss": 0.0017,
+      "step": 342
+    },
+    {
+      "epoch": 21.27,
+      "learning_rate": 3.986347115339281e-06,
+      "loss": 0.001,
+      "step": 343
+    },
+    {
+      "epoch": 21.33,
+      "learning_rate": 3.932505169856993e-06,
+      "loss": 0.0014,
+      "step": 344
+    },
+    {
+      "epoch": 21.4,
+      "learning_rate": 3.878940174523371e-06,
+      "loss": 0.0016,
+      "step": 345
+    },
+    {
+      "epoch": 21.46,
+      "learning_rate": 3.825654574306873e-06,
+      "loss": 0.0012,
+      "step": 346
+    },
+    {
+      "epoch": 21.52,
+      "learning_rate": 3.7726508014229825e-06,
+      "loss": 0.0015,
+      "step": 347
+    },
+    {
+      "epoch": 21.58,
+      "learning_rate": 3.7199312752232053e-06,
+      "loss": 0.0012,
+      "step": 348
+    },
+    {
+      "epoch": 21.64,
+      "learning_rate": 3.6674984020846503e-06,
+      "loss": 0.0016,
+      "step": 349
+    },
+    {
+      "epoch": 21.71,
+      "learning_rate": 3.6153545753001663e-06,
+      "loss": 0.0017,
+      "step": 350
+    },
+    {
+      "epoch": 21.77,
+      "learning_rate": 3.563502174969117e-06,
+      "loss": 0.0012,
+      "step": 351
+    },
+    {
+      "epoch": 21.83,
+      "learning_rate": 3.5119435678887328e-06,
+      "loss": 0.0016,
+      "step": 352
+    },
+    {
+      "epoch": 21.89,
+      "learning_rate": 3.460681107446091e-06,
+      "loss": 0.0018,
+      "step": 353
+    },
+    {
+      "epoch": 21.95,
+      "learning_rate": 3.409717133510683e-06,
+      "loss": 0.0017,
+      "step": 354
+    },
+    {
+      "epoch": 22.02,
+      "learning_rate": 3.3590539723276083e-06,
+      "loss": 0.0015,
+      "step": 355
+    },
+    {
+      "epoch": 22.08,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.0012,
+      "step": 356
+    },
+    {
+      "epoch": 22.14,
+      "learning_rate": 3.258639324440527e-06,
+      "loss": 0.0018,
+      "step": 357
+    },
+    {
+      "epoch": 22.2,
+      "learning_rate": 3.208892421152314e-06,
+      "loss": 0.0014,
+      "step": 358
+    },
+    {
+      "epoch": 22.26,
+      "learning_rate": 3.159455497238827e-06,
+      "loss": 0.0013,
+      "step": 359
+    },
+    {
+      "epoch": 22.33,
+      "learning_rate": 3.110330809243134e-06,
+      "loss": 0.0012,
+      "step": 360
+    },
+    {
+      "epoch": 22.39,
+      "learning_rate": 3.0615205994563412e-06,
+      "loss": 0.0013,
+      "step": 361
+    },
+    {
+      "epoch": 22.45,
+      "learning_rate": 3.0130270958152196e-06,
+      "loss": 0.0013,
+      "step": 362
+    },
+    {
+      "epoch": 22.51,
+      "learning_rate": 2.964852511800519e-06,
+      "loss": 0.0013,
+      "step": 363
+    },
+    {
+      "epoch": 22.57,
+      "learning_rate": 2.9169990463359556e-06,
+      "loss": 0.0016,
+      "step": 364
+    },
+    {
+      "epoch": 22.64,
+      "learning_rate": 2.869468883687798e-06,
+      "loss": 0.0018,
+      "step": 365
+    },
+    {
+      "epoch": 22.7,
+      "learning_rate": 2.822264193365212e-06,
+      "loss": 0.0014,
+      "step": 366
+    },
+    {
+      "epoch": 22.76,
+      "learning_rate": 2.775387130021214e-06,
+      "loss": 0.0015,
+      "step": 367
+    },
+    {
+      "epoch": 22.82,
+      "learning_rate": 2.7288398333543063e-06,
+      "loss": 0.0016,
+      "step": 368
+    },
+    {
+      "epoch": 22.88,
+      "learning_rate": 2.6826244280108438e-06,
+      "loss": 0.0011,
+      "step": 369
+    },
+    {
+      "epoch": 22.95,
+      "learning_rate": 2.6367430234880286e-06,
+      "loss": 0.0017,
+      "step": 370
+    },
+    {
+      "epoch": 23.01,
+      "learning_rate": 2.591197714037631e-06,
+      "loss": 0.0014,
+      "step": 371
+    },
+    {
+      "epoch": 23.07,
+      "learning_rate": 2.545990578570404e-06,
+      "loss": 0.0012,
+      "step": 372
+    },
+    {
+      "epoch": 23.13,
+      "learning_rate": 2.5011236805611818e-06,
+      "loss": 0.0014,
+      "step": 373
+    },
+    {
+      "epoch": 23.19,
+      "learning_rate": 2.4565990679546913e-06,
+      "loss": 0.0012,
+      "step": 374
+    },
+    {
+      "epoch": 23.26,
+      "learning_rate": 2.4124187730720916e-06,
+      "loss": 0.001,
+      "step": 375
+    },
+    {
+      "epoch": 23.32,
+      "learning_rate": 2.3685848125181843e-06,
+      "loss": 0.0012,
+      "step": 376
+    },
+    {
+      "epoch": 23.38,
+      "learning_rate": 2.3250991870893837e-06,
+      "loss": 0.0015,
+      "step": 377
+    },
+    {
+      "epoch": 23.44,
+      "learning_rate": 2.2819638816823796e-06,
+      "loss": 0.0012,
+      "step": 378
+    },
+    {
+      "epoch": 23.5,
+      "learning_rate": 2.239180865203552e-06,
+      "loss": 0.0012,
+      "step": 379
+    },
+    {
+      "epoch": 23.57,
+      "learning_rate": 2.196752090479083e-06,
+      "loss": 0.002,
+      "step": 380
+    },
+    {
+      "epoch": 23.63,
+      "learning_rate": 2.154679494165829e-06,
+      "loss": 0.0012,
+      "step": 381
+    },
+    {
+      "epoch": 23.69,
+      "learning_rate": 2.1129649966629185e-06,
+      "loss": 0.0012,
+      "step": 382
+    },
+    {
+      "epoch": 23.75,
+      "learning_rate": 2.0716105020241074e-06,
+      "loss": 0.0011,
+      "step": 383
+    },
+    {
+      "epoch": 23.81,
+      "learning_rate": 2.030617897870851e-06,
+      "loss": 0.0016,
+      "step": 384
+    },
+    {
+      "epoch": 23.88,
+      "learning_rate": 1.9899890553061565e-06,
+      "loss": 0.0018,
+      "step": 385
+    },
+    {
+      "epoch": 23.94,
+      "learning_rate": 1.9497258288291655e-06,
+      "loss": 0.0018,
+      "step": 386
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.0019,
+      "step": 387
+    },
+    {
+      "epoch": 24.06,
+      "learning_rate": 1.8703035586084817e-06,
+      "loss": 0.0012,
+      "step": 388
+    },
+    {
+      "epoch": 24.12,
+      "learning_rate": 1.8311481400857622e-06,
+      "loss": 0.0012,
+      "step": 389
+    },
+    {
+      "epoch": 24.19,
+      "learning_rate": 1.7923655879272395e-06,
+      "loss": 0.0014,
+      "step": 390
+    },
+    {
+      "epoch": 24.25,
+      "learning_rate": 1.753957672358324e-06,
+      "loss": 0.0016,
+      "step": 391
+    },
+    {
+      "epoch": 24.31,
+      "learning_rate": 1.7159261465041954e-06,
+      "loss": 0.0014,
+      "step": 392
+    },
+    {
+      "epoch": 24.37,
+      "learning_rate": 1.6782727463097626e-06,
+      "loss": 0.0015,
+      "step": 393
+    },
+    {
+      "epoch": 24.43,
+      "learning_rate": 1.6409991904604173e-06,
+      "loss": 0.0018,
+      "step": 394
+    },
+    {
+      "epoch": 24.5,
+      "learning_rate": 1.60410718030361e-06,
+      "loss": 0.0011,
+      "step": 395
+    },
+    {
+      "epoch": 24.56,
+      "learning_rate": 1.5675983997711797e-06,
+      "loss": 0.0013,
+      "step": 396
+    },
+    {
+      "epoch": 24.62,
+      "learning_rate": 1.5314745153024768e-06,
+      "loss": 0.0014,
+      "step": 397
+    },
+    {
+      "epoch": 24.68,
+      "learning_rate": 1.4957371757683258e-06,
+      "loss": 0.0014,
+      "step": 398
+    },
+    {
+      "epoch": 24.74,
+      "learning_rate": 1.4603880123957448e-06,
+      "loss": 0.0014,
+      "step": 399
+    },
+    {
+      "epoch": 24.81,
+      "learning_rate": 1.425428638693489e-06,
+      "loss": 0.0019,
+      "step": 400
+    },
+    {
+      "epoch": 24.87,
+      "learning_rate": 1.390860650378414e-06,
+      "loss": 0.0014,
+      "step": 401
+    },
+    {
+      "epoch": 24.93,
+      "learning_rate": 1.356685625302625e-06,
+      "loss": 0.0013,
+      "step": 402
+    },
+    {
+      "epoch": 24.99,
+      "learning_rate": 1.3229051233814637e-06,
+      "loss": 0.0013,
+      "step": 403
+    },
+    {
+      "epoch": 25.05,
+      "learning_rate": 1.2895206865223065e-06,
+      "loss": 0.0012,
+      "step": 404
+    },
+    {
+      "epoch": 25.12,
+      "learning_rate": 1.2565338385541792e-06,
+      "loss": 0.0013,
+      "step": 405
+    },
+    {
+      "epoch": 25.18,
+      "learning_rate": 1.2239460851582118e-06,
+      "loss": 0.0013,
+      "step": 406
+    },
+    {
+      "epoch": 25.24,
+      "learning_rate": 1.1917589137989006e-06,
+      "loss": 0.0013,
+      "step": 407
+    },
+    {
+      "epoch": 25.3,
+      "learning_rate": 1.159973793656215e-06,
+      "loss": 0.0014,
+      "step": 408
+    },
+    {
+      "epoch": 25.36,
+      "learning_rate": 1.1285921755585504e-06,
+      "loss": 0.0013,
+      "step": 409
+    },
+    {
+      "epoch": 25.43,
+      "learning_rate": 1.097615491916485e-06,
+      "loss": 0.0016,
+      "step": 410
+    },
+    {
+      "epoch": 25.49,
+      "learning_rate": 1.0670451566574102e-06,
+      "loss": 0.0014,
+      "step": 411
+    },
+    {
+      "epoch": 25.55,
+      "learning_rate": 1.0368825651609893e-06,
+      "loss": 0.0014,
+      "step": 412
+    },
+    {
+      "epoch": 25.61,
+      "learning_rate": 1.007129094195468e-06,
+      "loss": 0.0013,
+      "step": 413
+    },
+    {
+      "epoch": 25.67,
+      "learning_rate": 9.77786101854825e-07,
+      "loss": 0.0015,
+      "step": 414
+    },
+    {
+      "epoch": 25.74,
+      "learning_rate": 9.488549274967873e-07,
+      "loss": 0.0012,
+      "step": 415
+    },
+    {
+      "epoch": 25.8,
+      "learning_rate": 9.203368916817012e-07,
+      "loss": 0.0014,
+      "step": 416
+    },
+    {
+      "epoch": 25.86,
+      "learning_rate": 8.92233296112236e-07,
+      "loss": 0.0012,
+      "step": 417
+    },
+    {
+      "epoch": 25.92,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.0013,
+      "step": 418
+    },
+    {
+      "epoch": 25.98,
+      "learning_rate": 8.37274537876931e-07,
+      "loss": 0.0014,
+      "step": 419
+    },
+    {
+      "epoch": 26.05,
+      "learning_rate": 8.10421883797694e-07,
+      "loss": 0.0012,
+      "step": 420
+    },
+    {
+      "epoch": 26.11,
+      "learning_rate": 7.839886870227909e-07,
+      "loss": 0.0013,
+      "step": 421
+    },
+    {
+      "epoch": 26.17,
+      "learning_rate": 7.579761540926434e-07,
+      "loss": 0.0017,
+      "step": 422
+    },
+    {
+      "epoch": 26.23,
+      "learning_rate": 7.32385472346514e-07,
+      "loss": 0.001,
+      "step": 423
+    },
+    {
+      "epoch": 26.29,
+      "learning_rate": 7.072178098683247e-07,
+      "loss": 0.0015,
+      "step": 424
+    },
+    {
+      "epoch": 26.36,
+      "learning_rate": 6.824743154333157e-07,
+      "loss": 0.0015,
+      "step": 425
+    },
+    {
+      "epoch": 26.42,
+      "learning_rate": 6.581561184556296e-07,
+      "loss": 0.0013,
+      "step": 426
+    },
+    {
+      "epoch": 26.48,
+      "learning_rate": 6.342643289367523e-07,
+      "loss": 0.0016,
+      "step": 427
+    },
+    {
+      "epoch": 26.54,
+      "learning_rate": 6.108000374148448e-07,
+      "loss": 0.0013,
+      "step": 428
+    },
+    {
+      "epoch": 26.6,
+      "learning_rate": 5.877643149149669e-07,
+      "loss": 0.0018,
+      "step": 429
+    },
+    {
+      "epoch": 26.67,
+      "learning_rate": 5.651582129001987e-07,
+      "loss": 0.0011,
+      "step": 430
+    },
+    {
+      "epoch": 26.73,
+      "learning_rate": 5.429827632236284e-07,
+      "loss": 0.0016,
+      "step": 431
+    },
+    {
+      "epoch": 26.79,
+      "learning_rate": 5.212389780812733e-07,
+      "loss": 0.0012,
+      "step": 432
+    },
+    {
+      "epoch": 26.85,
+      "learning_rate": 4.999278499658667e-07,
+      "loss": 0.0012,
+      "step": 433
+    },
+    {
+      "epoch": 26.91,
+      "learning_rate": 4.790503516215572e-07,
+      "loss": 0.0013,
+      "step": 434
+    },
+    {
+      "epoch": 26.98,
+      "learning_rate": 4.5860743599951186e-07,
+      "loss": 0.0013,
+      "step": 435
+    },
+    {
+      "epoch": 27.04,
+      "learning_rate": 4.3860003621441384e-07,
+      "loss": 0.0011,
+      "step": 436
+    },
+    {
+      "epoch": 27.1,
+      "learning_rate": 4.190290655018736e-07,
+      "loss": 0.0015,
+      "step": 437
+    },
+    {
+      "epoch": 27.16,
+      "learning_rate": 3.998954171767422e-07,
+      "loss": 0.0011,
+      "step": 438
+    },
+    {
+      "epoch": 27.22,
+      "learning_rate": 3.8119996459234144e-07,
+      "loss": 0.0011,
+      "step": 439
+    },
+    {
+      "epoch": 27.29,
+      "learning_rate": 3.629435611005916e-07,
+      "loss": 0.0015,
+      "step": 440
+    },
+    {
+      "epoch": 27.35,
+      "learning_rate": 3.451270400130646e-07,
+      "loss": 0.0015,
+      "step": 441
+    },
+    {
+      "epoch": 27.41,
+      "learning_rate": 3.2775121456295024e-07,
+      "loss": 0.0012,
+      "step": 442
+    },
+    {
+      "epoch": 27.47,
+      "learning_rate": 3.10816877867931e-07,
+      "loss": 0.0013,
+      "step": 443
+    },
+    {
+      "epoch": 27.53,
+      "learning_rate": 2.943248028939838e-07,
+      "loss": 0.0016,
+      "step": 444
+    },
+    {
+      "epoch": 27.6,
+      "learning_rate": 2.7827574242009434e-07,
+      "loss": 0.0015,
+      "step": 445
+    },
+    {
+      "epoch": 27.66,
+      "learning_rate": 2.6267042900390173e-07,
+      "loss": 0.001,
+      "step": 446
+    },
+    {
+      "epoch": 27.72,
+      "learning_rate": 2.4750957494826033e-07,
+      "loss": 0.0011,
+      "step": 447
+    },
+    {
+      "epoch": 27.78,
+      "learning_rate": 2.3279387226871842e-07,
+      "loss": 0.0012,
+      "step": 448
+    },
+    {
+      "epoch": 27.84,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.0013,
+      "step": 449
+    },
+    {
+      "epoch": 27.91,
+      "learning_rate": 2.0470058747505516e-07,
+      "loss": 0.0015,
+      "step": 450
+    },
+    {
+      "epoch": 27.97,
+      "learning_rate": 1.9132428767589471e-07,
+      "loss": 0.0016,
+      "step": 451
+    },
+    {
+      "epoch": 28.03,
+      "learning_rate": 1.783957038242279e-07,
+      "loss": 0.0014,
+      "step": 452
+    },
+    {
+      "epoch": 28.09,
+      "learning_rate": 1.6591542604387445e-07,
+      "loss": 0.0012,
+      "step": 453
+    },
+    {
+      "epoch": 28.16,
+      "learning_rate": 1.538840239957684e-07,
+      "loss": 0.0013,
+      "step": 454
+    },
+    {
+      "epoch": 28.22,
+      "learning_rate": 1.4230204685196202e-07,
+      "loss": 0.0012,
+      "step": 455
+    },
+    {
+      "epoch": 28.28,
+      "learning_rate": 1.3117002327055927e-07,
+      "loss": 0.0012,
+      "step": 456
+    },
+    {
+      "epoch": 28.34,
+      "learning_rate": 1.20488461371574e-07,
+      "loss": 0.0013,
+      "step": 457
+    },
+    {
+      "epoch": 28.4,
+      "learning_rate": 1.102578487137529e-07,
+      "loss": 0.0012,
+      "step": 458
+    },
+    {
+      "epoch": 28.47,
+      "learning_rate": 1.0047865227230891e-07,
+      "loss": 0.001,
+      "step": 459
+    },
+    {
+      "epoch": 28.53,
+      "learning_rate": 9.11513184176116e-08,
+      "loss": 0.0016,
+      "step": 460
+    },
+    {
+      "epoch": 28.59,
+      "learning_rate": 8.227627289481121e-08,
+      "loss": 0.0014,
+      "step": 461
+    },
+    {
+      "epoch": 28.65,
+      "learning_rate": 7.385392080440535e-08,
+      "loss": 0.0016,
+      "step": 462
+    },
+    {
+      "epoch": 28.71,
+      "learning_rate": 6.588464658374816e-08,
+      "loss": 0.0011,
+      "step": 463
+    },
+    {
+      "epoch": 28.78,
+      "learning_rate": 5.836881398950667e-08,
+      "loss": 0.0014,
+      "step": 464
+    },
+    {
+      "epoch": 28.84,
+      "learning_rate": 5.1306766081048456e-08,
+      "loss": 0.0014,
+      "step": 465
+    },
+    {
+      "epoch": 28.9,
+      "learning_rate": 4.469882520479196e-08,
+      "loss": 0.0015,
+      "step": 466
+    },
+    {
+      "epoch": 28.96,
+      "learning_rate": 3.854529297948606e-08,
+      "loss": 0.0016,
+      "step": 467
+    },
+    {
+      "epoch": 29.02,
+      "learning_rate": 3.284645028244771e-08,
+      "loss": 0.0011,
+      "step": 468
+    },
+    {
+      "epoch": 29.09,
+      "learning_rate": 2.760255723673888e-08,
+      "loss": 0.0015,
+      "step": 469
+    },
+    {
+      "epoch": 29.15,
+      "learning_rate": 2.2813853199292745e-08,
+      "loss": 0.0012,
+      "step": 470
+    },
+    {
+      "epoch": 29.21,
+      "learning_rate": 1.8480556749991274e-08,
+      "loss": 0.0018,
+      "step": 471
+    },
+    {
+      "epoch": 29.27,
+      "learning_rate": 1.4602865681682122e-08,
+      "loss": 0.0014,
+      "step": 472
+    },
+    {
+      "epoch": 29.33,
+      "learning_rate": 1.1180956991160285e-08,
+      "loss": 0.0016,
+      "step": 473
+    },
+    {
+      "epoch": 29.4,
+      "learning_rate": 8.214986871076803e-09,
+      "loss": 0.0011,
+      "step": 474
+    },
+    {
+      "epoch": 29.46,
+      "learning_rate": 5.705090702819993e-09,
+      "loss": 0.0011,
+      "step": 475
+    },
+    {
+      "epoch": 29.52,
+      "learning_rate": 3.6513830503293047e-09,
+      "loss": 0.0013,
+      "step": 476
+    },
+    {
+      "epoch": 29.58,
+      "learning_rate": 2.053957654871708e-09,
+      "loss": 0.0014,
+      "step": 477
+    },
+    {
+      "epoch": 29.64,
+      "learning_rate": 9.128874307551273e-10,
+      "loss": 0.0013,
+      "step": 478
+    },
+    {
+      "epoch": 29.71,
+      "learning_rate": 2.282244620088747e-10,
+      "loss": 0.0013,
+      "step": 479
+    },
+    {
+      "epoch": 29.77,
+      "learning_rate": 0.0,
+      "loss": 0.0016,
+      "step": 480
+    },
+    {
+      "epoch": 29.77,
+      "step": 480,
+      "total_flos": 2.2343126815342592e+17,
+      "train_loss": 0.07362916635223277,
+      "train_runtime": 3434.0129,
+      "train_samples_per_second": 18.023,
+      "train_steps_per_second": 0.14
+    }
+  ],
+  "max_steps": 480,
+  "num_train_epochs": 30,
+  "total_flos": 2.2343126815342592e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18cf10683b9faeec40c0dc21f1cd04a199015fc8addb19d7b68b354d40841ce
+size 3771