Initial commit

.gitattributes

@@ -0,0 +1,3 @@
+pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text

added_tokens.json

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

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "yahma/llama-7b-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": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8acaffa06eb0ef92c191657eaa769110df1b72db37c17433086af9d666aacb89
+size 9878009874

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d279cb42026f3cf8746758cfef23f8e5ce44adebbd3a4bfbf35a1cf57716833
+size 9894805046

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0bef61fdacd88f2c97201c9d5c35c27504e2753e7426f22764536e4cfed548
+size 7181009913

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953703424
+  },
+  "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": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": false
+}

trainer_state.json

@@ -0,0 +1,1987 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9974219421369233,
+  "global_step": 327,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1112,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.0206,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-06,
+      "loss": 0.9224,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.9011,
+      "step": 4
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 0.8421,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2e-05,
+      "loss": 0.8501,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4e-05,
+      "loss": 0.8161,
+      "step": 7
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7479,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8e-05,
+      "loss": 0.8107,
+      "step": 9
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 0.7969,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999508925174792e-05,
+      "loss": 0.7834,
+      "step": 11
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998035748930055e-05,
+      "loss": 0.8382,
+      "step": 12
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9995580615953747e-05,
+      "loss": 0.7545,
+      "step": 13
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9992143767376667e-05,
+      "loss": 0.7821,
+      "step": 14
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998772554074878e-05,
+      "loss": 0.7666,
+      "step": 15
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9982326370006056e-05,
+      "loss": 0.7816,
+      "step": 16
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9975946785427864e-05,
+      "loss": 0.7646,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9968587413584875e-05,
+      "loss": 0.7887,
+      "step": 18
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9960248977277548e-05,
+      "loss": 0.7951,
+      "step": 19
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9950932295465102e-05,
+      "loss": 0.7397,
+      "step": 20
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9940638283185118e-05,
+      "loss": 0.717,
+      "step": 21
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9929367951463655e-05,
+      "loss": 0.7622,
+      "step": 22
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.991712240721595e-05,
+      "loss": 0.7359,
+      "step": 23
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9903902853137703e-05,
+      "loss": 0.8178,
+      "step": 24
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9889710587586953e-05,
+      "loss": 0.705,
+      "step": 25
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9874547004456565e-05,
+      "loss": 0.8036,
+      "step": 26
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9858413593037326e-05,
+      "loss": 0.7602,
+      "step": 27
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9841311937871677e-05,
+      "loss": 0.7259,
+      "step": 28
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.982324371859808e-05,
+      "loss": 0.7589,
+      "step": 29
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.980421070978606e-05,
+      "loss": 0.7497,
+      "step": 30
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9784214780761917e-05,
+      "loss": 0.7793,
+      "step": 31
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9763257895425112e-05,
+      "loss": 0.7534,
+      "step": 32
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.974134211205541e-05,
+      "loss": 0.7051,
+      "step": 33
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.971846958311071e-05,
+      "loss": 0.7174,
+      "step": 34
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9694642555015643e-05,
+      "loss": 0.7289,
+      "step": 35
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9669863367940936e-05,
+      "loss": 0.7352,
+      "step": 36
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9644134455573588e-05,
+      "loss": 0.7557,
+      "step": 37
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9617458344877818e-05,
+      "loss": 0.7349,
+      "step": 38
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9589837655846916e-05,
+      "loss": 0.7211,
+      "step": 39
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9561275101245886e-05,
+      "loss": 0.7037,
+      "step": 40
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9531773486345025e-05,
+      "loss": 0.7744,
+      "step": 41
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9501335708644415e-05,
+      "loss": 0.7703,
+      "step": 42
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9469964757589324e-05,
+      "loss": 0.7808,
+      "step": 43
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9437663714276617e-05,
+      "loss": 0.7256,
+      "step": 44
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9404435751152134e-05,
+      "loss": 0.7824,
+      "step": 45
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.937028413169911e-05,
+      "loss": 0.7175,
+      "step": 46
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9335212210117656e-05,
+      "loss": 0.7627,
+      "step": 47
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9299223430995323e-05,
+      "loss": 0.7156,
+      "step": 48
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9262321328968797e-05,
+      "loss": 0.6907,
+      "step": 49
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9224509528376737e-05,
+      "loss": 0.7574,
+      "step": 50
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9185791742903816e-05,
+      "loss": 0.733,
+      "step": 51
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9146171775215982e-05,
+      "loss": 0.6711,
+      "step": 52
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9105653516586974e-05,
+      "loss": 0.7283,
+      "step": 53
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.906424094651615e-05,
+      "loss": 0.6833,
+      "step": 54
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9021938132337628e-05,
+      "loss": 0.6852,
+      "step": 55
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8978749228820827e-05,
+      "loss": 0.8043,
+      "step": 56
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8934678477762398e-05,
+      "loss": 0.7194,
+      "step": 57
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8889730207569607e-05,
+      "loss": 0.7081,
+      "step": 58
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8843908832835248e-05,
+      "loss": 0.7397,
+      "step": 59
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8797218853904037e-05,
+      "loss": 0.7373,
+      "step": 60
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.874966485643062e-05,
+      "loss": 0.7241,
+      "step": 61
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.87012515109292e-05,
+      "loss": 0.74,
+      "step": 62
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.865198357231481e-05,
+      "loss": 0.6932,
+      "step": 63
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8601865879436318e-05,
+      "loss": 0.7266,
+      "step": 64
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8550903354601182e-05,
+      "loss": 0.6856,
+      "step": 65
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8499101003091995e-05,
+      "loss": 0.7238,
+      "step": 66
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.84464639126749e-05,
+      "loss": 0.7108,
+      "step": 67
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.839299725309989e-05,
+      "loss": 0.6989,
+      "step": 68
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8338706275593066e-05,
+      "loss": 0.7524,
+      "step": 69
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8283596312340893e-05,
+      "loss": 0.7399,
+      "step": 70
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8227672775966478e-05,
+      "loss": 0.7099,
+      "step": 71
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8170941158997992e-05,
+      "loss": 0.7122,
+      "step": 72
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8113407033329213e-05,
+      "loss": 0.7275,
+      "step": 73
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8055076049672286e-05,
+      "loss": 0.6915,
+      "step": 74
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7995953937002723e-05,
+      "loss": 0.7147,
+      "step": 75
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.793604650199676e-05,
+      "loss": 0.6721,
+      "step": 76
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7875359628461035e-05,
+      "loss": 0.7075,
+      "step": 77
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7813899276754703e-05,
+      "loss": 0.7297,
+      "step": 78
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7751671483204062e-05,
+      "loss": 0.7018,
+      "step": 79
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.768868235950968e-05,
+      "loss": 0.7523,
+      "step": 80
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7624938092146138e-05,
+      "loss": 0.7886,
+      "step": 81
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7560444941754425e-05,
+      "loss": 0.681,
+      "step": 82
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.749520924252706e-05,
+      "loss": 0.693,
+      "step": 83
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.742923740158595e-05,
+      "loss": 0.7057,
+      "step": 84
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.736253589835316e-05,
+      "loss": 0.7088,
+      "step": 85
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7295111283914487e-05,
+      "loss": 0.7069,
+      "step": 86
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7226970180376087e-05,
+      "loss": 0.7533,
+      "step": 87
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.715811928021406e-05,
+      "loss": 0.7198,
+      "step": 88
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.708856534561716e-05,
+      "loss": 0.7136,
+      "step": 89
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.701831520782264e-05,
+      "loss": 0.7133,
+      "step": 90
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.694737576644533e-05,
+      "loss": 0.733,
+      "step": 91
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6875753988799984e-05,
+      "loss": 0.6841,
+      "step": 92
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.680345690921699e-05,
+      "loss": 0.7012,
+      "step": 93
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6730491628351487e-05,
+      "loss": 0.7667,
+      "step": 94
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6656865312485996e-05,
+      "loss": 0.7431,
+      "step": 95
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6582585192826544e-05,
+      "loss": 0.7613,
+      "step": 96
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6507658564792492e-05,
+      "loss": 0.6986,
+      "step": 97
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6432092787299994e-05,
+      "loss": 0.751,
+      "step": 98
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6355895282039244e-05,
+      "loss": 0.7664,
+      "step": 99
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.627907353274555e-05,
+      "loss": 0.6962,
+      "step": 100
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.620163508446435e-05,
+      "loss": 0.6989,
+      "step": 101
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.612358754281012e-05,
+      "loss": 0.7256,
+      "step": 102
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.604493857321944e-05,
+      "loss": 0.6577,
+      "step": 103
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.596569590019811e-05,
+      "loss": 0.7125,
+      "step": 104
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.588586730656249e-05,
+      "loss": 0.6889,
+      "step": 105
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5805460632675112e-05,
+      "loss": 0.7164,
+      "step": 106
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5724483775674645e-05,
+      "loss": 0.7055,
+      "step": 107
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5642944688700263e-05,
+      "loss": 0.7263,
+      "step": 108
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.556085138011055e-05,
+      "loss": 0.7597,
+      "step": 109
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.547821191269693e-05,
+      "loss": 0.5082,
+      "step": 110
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.539503440289181e-05,
+      "loss": 0.4754,
+      "step": 111
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5311327019971415e-05,
+      "loss": 0.4675,
+      "step": 112
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5227097985253422e-05,
+      "loss": 0.4605,
+      "step": 113
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5142355571289533e-05,
+      "loss": 0.4698,
+      "step": 114
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5057108101052978e-05,
+      "loss": 0.4604,
+      "step": 115
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.4971363947121065e-05,
+      "loss": 0.4471,
+      "step": 116
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4885131530852872e-05,
+      "loss": 0.4705,
+      "step": 117
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.479841932156215e-05,
+      "loss": 0.4537,
+      "step": 118
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4711235835685502e-05,
+      "loss": 0.4626,
+      "step": 119
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.462358963594595e-05,
+      "loss": 0.4561,
+      "step": 120
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4535489330511932e-05,
+      "loss": 0.437,
+      "step": 121
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4446943572151869e-05,
+      "loss": 0.4574,
+      "step": 122
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4357961057384323e-05,
+      "loss": 0.4613,
+      "step": 123
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.426855052562387e-05,
+      "loss": 0.4483,
+      "step": 124
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4178720758322761e-05,
+      "loss": 0.4536,
+      "step": 125
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4088480578108454e-05,
+      "loss": 0.446,
+      "step": 126
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.3997838847917096e-05,
+      "loss": 0.4131,
+      "step": 127
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3906804470123038e-05,
+      "loss": 0.4396,
+      "step": 128
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.3815386385664526e-05,
+      "loss": 0.4636,
+      "step": 129
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3723593573165523e-05,
+      "loss": 0.4212,
+      "step": 130
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3631435048053899e-05,
+      "loss": 0.4241,
+      "step": 131
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3538919861675979e-05,
+      "loss": 0.4698,
+      "step": 132
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3446057100407557e-05,
+      "loss": 0.4292,
+      "step": 133
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3352855884761483e-05,
+      "loss": 0.451,
+      "step": 134
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3259325368491897e-05,
+      "loss": 0.4645,
+      "step": 135
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3165474737695185e-05,
+      "loss": 0.4212,
+      "step": 136
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3071313209907768e-05,
+      "loss": 0.4607,
+      "step": 137
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.2976850033200806e-05,
+      "loss": 0.4603,
+      "step": 138
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.2882094485271894e-05,
+      "loss": 0.4411,
+      "step": 139
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2787055872533867e-05,
+      "loss": 0.4485,
+      "step": 140
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2691743529200749e-05,
+      "loss": 0.4358,
+      "step": 141
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2596166816371005e-05,
+      "loss": 0.4611,
+      "step": 142
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2500335121108151e-05,
+      "loss": 0.4453,
+      "step": 143
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2404257855518782e-05,
+      "loss": 0.4405,
+      "step": 144
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2307944455828178e-05,
+      "loss": 0.44,
+      "step": 145
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.221140438145353e-05,
+      "loss": 0.4187,
+      "step": 146
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2114647114074863e-05,
+      "loss": 0.4409,
+      "step": 147
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2017682156703807e-05,
+      "loss": 0.4257,
+      "step": 148
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1920519032750269e-05,
+      "loss": 0.451,
+      "step": 149
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1823167285087064e-05,
+      "loss": 0.4603,
+      "step": 150
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1725636475112688e-05,
+      "loss": 0.4333,
+      "step": 151
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1627936181812233e-05,
+      "loss": 0.4171,
+      "step": 152
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.153007600081659e-05,
+      "loss": 0.431,
+      "step": 153
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1432065543460016e-05,
+      "loss": 0.431,
+      "step": 154
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1333914435836153e-05,
+      "loss": 0.4502,
+      "step": 155
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1235632317852605e-05,
+      "loss": 0.4467,
+      "step": 156
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1137228842284156e-05,
+      "loss": 0.4352,
+      "step": 157
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1038713673824715e-05,
+      "loss": 0.4316,
+      "step": 158
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.094009648813811e-05,
+      "loss": 0.4109,
+      "step": 159
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0841386970907786e-05,
+      "loss": 0.4148,
+      "step": 160
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.074259481688553e-05,
+      "loss": 0.4276,
+      "step": 161
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0643729728939292e-05,
+      "loss": 0.4433,
+      "step": 162
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0544801417100228e-05,
+      "loss": 0.4566,
+      "step": 163
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.044581959760903e-05,
+      "loss": 0.4442,
+      "step": 164
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0346793991961636e-05,
+      "loss": 0.4308,
+      "step": 165
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0247734325954448e-05,
+      "loss": 0.4585,
+      "step": 166
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0148650328729097e-05,
+      "loss": 0.4423,
+      "step": 167
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0049551731816902e-05,
+      "loss": 0.425,
+      "step": 168
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.950448268183101e-06,
+      "loss": 0.4161,
+      "step": 169
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.85134967127091e-06,
+      "loss": 0.4833,
+      "step": 170
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.752265674045556e-06,
+      "loss": 0.4416,
+      "step": 171
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.653206008038364e-06,
+      "loss": 0.4312,
+      "step": 172
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.554180402390972e-06,
+      "loss": 0.4466,
+      "step": 173
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.455198582899773e-06,
+      "loss": 0.4443,
+      "step": 174
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.356270271060711e-06,
+      "loss": 0.4239,
+      "step": 175
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.257405183114473e-06,
+      "loss": 0.4305,
+      "step": 176
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.158613029092214e-06,
+      "loss": 0.4318,
+      "step": 177
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.059903511861892e-06,
+      "loss": 0.435,
+      "step": 178
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.961286326175288e-06,
+      "loss": 0.4352,
+      "step": 179
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.862771157715847e-06,
+      "loss": 0.4691,
+      "step": 180
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.764367682147396e-06,
+      "loss": 0.499,
+      "step": 181
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.666085564163852e-06,
+      "loss": 0.4437,
+      "step": 182
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.567934456539985e-06,
+      "loss": 0.4366,
+      "step": 183
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.469923999183412e-06,
+      "loss": 0.4503,
+      "step": 184
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.372063818187768e-06,
+      "loss": 0.4338,
+      "step": 185
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.274363524887315e-06,
+      "loss": 0.429,
+      "step": 186
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.176832714912942e-06,
+      "loss": 0.4378,
+      "step": 187
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.079480967249738e-06,
+      "loss": 0.4356,
+      "step": 188
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.982317843296192e-06,
+      "loss": 0.4369,
+      "step": 189
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.885352885925139e-06,
+      "loss": 0.4523,
+      "step": 190
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.788595618546474e-06,
+      "loss": 0.4731,
+      "step": 191
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.692055544171823e-06,
+      "loss": 0.4428,
+      "step": 192
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.595742144481223e-06,
+      "loss": 0.4373,
+      "step": 193
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.4996648788918505e-06,
+      "loss": 0.4646,
+      "step": 194
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.403833183628995e-06,
+      "loss": 0.4454,
+      "step": 195
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.308256470799255e-06,
+      "loss": 0.4864,
+      "step": 196
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.212944127466135e-06,
+      "loss": 0.4201,
+      "step": 197
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.117905514728107e-06,
+      "loss": 0.4181,
+      "step": 198
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.023149966799198e-06,
+      "loss": 0.4277,
+      "step": 199
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.928686790092235e-06,
+      "loss": 0.434,
+      "step": 200
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.834525262304818e-06,
+      "loss": 0.4466,
+      "step": 201
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.740674631508105e-06,
+      "loss": 0.4034,
+      "step": 202
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.64714411523852e-06,
+      "loss": 0.4543,
+      "step": 203
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.553942899592447e-06,
+      "loss": 0.438,
+      "step": 204
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.461080138324025e-06,
+      "loss": 0.4268,
+      "step": 205
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.3685649519461035e-06,
+      "loss": 0.4403,
+      "step": 206
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.276406426834479e-06,
+      "loss": 0.426,
+      "step": 207
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.184613614335476e-06,
+      "loss": 0.4445,
+      "step": 208
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.093195529876963e-06,
+      "loss": 0.457,
+      "step": 209
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.002161152082909e-06,
+      "loss": 0.4338,
+      "step": 210
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.911519421891546e-06,
+      "loss": 0.4253,
+      "step": 211
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.821279241677238e-06,
+      "loss": 0.4142,
+      "step": 212
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.731449474376134e-06,
+      "loss": 0.4384,
+      "step": 213
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.6420389426156815e-06,
+      "loss": 0.4615,
+      "step": 214
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.553056427848136e-06,
+      "loss": 0.4313,
+      "step": 215
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.4645106694880735e-06,
+      "loss": 0.4029,
+      "step": 216
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.376410364054052e-06,
+      "loss": 0.4758,
+      "step": 217
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.288764164314499e-06,
+      "loss": 0.4246,
+      "step": 218
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.201580678437852e-06,
+      "loss": 0.3109,
+      "step": 219
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.11486846914713e-06,
+      "loss": 0.3003,
+      "step": 220
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.028636052878938e-06,
+      "loss": 0.3134,
+      "step": 221
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 4.942891898947024e-06,
+      "loss": 0.3067,
+      "step": 222
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.85764442871047e-06,
+      "loss": 0.2897,
+      "step": 223
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.772902014746583e-06,
+      "loss": 0.3087,
+      "step": 224
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.68867298002859e-06,
+      "loss": 0.2831,
+      "step": 225
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.604965597108192e-06,
+      "loss": 0.2564,
+      "step": 226
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.521788087303074e-06,
+      "loss": 0.2782,
+      "step": 227
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.439148619889451e-06,
+      "loss": 0.3062,
+      "step": 228
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.357055311299736e-06,
+      "loss": 0.2944,
+      "step": 229
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.275516224325356e-06,
+      "loss": 0.2802,
+      "step": 230
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.194539367324888e-06,
+      "loss": 0.2784,
+      "step": 231
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.114132693437511e-06,
+      "loss": 0.2709,
+      "step": 232
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.034304099801891e-06,
+      "loss": 0.2628,
+      "step": 233
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.955061426780562e-06,
+      "loss": 0.2696,
+      "step": 234
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.876412457189883e-06,
+      "loss": 0.2894,
+      "step": 235
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.7983649155356537e-06,
+      "loss": 0.2969,
+      "step": 236
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.7209264672544498e-06,
+      "loss": 0.2931,
+      "step": 237
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.6441047179607616e-06,
+      "loss": 0.2875,
+      "step": 238
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.56790721270001e-06,
+      "loss": 0.2812,
+      "step": 239
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.492341435207509e-06,
+      "loss": 0.275,
+      "step": 240
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.417414807173457e-06,
+      "loss": 0.2766,
+      "step": 241
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.343134687514007e-06,
+      "loss": 0.289,
+      "step": 242
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.269508371648512e-06,
+      "loss": 0.2557,
+      "step": 243
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.1965430907830164e-06,
+      "loss": 0.2795,
+      "step": 244
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.124246011200018e-06,
+      "loss": 0.2802,
+      "step": 245
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.052624233554672e-06,
+      "loss": 0.2957,
+      "step": 246
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.9816847921773616e-06,
+      "loss": 0.2779,
+      "step": 247
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.911434654382843e-06,
+      "loss": 0.2748,
+      "step": 248
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.8418807197859423e-06,
+      "loss": 0.2933,
+      "step": 249
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.773029819623916e-06,
+      "loss": 0.284,
+      "step": 250
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.704888716085513e-06,
+      "loss": 0.312,
+      "step": 251
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.6374641016468416e-06,
+      "loss": 0.2856,
+      "step": 252
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.570762598414052e-06,
+      "loss": 0.2803,
+      "step": 253
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.5047907574729446e-06,
+      "loss": 0.2999,
+      "step": 254
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.4395550582455774e-06,
+      "loss": 0.3072,
+      "step": 255
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.3750619078538663e-06,
+      "loss": 0.3066,
+      "step": 256
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.3113176404903226e-06,
+      "loss": 0.2756,
+      "step": 257
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.24832851679594e-06,
+      "loss": 0.2663,
+      "step": 258
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.186100723245299e-06,
+      "loss": 0.2708,
+      "step": 259
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.1246403715389675e-06,
+      "loss": 0.2755,
+      "step": 260
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.063953498003239e-06,
+      "loss": 0.293,
+      "step": 261
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.004046062997279e-06,
+      "loss": 0.2974,
+      "step": 262
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9449239503277197e-06,
+      "loss": 0.2957,
+      "step": 263
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.8865929666707895e-06,
+      "loss": 0.2666,
+      "step": 264
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.8290588410020116e-06,
+      "loss": 0.2748,
+      "step": 265
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.7723272240335264e-06,
+      "loss": 0.2723,
+      "step": 266
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.7164036876591106e-06,
+      "loss": 0.2937,
+      "step": 267
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6612937244069326e-06,
+      "loss": 0.2651,
+      "step": 268
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.6070027469001115e-06,
+      "loss": 0.3045,
+      "step": 269
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.5535360873251026e-06,
+      "loss": 0.2705,
+      "step": 270
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.5008989969080067e-06,
+      "loss": 0.2898,
+      "step": 271
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4490966453988187e-06,
+      "loss": 0.2939,
+      "step": 272
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.3981341205636823e-06,
+      "loss": 0.2739,
+      "step": 273
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.3480164276851925e-06,
+      "loss": 0.2832,
+      "step": 274
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.2987484890708024e-06,
+      "loss": 0.2772,
+      "step": 275
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.250335143569381e-06,
+      "loss": 0.2604,
+      "step": 276
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.2027811460959648e-06,
+      "loss": 0.2825,
+      "step": 277
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1560911671647535e-06,
+      "loss": 0.2797,
+      "step": 278
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.110269792430393e-06,
+      "loss": 0.281,
+      "step": 279
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.0653215222376045e-06,
+      "loss": 0.2647,
+      "step": 280
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.021250771179173e-06,
+      "loss": 0.2729,
+      "step": 281
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.780618676623722e-07,
+      "loss": 0.2753,
+      "step": 282
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.357590534838534e-07,
+      "loss": 0.2899,
+      "step": 283
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 8.943464834130288e-07,
+      "loss": 0.2782,
+      "step": 284
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.538282247840201e-07,
+      "loss": 0.2581,
+      "step": 285
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.142082570961851e-07,
+      "loss": 0.2585,
+      "step": 286
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.754904716232647e-07,
+      "loss": 0.2535,
+      "step": 287
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.376786710312045e-07,
+      "loss": 0.2747,
+      "step": 288
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 7.007765690046775e-07,
+      "loss": 0.2621,
+      "step": 289
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.647877898823463e-07,
+      "loss": 0.2874,
+      "step": 290
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.297158683008897e-07,
+      "loss": 0.2991,
+      "step": 291
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.955642488478675e-07,
+      "loss": 0.2803,
+      "step": 292
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.623362857233838e-07,
+      "loss": 0.2702,
+      "step": 293
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.30035242410678e-07,
+      "loss": 0.3021,
+      "step": 294
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.986642913555895e-07,
+      "loss": 0.275,
+      "step": 295
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.6822651365497686e-07,
+      "loss": 0.299,
+      "step": 296
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.387248987541182e-07,
+      "loss": 0.272,
+      "step": 297
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.1016234415308553e-07,
+      "loss": 0.3165,
+      "step": 298
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.8254165512218276e-07,
+      "loss": 0.2797,
+      "step": 299
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.5586554442641587e-07,
+      "loss": 0.268,
+      "step": 300
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.3013663205906597e-07,
+      "loss": 0.2876,
+      "step": 301
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.0535744498435993e-07,
+      "loss": 0.2896,
+      "step": 302
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.815304168892918e-07,
+      "loss": 0.2808,
+      "step": 303
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.586578879445922e-07,
+      "loss": 0.2789,
+      "step": 304
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.367421045748908e-07,
+      "loss": 0.2779,
+      "step": 305
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.1578521923808714e-07,
+      "loss": 0.275,
+      "step": 306
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.9578929021394022e-07,
+      "loss": 0.2801,
+      "step": 307
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.767562814019208e-07,
+      "loss": 0.2599,
+      "step": 308
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.586880621283249e-07,
+      "loss": 0.2963,
+      "step": 309
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.41586406962676e-07,
+      "loss": 0.2609,
+      "step": 310
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.2545299554343804e-07,
+      "loss": 0.2838,
+      "step": 311
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.1028941241305047e-07,
+      "loss": 0.2759,
+      "step": 312
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 9.609714686229954e-08,
+      "loss": 0.2766,
+      "step": 313
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 8.287759278405083e-08,
+      "loss": 0.2822,
+      "step": 314
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.063204853634543e-08,
+      "loss": 0.2782,
+      "step": 315
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.9361716814883006e-08,
+      "loss": 0.2725,
+      "step": 316
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.906770453490195e-08,
+      "loss": 0.2831,
+      "step": 317
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 3.9751022722455123e-08,
+      "loss": 0.2906,
+      "step": 318
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.141258641512379e-08,
+      "loss": 0.276,
+      "step": 319
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.4053214572137274e-08,
+      "loss": 0.2958,
+      "step": 320
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.7673629993943954e-08,
+      "loss": 0.2671,
+      "step": 321
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.2274459251220283e-08,
+      "loss": 0.2715,
+      "step": 322
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 7.856232623332238e-09,
+      "loss": 0.3038,
+      "step": 323
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 4.419384046253638e-09,
+      "loss": 0.2781,
+      "step": 324
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.9642510699469096e-09,
+      "loss": 0.3005,
+      "step": 325
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 4.910748252107133e-10,
+      "loss": 0.2983,
+      "step": 326
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.2646,
+      "step": 327
+    },
+    {
+      "epoch": 3.0,
+      "step": 327,
+      "total_flos": 2.240636936655995e+17,
+      "train_loss": 0.49079794065303395,
+      "train_runtime": 21795.7464,
+      "train_samples_per_second": 1.922,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "max_steps": 327,
+  "num_train_epochs": 3,
+  "total_flos": 2.240636936655995e+17,
+  "trial_name": null,
+  "trial_params": null
+}