Upload folder using huggingface_hub

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "Devden/DialectAI-Vicuna-7B",
+  "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": false,
+  "vocab_size": 32000
+}

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 sha256:6e8c46725b83f1a902a194b81fcb74da2b4fb3feca4dc6e0c84a90684ced29f5
+size 9877993490

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63e4e0f859906d040f35a9476760f72dd5f03324e98733d5e867d31b6d24d0f
+size 9894805046

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3cdb72bf689eb1d46431fd78a1d62ad4fc71ad3e93d42e0406c0ccc3ae757b
+size 7180993529

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953670656
+  },
+  "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"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75c96f06b249e57a701db73ce821398e69672027a86d3a44063830602a29ab4
+size 14583

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dae7f45b6bac644ac207a61f43cba6d4b919a4cac22022bbb02907914422f5d
+size 14583

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53c770fe48635faad7fa341007d771781f1397cd47daab5b58f879ffb65f178
+size 14583

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68692af1001e65d02e07ac9974ccf4c332cfb23bc8f89566e1a908b1f2c4a1ed
+size 14583

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2224823d3ab368867dc23cefb65658f627c811f1f24a4bfd52646ef5afbf5e
+size 627

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,3016 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.19707831399502376,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0509721492380452e-08,
+      "loss": 1.1226,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.1019442984760905e-08,
+      "loss": 1.035,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.152916447714136e-08,
+      "loss": 1.0924,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.203888596952181e-08,
+      "loss": 1.0726,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.2548607461902266e-08,
+      "loss": 1.1055,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.305832895428272e-08,
+      "loss": 1.1069,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.356805044666317e-08,
+      "loss": 1.1214,
+      "step": 7
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.407777193904362e-08,
+      "loss": 1.0352,
+      "step": 8
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.458749343142408e-08,
+      "loss": 1.0834,
+      "step": 9
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0509721492380453e-07,
+      "loss": 1.0943,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.1560693641618497e-07,
+      "loss": 1.0665,
+      "step": 11
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.2611665790856543e-07,
+      "loss": 1.038,
+      "step": 12
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3662637940094587e-07,
+      "loss": 1.0735,
+      "step": 13
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4713610089332634e-07,
+      "loss": 1.1459,
+      "step": 14
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5764582238570677e-07,
+      "loss": 1.0382,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6815554387808724e-07,
+      "loss": 1.0474,
+      "step": 16
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.786652653704677e-07,
+      "loss": 1.0968,
+      "step": 17
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8917498686284816e-07,
+      "loss": 1.0508,
+      "step": 18
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.996847083552286e-07,
+      "loss": 1.0399,
+      "step": 19
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.1019442984760907e-07,
+      "loss": 1.0031,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.2070415133998953e-07,
+      "loss": 0.9566,
+      "step": 21
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3121387283236994e-07,
+      "loss": 1.0053,
+      "step": 22
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.417235943247504e-07,
+      "loss": 1.0701,
+      "step": 23
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.5223331581713087e-07,
+      "loss": 1.019,
+      "step": 24
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.627430373095113e-07,
+      "loss": 1.0403,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.7325275880189174e-07,
+      "loss": 0.9973,
+      "step": 26
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.837624802942722e-07,
+      "loss": 0.9612,
+      "step": 27
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9427220178665267e-07,
+      "loss": 0.9842,
+      "step": 28
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.0478192327903313e-07,
+      "loss": 1.01,
+      "step": 29
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.1529164477141355e-07,
+      "loss": 0.9919,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.2580136626379406e-07,
+      "loss": 0.9786,
+      "step": 31
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.3631108775617447e-07,
+      "loss": 0.9469,
+      "step": 32
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.468208092485549e-07,
+      "loss": 0.9505,
+      "step": 33
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.573305307409354e-07,
+      "loss": 0.9357,
+      "step": 34
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.678402522333158e-07,
+      "loss": 1.0086,
+      "step": 35
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.7834997372569633e-07,
+      "loss": 1.0187,
+      "step": 36
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.8885969521807674e-07,
+      "loss": 0.9877,
+      "step": 37
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.993694167104572e-07,
+      "loss": 0.8856,
+      "step": 38
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.0987913820283767e-07,
+      "loss": 0.9854,
+      "step": 39
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.2038885969521813e-07,
+      "loss": 1.0107,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.3089858118759854e-07,
+      "loss": 0.933,
+      "step": 41
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4140830267997906e-07,
+      "loss": 0.9874,
+      "step": 42
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.5191802417235947e-07,
+      "loss": 0.9812,
+      "step": 43
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.624277456647399e-07,
+      "loss": 0.9467,
+      "step": 44
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.729374671571204e-07,
+      "loss": 0.9949,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.834471886495008e-07,
+      "loss": 1.005,
+      "step": 46
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.939569101418812e-07,
+      "loss": 0.935,
+      "step": 47
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.044666316342617e-07,
+      "loss": 0.9481,
+      "step": 48
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.149763531266421e-07,
+      "loss": 0.9681,
+      "step": 49
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.254860746190226e-07,
+      "loss": 0.9508,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.359957961114031e-07,
+      "loss": 0.8342,
+      "step": 51
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.465055176037835e-07,
+      "loss": 0.9349,
+      "step": 52
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.57015239096164e-07,
+      "loss": 0.9312,
+      "step": 53
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.675249605885444e-07,
+      "loss": 0.8591,
+      "step": 54
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.780346820809249e-07,
+      "loss": 0.9763,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.885444035733053e-07,
+      "loss": 0.9114,
+      "step": 56
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.990541250656859e-07,
+      "loss": 0.9064,
+      "step": 57
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.095638465580663e-07,
+      "loss": 0.9438,
+      "step": 58
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.200735680504468e-07,
+      "loss": 0.865,
+      "step": 59
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.305832895428271e-07,
+      "loss": 0.8593,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.410930110352076e-07,
+      "loss": 0.9031,
+      "step": 61
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.516027325275881e-07,
+      "loss": 0.9431,
+      "step": 62
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.621124540199684e-07,
+      "loss": 0.8947,
+      "step": 63
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.726221755123489e-07,
+      "loss": 0.9237,
+      "step": 64
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.831318970047295e-07,
+      "loss": 0.9067,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.936416184971098e-07,
+      "loss": 0.905,
+      "step": 66
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.041513399894903e-07,
+      "loss": 0.8822,
+      "step": 67
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.146610614818708e-07,
+      "loss": 0.9116,
+      "step": 68
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.251707829742513e-07,
+      "loss": 0.8923,
+      "step": 69
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.356805044666316e-07,
+      "loss": 1.0088,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.461902259590121e-07,
+      "loss": 0.9253,
+      "step": 71
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.566999474513927e-07,
+      "loss": 0.875,
+      "step": 72
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.672096689437731e-07,
+      "loss": 0.9378,
+      "step": 73
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.777193904361535e-07,
+      "loss": 0.9202,
+      "step": 74
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.88229111928534e-07,
+      "loss": 0.9185,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.987388334209144e-07,
+      "loss": 0.9362,
+      "step": 76
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.092485549132949e-07,
+      "loss": 0.8857,
+      "step": 77
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.197582764056753e-07,
+      "loss": 0.8658,
+      "step": 78
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.302679978980557e-07,
+      "loss": 0.8919,
+      "step": 79
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.407777193904363e-07,
+      "loss": 0.9018,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.512874408828168e-07,
+      "loss": 0.8743,
+      "step": 81
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.617971623751971e-07,
+      "loss": 0.9393,
+      "step": 82
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.723068838675776e-07,
+      "loss": 0.8945,
+      "step": 83
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.828166053599581e-07,
+      "loss": 0.9197,
+      "step": 84
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.933263268523384e-07,
+      "loss": 0.9709,
+      "step": 85
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.038360483447189e-07,
+      "loss": 0.8581,
+      "step": 86
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.143457698370995e-07,
+      "loss": 0.8924,
+      "step": 87
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.248554913294798e-07,
+      "loss": 0.8823,
+      "step": 88
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.353652128218603e-07,
+      "loss": 0.8701,
+      "step": 89
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.458749343142408e-07,
+      "loss": 0.8422,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.563846558066212e-07,
+      "loss": 0.8954,
+      "step": 91
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.668943772990016e-07,
+      "loss": 0.9193,
+      "step": 92
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.774040987913822e-07,
+      "loss": 0.8889,
+      "step": 93
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.879138202837624e-07,
+      "loss": 0.8538,
+      "step": 94
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.98423541776143e-07,
+      "loss": 0.8416,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0089332632685235e-06,
+      "loss": 0.9169,
+      "step": 96
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0194429847609039e-06,
+      "loss": 0.8734,
+      "step": 97
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0299527062532843e-06,
+      "loss": 0.9196,
+      "step": 98
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.040462427745665e-06,
+      "loss": 0.9213,
+      "step": 99
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0509721492380451e-06,
+      "loss": 0.8665,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0614818707304257e-06,
+      "loss": 0.867,
+      "step": 101
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0719915922228062e-06,
+      "loss": 0.8649,
+      "step": 102
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0825013137151866e-06,
+      "loss": 0.8447,
+      "step": 103
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.093011035207567e-06,
+      "loss": 0.865,
+      "step": 104
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1035207566999476e-06,
+      "loss": 0.9243,
+      "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.114030478192328e-06,
+      "loss": 0.916,
+      "step": 106
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1245401996847084e-06,
+      "loss": 0.8486,
+      "step": 107
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1350499211770888e-06,
+      "loss": 0.9284,
+      "step": 108
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1455596426694692e-06,
+      "loss": 0.8814,
+      "step": 109
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1560693641618499e-06,
+      "loss": 0.9023,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1665790856542303e-06,
+      "loss": 0.9036,
+      "step": 111
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1770888071466107e-06,
+      "loss": 0.839,
+      "step": 112
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.187598528638991e-06,
+      "loss": 0.83,
+      "step": 113
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1981082501313717e-06,
+      "loss": 0.8136,
+      "step": 114
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2086179716237521e-06,
+      "loss": 0.8475,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2191276931161325e-06,
+      "loss": 0.8561,
+      "step": 116
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.229637414608513e-06,
+      "loss": 0.8307,
+      "step": 117
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2401471361008936e-06,
+      "loss": 0.8672,
+      "step": 118
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.250656857593274e-06,
+      "loss": 0.9235,
+      "step": 119
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2611665790856542e-06,
+      "loss": 0.9005,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2716763005780348e-06,
+      "loss": 0.9471,
+      "step": 121
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2821860220704152e-06,
+      "loss": 0.8485,
+      "step": 122
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2926957435627956e-06,
+      "loss": 0.8306,
+      "step": 123
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3032054650551763e-06,
+      "loss": 0.8953,
+      "step": 124
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3137151865475567e-06,
+      "loss": 0.8887,
+      "step": 125
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3242249080399369e-06,
+      "loss": 0.9285,
+      "step": 126
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3347346295323175e-06,
+      "loss": 0.8876,
+      "step": 127
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3452443510246979e-06,
+      "loss": 0.8815,
+      "step": 128
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3557540725170785e-06,
+      "loss": 0.8883,
+      "step": 129
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.366263794009459e-06,
+      "loss": 0.8416,
+      "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3767735155018393e-06,
+      "loss": 0.8636,
+      "step": 131
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3872832369942195e-06,
+      "loss": 0.9279,
+      "step": 132
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3977929584866002e-06,
+      "loss": 0.8635,
+      "step": 133
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.4083026799789806e-06,
+      "loss": 0.8704,
+      "step": 134
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.4188124014713612e-06,
+      "loss": 0.9254,
+      "step": 135
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.4293221229637416e-06,
+      "loss": 0.8566,
+      "step": 136
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.439831844456122e-06,
+      "loss": 0.8802,
+      "step": 137
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.4503415659485026e-06,
+      "loss": 0.8882,
+      "step": 138
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.4608512874408828e-06,
+      "loss": 0.8894,
+      "step": 139
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4713610089332632e-06,
+      "loss": 0.8016,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4818707304256439e-06,
+      "loss": 0.843,
+      "step": 141
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4923804519180243e-06,
+      "loss": 0.8225,
+      "step": 142
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.502890173410405e-06,
+      "loss": 0.9416,
+      "step": 143
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5133998949027853e-06,
+      "loss": 0.8928,
+      "step": 144
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5239096163951655e-06,
+      "loss": 0.8778,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5344193378875461e-06,
+      "loss": 0.8778,
+      "step": 146
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5449290593799265e-06,
+      "loss": 0.8203,
+      "step": 147
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.555438780872307e-06,
+      "loss": 0.8298,
+      "step": 148
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5659485023646876e-06,
+      "loss": 0.8581,
+      "step": 149
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.576458223857068e-06,
+      "loss": 0.8292,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5869679453494482e-06,
+      "loss": 0.8326,
+      "step": 151
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5974776668418288e-06,
+      "loss": 0.8218,
+      "step": 152
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6079873883342092e-06,
+      "loss": 0.845,
+      "step": 153
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6184971098265898e-06,
+      "loss": 0.8576,
+      "step": 154
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6290068313189703e-06,
+      "loss": 0.87,
+      "step": 155
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6395165528113507e-06,
+      "loss": 0.9236,
+      "step": 156
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6500262743037309e-06,
+      "loss": 0.8897,
+      "step": 157
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6605359957961115e-06,
+      "loss": 0.8678,
+      "step": 158
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.671045717288492e-06,
+      "loss": 0.8475,
+      "step": 159
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6815554387808725e-06,
+      "loss": 0.8253,
+      "step": 160
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.692065160273253e-06,
+      "loss": 0.8887,
+      "step": 161
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.7025748817656336e-06,
+      "loss": 0.9127,
+      "step": 162
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.7130846032580138e-06,
+      "loss": 0.8863,
+      "step": 163
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.7235943247503942e-06,
+      "loss": 0.8783,
+      "step": 164
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.7341040462427746e-06,
+      "loss": 0.8765,
+      "step": 165
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.7446137677351552e-06,
+      "loss": 0.8933,
+      "step": 166
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.7551234892275356e-06,
+      "loss": 0.8049,
+      "step": 167
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.7656332107199162e-06,
+      "loss": 0.8465,
+      "step": 168
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.7761429322122964e-06,
+      "loss": 0.8307,
+      "step": 169
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.7866526537046768e-06,
+      "loss": 0.8415,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.7971623751970575e-06,
+      "loss": 0.9014,
+      "step": 171
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8076720966894379e-06,
+      "loss": 0.8472,
+      "step": 172
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.8447,
+      "step": 173
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.828691539674199e-06,
+      "loss": 0.8928,
+      "step": 174
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8392012611665791e-06,
+      "loss": 0.9114,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8497109826589595e-06,
+      "loss": 0.8536,
+      "step": 176
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8602207041513401e-06,
+      "loss": 0.8554,
+      "step": 177
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8707304256437206e-06,
+      "loss": 0.7809,
+      "step": 178
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8812401471361012e-06,
+      "loss": 0.8485,
+      "step": 179
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8917498686284816e-06,
+      "loss": 0.8215,
+      "step": 180
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.902259590120862e-06,
+      "loss": 0.8399,
+      "step": 181
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9127693116132424e-06,
+      "loss": 0.8658,
+      "step": 182
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.923279033105623e-06,
+      "loss": 0.8194,
+      "step": 183
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9337887545980032e-06,
+      "loss": 0.9043,
+      "step": 184
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9442984760903836e-06,
+      "loss": 0.806,
+      "step": 185
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9548081975827645e-06,
+      "loss": 0.8179,
+      "step": 186
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.965317919075145e-06,
+      "loss": 0.8461,
+      "step": 187
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.975827640567525e-06,
+      "loss": 0.8699,
+      "step": 188
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9863373620599057e-06,
+      "loss": 0.9114,
+      "step": 189
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.996847083552286e-06,
+      "loss": 0.846,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.0073568050446665e-06,
+      "loss": 0.8631,
+      "step": 191
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.017866526537047e-06,
+      "loss": 0.8162,
+      "step": 192
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.0283762480294274e-06,
+      "loss": 0.8563,
+      "step": 193
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.0388859695218078e-06,
+      "loss": 0.8067,
+      "step": 194
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.049395691014188e-06,
+      "loss": 0.8742,
+      "step": 195
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.0599054125065686e-06,
+      "loss": 0.8952,
+      "step": 196
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.0704151339989494e-06,
+      "loss": 0.8416,
+      "step": 197
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.08092485549133e-06,
+      "loss": 0.8678,
+      "step": 198
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.0914345769837102e-06,
+      "loss": 0.8226,
+      "step": 199
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.1019442984760902e-06,
+      "loss": 0.7962,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.112454019968471e-06,
+      "loss": 0.8959,
+      "step": 201
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.1229637414608515e-06,
+      "loss": 0.8077,
+      "step": 202
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.133473462953232e-06,
+      "loss": 0.8309,
+      "step": 203
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.1439831844456123e-06,
+      "loss": 0.825,
+      "step": 204
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.154492905937993e-06,
+      "loss": 0.8421,
+      "step": 205
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.165002627430373e-06,
+      "loss": 0.8885,
+      "step": 206
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.1755123489227535e-06,
+      "loss": 0.8628,
+      "step": 207
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.186022070415134e-06,
+      "loss": 0.8114,
+      "step": 208
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.1965317919075148e-06,
+      "loss": 0.8257,
+      "step": 209
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.207041513399895e-06,
+      "loss": 0.8555,
+      "step": 210
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.2175512348922756e-06,
+      "loss": 0.8733,
+      "step": 211
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.228060956384656e-06,
+      "loss": 0.8273,
+      "step": 212
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.2385706778770364e-06,
+      "loss": 0.8197,
+      "step": 213
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.249080399369417e-06,
+      "loss": 0.7955,
+      "step": 214
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.2595901208617972e-06,
+      "loss": 0.806,
+      "step": 215
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.2700998423541777e-06,
+      "loss": 0.8325,
+      "step": 216
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.2806095638465585e-06,
+      "loss": 0.8283,
+      "step": 217
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.2911192853389385e-06,
+      "loss": 0.7938,
+      "step": 218
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.301629006831319e-06,
+      "loss": 0.8119,
+      "step": 219
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.3121387283236997e-06,
+      "loss": 0.8418,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.32264844981608e-06,
+      "loss": 0.8606,
+      "step": 221
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.3331581713084605e-06,
+      "loss": 0.8541,
+      "step": 222
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.343667892800841e-06,
+      "loss": 0.8402,
+      "step": 223
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.3541776142932214e-06,
+      "loss": 0.8204,
+      "step": 224
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.3646873357856018e-06,
+      "loss": 0.8525,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.375197057277982e-06,
+      "loss": 0.8229,
+      "step": 226
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.3857067787703626e-06,
+      "loss": 0.7948,
+      "step": 227
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.3962165002627434e-06,
+      "loss": 0.8312,
+      "step": 228
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.406726221755124e-06,
+      "loss": 0.8345,
+      "step": 229
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.4172359432475043e-06,
+      "loss": 0.816,
+      "step": 230
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.4277456647398847e-06,
+      "loss": 0.7643,
+      "step": 231
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.438255386232265e-06,
+      "loss": 0.8797,
+      "step": 232
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.4487651077246455e-06,
+      "loss": 0.8267,
+      "step": 233
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.459274829217026e-06,
+      "loss": 0.834,
+      "step": 234
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.4697845507094063e-06,
+      "loss": 0.8035,
+      "step": 235
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.480294272201787e-06,
+      "loss": 0.8127,
+      "step": 236
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.490803993694167e-06,
+      "loss": 0.8404,
+      "step": 237
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.501313715186548e-06,
+      "loss": 0.8017,
+      "step": 238
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.5118234366789284e-06,
+      "loss": 0.783,
+      "step": 239
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.5223331581713084e-06,
+      "loss": 0.8523,
+      "step": 240
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.5328428796636888e-06,
+      "loss": 0.8818,
+      "step": 241
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.5433526011560696e-06,
+      "loss": 0.8113,
+      "step": 242
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.55386232264845e-06,
+      "loss": 0.8489,
+      "step": 243
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.5643720441408304e-06,
+      "loss": 0.8477,
+      "step": 244
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.574881765633211e-06,
+      "loss": 0.8228,
+      "step": 245
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.5853914871255913e-06,
+      "loss": 0.8161,
+      "step": 246
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.595901208617972e-06,
+      "loss": 0.8977,
+      "step": 247
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.6064109301103525e-06,
+      "loss": 0.797,
+      "step": 248
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.616920651602733e-06,
+      "loss": 0.7946,
+      "step": 249
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.6274303730951133e-06,
+      "loss": 0.8672,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.6379400945874937e-06,
+      "loss": 0.8719,
+      "step": 251
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.6484498160798737e-06,
+      "loss": 0.81,
+      "step": 252
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.658959537572254e-06,
+      "loss": 0.7862,
+      "step": 253
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.669469259064635e-06,
+      "loss": 0.8419,
+      "step": 254
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.6799789805570154e-06,
+      "loss": 0.8263,
+      "step": 255
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.6904887020493958e-06,
+      "loss": 0.9026,
+      "step": 256
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.700998423541776e-06,
+      "loss": 0.8,
+      "step": 257
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.711508145034157e-06,
+      "loss": 0.7938,
+      "step": 258
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.7220178665265374e-06,
+      "loss": 0.857,
+      "step": 259
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.732527588018918e-06,
+      "loss": 0.7823,
+      "step": 260
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.7430373095112983e-06,
+      "loss": 0.8051,
+      "step": 261
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.7535470310036787e-06,
+      "loss": 0.7843,
+      "step": 262
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.7640567524960595e-06,
+      "loss": 0.8237,
+      "step": 263
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.774566473988439e-06,
+      "loss": 0.8013,
+      "step": 264
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.78507619548082e-06,
+      "loss": 0.8332,
+      "step": 265
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.7955859169732003e-06,
+      "loss": 0.863,
+      "step": 266
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.8060956384655807e-06,
+      "loss": 0.789,
+      "step": 267
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.816605359957961e-06,
+      "loss": 0.7895,
+      "step": 268
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.8271150814503416e-06,
+      "loss": 0.8474,
+      "step": 269
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.8376248029427224e-06,
+      "loss": 0.9381,
+      "step": 270
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.848134524435103e-06,
+      "loss": 0.7906,
+      "step": 271
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.858644245927483e-06,
+      "loss": 0.8295,
+      "step": 272
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.8691539674198636e-06,
+      "loss": 0.8607,
+      "step": 273
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.879663688912244e-06,
+      "loss": 0.8294,
+      "step": 274
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.890173410404625e-06,
+      "loss": 0.8384,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9006831318970053e-06,
+      "loss": 0.8402,
+      "step": 276
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9111928533893853e-06,
+      "loss": 0.8587,
+      "step": 277
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9217025748817657e-06,
+      "loss": 0.7734,
+      "step": 278
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.932212296374146e-06,
+      "loss": 0.7796,
+      "step": 279
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9427220178665265e-06,
+      "loss": 0.8167,
+      "step": 280
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9532317393589073e-06,
+      "loss": 0.8551,
+      "step": 281
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9637414608512877e-06,
+      "loss": 0.8125,
+      "step": 282
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.974251182343668e-06,
+      "loss": 0.7928,
+      "step": 283
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9847609038360486e-06,
+      "loss": 0.7864,
+      "step": 284
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.995270625328429e-06,
+      "loss": 0.8908,
+      "step": 285
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.00578034682081e-06,
+      "loss": 0.8098,
+      "step": 286
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.0162900683131902e-06,
+      "loss": 0.784,
+      "step": 287
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.0267997898055706e-06,
+      "loss": 0.8152,
+      "step": 288
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.0373095112979506e-06,
+      "loss": 0.8079,
+      "step": 289
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.047819232790331e-06,
+      "loss": 0.8098,
+      "step": 290
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.0583289542827114e-06,
+      "loss": 0.8008,
+      "step": 291
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.0688386757750923e-06,
+      "loss": 0.8185,
+      "step": 292
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.0793483972674727e-06,
+      "loss": 0.8014,
+      "step": 293
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.089858118759853e-06,
+      "loss": 0.7557,
+      "step": 294
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.1003678402522335e-06,
+      "loss": 0.7783,
+      "step": 295
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.110877561744614e-06,
+      "loss": 0.8218,
+      "step": 296
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.1213872832369948e-06,
+      "loss": 0.8198,
+      "step": 297
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.131897004729375e-06,
+      "loss": 0.8062,
+      "step": 298
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.1424067262217556e-06,
+      "loss": 0.8037,
+      "step": 299
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.152916447714136e-06,
+      "loss": 0.8203,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.163426169206516e-06,
+      "loss": 0.8182,
+      "step": 301
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.1739358906988964e-06,
+      "loss": 0.8488,
+      "step": 302
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.1844456121912772e-06,
+      "loss": 0.81,
+      "step": 303
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.1949553336836576e-06,
+      "loss": 0.8073,
+      "step": 304
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.205465055176038e-06,
+      "loss": 0.8169,
+      "step": 305
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.2159747766684185e-06,
+      "loss": 0.8016,
+      "step": 306
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.226484498160799e-06,
+      "loss": 0.8066,
+      "step": 307
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.2369942196531797e-06,
+      "loss": 0.8052,
+      "step": 308
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.24750394114556e-06,
+      "loss": 0.7699,
+      "step": 309
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.2580136626379405e-06,
+      "loss": 0.8497,
+      "step": 310
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.268523384130321e-06,
+      "loss": 0.7892,
+      "step": 311
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.2790331056227013e-06,
+      "loss": 0.8514,
+      "step": 312
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.289542827115082e-06,
+      "loss": 0.7749,
+      "step": 313
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.3000525486074617e-06,
+      "loss": 0.7904,
+      "step": 314
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.3105622700998426e-06,
+      "loss": 0.7986,
+      "step": 315
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.321071991592223e-06,
+      "loss": 0.779,
+      "step": 316
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.3315817130846034e-06,
+      "loss": 0.8299,
+      "step": 317
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.342091434576984e-06,
+      "loss": 0.7993,
+      "step": 318
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.3526011560693642e-06,
+      "loss": 0.8412,
+      "step": 319
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.363110877561745e-06,
+      "loss": 0.8111,
+      "step": 320
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.3736205990541255e-06,
+      "loss": 0.8285,
+      "step": 321
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.384130320546506e-06,
+      "loss": 0.8332,
+      "step": 322
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.3946400420388863e-06,
+      "loss": 0.8837,
+      "step": 323
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.405149763531267e-06,
+      "loss": 0.8275,
+      "step": 324
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.4156594850236475e-06,
+      "loss": 0.8397,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.4261692065160275e-06,
+      "loss": 0.835,
+      "step": 326
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.436678928008408e-06,
+      "loss": 0.8153,
+      "step": 327
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.4471886495007883e-06,
+      "loss": 0.8656,
+      "step": 328
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.4576983709931688e-06,
+      "loss": 0.8272,
+      "step": 329
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.468208092485549e-06,
+      "loss": 0.8442,
+      "step": 330
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.47871781397793e-06,
+      "loss": 0.8567,
+      "step": 331
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.4892275354703104e-06,
+      "loss": 0.7913,
+      "step": 332
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.499737256962691e-06,
+      "loss": 0.8499,
+      "step": 333
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.5102469784550712e-06,
+      "loss": 0.7344,
+      "step": 334
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.5207566999474516e-06,
+      "loss": 0.8471,
+      "step": 335
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.5312664214398325e-06,
+      "loss": 0.8772,
+      "step": 336
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.541776142932213e-06,
+      "loss": 0.9182,
+      "step": 337
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.552285864424593e-06,
+      "loss": 0.7932,
+      "step": 338
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.5627955859169733e-06,
+      "loss": 0.8078,
+      "step": 339
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.5733053074093537e-06,
+      "loss": 0.7449,
+      "step": 340
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.583815028901734e-06,
+      "loss": 0.8372,
+      "step": 341
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.594324750394115e-06,
+      "loss": 0.8061,
+      "step": 342
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.6048344718864954e-06,
+      "loss": 0.7962,
+      "step": 343
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.6153441933788758e-06,
+      "loss": 0.7833,
+      "step": 344
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.625853914871256e-06,
+      "loss": 0.8089,
+      "step": 345
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.8276,
+      "step": 346
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.6468733578560174e-06,
+      "loss": 0.7673,
+      "step": 347
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.657383079348398e-06,
+      "loss": 0.85,
+      "step": 348
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.6678928008407782e-06,
+      "loss": 0.8004,
+      "step": 349
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.6784025223331582e-06,
+      "loss": 0.8385,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.6889122438255386e-06,
+      "loss": 0.8413,
+      "step": 351
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.699421965317919e-06,
+      "loss": 0.8346,
+      "step": 352
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.7099316868103e-06,
+      "loss": 0.7425,
+      "step": 353
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.7204414083026803e-06,
+      "loss": 0.8421,
+      "step": 354
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.7309511297950607e-06,
+      "loss": 0.8623,
+      "step": 355
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.741460851287441e-06,
+      "loss": 0.7881,
+      "step": 356
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.7519705727798215e-06,
+      "loss": 0.8611,
+      "step": 357
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.7624802942722024e-06,
+      "loss": 0.8196,
+      "step": 358
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.7729900157645828e-06,
+      "loss": 0.8406,
+      "step": 359
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.783499737256963e-06,
+      "loss": 0.7493,
+      "step": 360
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.7940094587493436e-06,
+      "loss": 0.7704,
+      "step": 361
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.804519180241724e-06,
+      "loss": 0.7866,
+      "step": 362
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.815028901734104e-06,
+      "loss": 0.8068,
+      "step": 363
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.825538623226485e-06,
+      "loss": 0.7198,
+      "step": 364
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.836048344718865e-06,
+      "loss": 0.8212,
+      "step": 365
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.846558066211246e-06,
+      "loss": 0.777,
+      "step": 366
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.857067787703626e-06,
+      "loss": 0.8647,
+      "step": 367
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.8675775091960065e-06,
+      "loss": 0.7956,
+      "step": 368
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.878087230688387e-06,
+      "loss": 0.8092,
+      "step": 369
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.888596952180767e-06,
+      "loss": 0.7958,
+      "step": 370
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.899106673673148e-06,
+      "loss": 0.85,
+      "step": 371
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.909616395165529e-06,
+      "loss": 0.7967,
+      "step": 372
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.920126116657909e-06,
+      "loss": 0.7974,
+      "step": 373
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.93063583815029e-06,
+      "loss": 0.7822,
+      "step": 374
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.941145559642669e-06,
+      "loss": 0.8445,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.95165528113505e-06,
+      "loss": 0.8093,
+      "step": 376
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.96216500262743e-06,
+      "loss": 0.8476,
+      "step": 377
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.9726747241198114e-06,
+      "loss": 0.8214,
+      "step": 378
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.983184445612192e-06,
+      "loss": 0.8533,
+      "step": 379
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.993694167104572e-06,
+      "loss": 0.7723,
+      "step": 380
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.004203888596953e-06,
+      "loss": 0.807,
+      "step": 381
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.014713610089333e-06,
+      "loss": 0.8492,
+      "step": 382
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.0252233315817135e-06,
+      "loss": 0.8389,
+      "step": 383
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.035733053074094e-06,
+      "loss": 0.7838,
+      "step": 384
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.046242774566474e-06,
+      "loss": 0.8013,
+      "step": 385
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.056752496058855e-06,
+      "loss": 0.8072,
+      "step": 386
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.067262217551235e-06,
+      "loss": 0.8006,
+      "step": 387
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.0777719390436155e-06,
+      "loss": 0.8104,
+      "step": 388
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.088281660535996e-06,
+      "loss": 0.8065,
+      "step": 389
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.098791382028376e-06,
+      "loss": 0.7914,
+      "step": 390
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.109301103520757e-06,
+      "loss": 0.8036,
+      "step": 391
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.119810825013137e-06,
+      "loss": 0.8041,
+      "step": 392
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.130320546505518e-06,
+      "loss": 0.7746,
+      "step": 393
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.140830267997899e-06,
+      "loss": 0.765,
+      "step": 394
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.151339989490279e-06,
+      "loss": 0.7855,
+      "step": 395
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.16184971098266e-06,
+      "loss": 0.7624,
+      "step": 396
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.17235943247504e-06,
+      "loss": 0.7905,
+      "step": 397
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.1828691539674205e-06,
+      "loss": 0.7837,
+      "step": 398
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.193378875459801e-06,
+      "loss": 0.8263,
+      "step": 399
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.2038885969521805e-06,
+      "loss": 0.7906,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.214398318444562e-06,
+      "loss": 0.829,
+      "step": 401
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.224908039936942e-06,
+      "loss": 0.8397,
+      "step": 402
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.2354177614293225e-06,
+      "loss": 0.8143,
+      "step": 403
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.245927482921703e-06,
+      "loss": 0.8318,
+      "step": 404
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.256437204414083e-06,
+      "loss": 0.7841,
+      "step": 405
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.266946925906464e-06,
+      "loss": 0.8352,
+      "step": 406
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.277456647398844e-06,
+      "loss": 0.8099,
+      "step": 407
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.287966368891225e-06,
+      "loss": 0.7887,
+      "step": 408
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.298476090383605e-06,
+      "loss": 0.8013,
+      "step": 409
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.308985811875986e-06,
+      "loss": 0.7538,
+      "step": 410
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.319495533368367e-06,
+      "loss": 0.8405,
+      "step": 411
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.330005254860746e-06,
+      "loss": 0.7894,
+      "step": 412
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.340514976353127e-06,
+      "loss": 0.7704,
+      "step": 413
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.351024697845507e-06,
+      "loss": 0.781,
+      "step": 414
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.3615344193378875e-06,
+      "loss": 0.7339,
+      "step": 415
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.372044140830268e-06,
+      "loss": 0.8059,
+      "step": 416
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.382553862322649e-06,
+      "loss": 0.7805,
+      "step": 417
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.3930635838150296e-06,
+      "loss": 0.8449,
+      "step": 418
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.40357330530741e-06,
+      "loss": 0.8233,
+      "step": 419
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.41408302679979e-06,
+      "loss": 0.8101,
+      "step": 420
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.424592748292171e-06,
+      "loss": 0.7501,
+      "step": 421
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.435102469784551e-06,
+      "loss": 0.8055,
+      "step": 422
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.445612191276932e-06,
+      "loss": 0.8196,
+      "step": 423
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.456121912769312e-06,
+      "loss": 0.8087,
+      "step": 424
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.4666316342616924e-06,
+      "loss": 0.8175,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.477141355754073e-06,
+      "loss": 0.7983,
+      "step": 426
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.487651077246453e-06,
+      "loss": 0.7686,
+      "step": 427
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.498160798738834e-06,
+      "loss": 0.8567,
+      "step": 428
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.508670520231214e-06,
+      "loss": 0.8355,
+      "step": 429
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.5191802417235945e-06,
+      "loss": 0.7395,
+      "step": 430
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.529689963215975e-06,
+      "loss": 0.7831,
+      "step": 431
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.540199684708355e-06,
+      "loss": 0.7781,
+      "step": 432
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.5507094062007366e-06,
+      "loss": 0.7756,
+      "step": 433
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.561219127693117e-06,
+      "loss": 0.7922,
+      "step": 434
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.571728849185497e-06,
+      "loss": 0.743,
+      "step": 435
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.582238570677877e-06,
+      "loss": 0.7949,
+      "step": 436
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.592748292170257e-06,
+      "loss": 0.766,
+      "step": 437
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.603258013662638e-06,
+      "loss": 0.7464,
+      "step": 438
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.613767735155019e-06,
+      "loss": 0.824,
+      "step": 439
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6242774566473994e-06,
+      "loss": 0.7683,
+      "step": 440
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.63478717813978e-06,
+      "loss": 0.8004,
+      "step": 441
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.64529689963216e-06,
+      "loss": 0.8034,
+      "step": 442
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.655806621124541e-06,
+      "loss": 0.7548,
+      "step": 443
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.666316342616921e-06,
+      "loss": 0.8016,
+      "step": 444
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.6768260641093015e-06,
+      "loss": 0.7472,
+      "step": 445
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.687335785601682e-06,
+      "loss": 0.7707,
+      "step": 446
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.697845507094062e-06,
+      "loss": 0.8231,
+      "step": 447
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.708355228586443e-06,
+      "loss": 0.851,
+      "step": 448
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.718864950078823e-06,
+      "loss": 0.7595,
+      "step": 449
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.7293746715712036e-06,
+      "loss": 0.795,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.739884393063584e-06,
+      "loss": 0.8017,
+      "step": 451
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.750394114555964e-06,
+      "loss": 0.7624,
+      "step": 452
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.760903836048345e-06,
+      "loss": 0.7707,
+      "step": 453
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.771413557540725e-06,
+      "loss": 0.8561,
+      "step": 454
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.7819232790331065e-06,
+      "loss": 0.7829,
+      "step": 455
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.792433000525487e-06,
+      "loss": 0.8147,
+      "step": 456
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.802942722017867e-06,
+      "loss": 0.7943,
+      "step": 457
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.813452443510248e-06,
+      "loss": 0.8013,
+      "step": 458
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.823962165002628e-06,
+      "loss": 0.7784,
+      "step": 459
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.8344718864950085e-06,
+      "loss": 0.7541,
+      "step": 460
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.844981607987388e-06,
+      "loss": 0.7895,
+      "step": 461
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.855491329479769e-06,
+      "loss": 0.8256,
+      "step": 462
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.86600105097215e-06,
+      "loss": 0.7822,
+      "step": 463
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.87651077246453e-06,
+      "loss": 0.8249,
+      "step": 464
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.8870204939569106e-06,
+      "loss": 0.8216,
+      "step": 465
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.897530215449291e-06,
+      "loss": 0.7614,
+      "step": 466
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.908039936941671e-06,
+      "loss": 0.7757,
+      "step": 467
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.918549658434052e-06,
+      "loss": 0.7565,
+      "step": 468
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.929059379926432e-06,
+      "loss": 0.8064,
+      "step": 469
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.939569101418813e-06,
+      "loss": 0.7756,
+      "step": 470
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.950078822911194e-06,
+      "loss": 0.798,
+      "step": 471
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.960588544403574e-06,
+      "loss": 0.7709,
+      "step": 472
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.971098265895954e-06,
+      "loss": 0.7985,
+      "step": 473
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.981607987388334e-06,
+      "loss": 0.7588,
+      "step": 474
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.992117708880715e-06,
+      "loss": 0.7575,
+      "step": 475
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.002627430373096e-06,
+      "loss": 0.7779,
+      "step": 476
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.0131371518654755e-06,
+      "loss": 0.7804,
+      "step": 477
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.023646873357857e-06,
+      "loss": 0.7687,
+      "step": 478
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.034156594850237e-06,
+      "loss": 0.8063,
+      "step": 479
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.044666316342617e-06,
+      "loss": 0.8207,
+      "step": 480
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.055176037834998e-06,
+      "loss": 0.7946,
+      "step": 481
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.0656857593273776e-06,
+      "loss": 0.8119,
+      "step": 482
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.076195480819759e-06,
+      "loss": 0.8291,
+      "step": 483
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.086705202312139e-06,
+      "loss": 0.7851,
+      "step": 484
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.09721492380452e-06,
+      "loss": 0.8316,
+      "step": 485
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.1077246452969e-06,
+      "loss": 0.7544,
+      "step": 486
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.1182343667892805e-06,
+      "loss": 0.7991,
+      "step": 487
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.128744088281661e-06,
+      "loss": 0.7846,
+      "step": 488
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.139253809774042e-06,
+      "loss": 0.8036,
+      "step": 489
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.149763531266422e-06,
+      "loss": 0.8046,
+      "step": 490
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.160273252758803e-06,
+      "loss": 0.8217,
+      "step": 491
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.1707829742511825e-06,
+      "loss": 0.792,
+      "step": 492
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.181292695743563e-06,
+      "loss": 0.7791,
+      "step": 493
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.191802417235944e-06,
+      "loss": 0.8335,
+      "step": 494
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5.202312138728324e-06,
+      "loss": 0.8251,
+      "step": 495
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5.212821860220705e-06,
+      "loss": 0.7816,
+      "step": 496
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5.2233315817130846e-06,
+      "loss": 0.7564,
+      "step": 497
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5.233841303205466e-06,
+      "loss": 0.7769,
+      "step": 498
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5.244351024697845e-06,
+      "loss": 0.7552,
+      "step": 499
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5.254860746190227e-06,
+      "loss": 0.7614,
+      "step": 500
+    }
+  ],
+  "max_steps": 63425,
+  "num_train_epochs": 25,
+  "total_flos": 1.324826417430528e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a995e57c5ef351645b3d9b96a658552090bbf013ddf7014ddf41bb6049fc00
+size 3771