Upload 15 files

added_tokens.json

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

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/ML-A100/models/Llama-2-13b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.1",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.35.1"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d8b53803d945c25ee4c102fe01fe5a0c8d3d4dedbed67678cb0db00164c5b5
+size 4978276040

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c091def96de2022fe77bdc713df664018ca6a586b01e5506a33d9953a45b39f
+size 4970422232

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb03620e493ab9e819b898eff12aef0a128b26982b0c4d557ad528df518e7ea
+size 4970422256

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c385a8cf536eb88603598a5b1602e31323fe53ed2abb4c720e50ca5129b6bf9f
+size 4933701504

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a524eeee2916df42aa936889bd7034c6f75fb1ae8b8d9ab85d9a4117a69b56
+size 4933722216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4855e8b0b538bca923c6ae5b927e177b2196500f7c47f55f93af25865a912a
+size 1245247160

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26031749120
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2011 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 664,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3082402064781276e-06,
+      "loss": 0.7935,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.6164804129562553e-06,
+      "loss": 0.7,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.381751875681663e-06,
+      "loss": 0.6316,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.924720619434383e-06,
+      "loss": 0.5405,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.345879896760937e-06,
+      "loss": 0.522,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.689992082159791e-06,
+      "loss": 0.4827,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.980934789368156e-06,
+      "loss": 0.4555,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.2329608259125105e-06,
+      "loss": 0.45,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.4552635448851985e-06,
+      "loss": 0.4315,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 5.6541201032390644e-06,
+      "loss": 0.4153,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.83400774154115e-06,
+      "loss": 0.4374,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.99823228863792e-06,
+      "loss": 0.4171,
+      "step": 24
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 6.149304227398896e-06,
+      "loss": 0.41,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 6.289174995846284e-06,
+      "loss": 0.4101,
+      "step": 28
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.419391565964472e-06,
+      "loss": 0.4075,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 6.541201032390639e-06,
+      "loss": 0.395,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 6.655623437887147e-06,
+      "loss": 0.3873,
+      "step": 34
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 6.763503751363326e-06,
+      "loss": 0.4005,
+      "step": 36
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 6.865549773769684e-06,
+      "loss": 0.3754,
+      "step": 38
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 6.9623603097171925e-06,
+      "loss": 0.3733,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 7.054446458571692e-06,
+      "loss": 0.3622,
+      "step": 42
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 7.1422479480192775e-06,
+      "loss": 0.369,
+      "step": 44
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 7.226145833886759e-06,
+      "loss": 0.3745,
+      "step": 46
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 7.306472495116047e-06,
+      "loss": 0.3775,
+      "step": 48
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 7.3835195870437456e-06,
+      "loss": 0.3652,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.457544433877025e-06,
+      "loss": 0.3645,
+      "step": 52
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.528775214088733e-06,
+      "loss": 0.3554,
+      "step": 54
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.597415202324413e-06,
+      "loss": 0.3591,
+      "step": 56
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.663646266610644e-06,
+      "loss": 0.3797,
+      "step": 58
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 7.7276317724426e-06,
+      "loss": 0.363,
+      "step": 60
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 7.789519010511834e-06,
+      "loss": 0.367,
+      "step": 62
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 7.849441238868767e-06,
+      "loss": 0.367,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 7.907519410744684e-06,
+      "loss": 0.3696,
+      "step": 66
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 7.963863644365277e-06,
+      "loss": 0.3627,
+      "step": 68
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 8.018574479650967e-06,
+      "loss": 0.3689,
+      "step": 70
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 8.071743957841455e-06,
+      "loss": 0.344,
+      "step": 72
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 8.123456553166724e-06,
+      "loss": 0.3412,
+      "step": 74
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.173789980247812e-06,
+      "loss": 0.3574,
+      "step": 76
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.222815896602431e-06,
+      "loss": 0.339,
+      "step": 78
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.270600516195319e-06,
+      "loss": 0.3547,
+      "step": 80
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.317205147216999e-06,
+      "loss": 0.358,
+      "step": 82
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.36268666504982e-06,
+      "loss": 0.3475,
+      "step": 84
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.407097929574588e-06,
+      "loss": 0.3554,
+      "step": 86
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.450488154497406e-06,
+      "loss": 0.3406,
+      "step": 88
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.492903235168008e-06,
+      "loss": 0.3267,
+      "step": 90
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.534386040364887e-06,
+      "loss": 0.341,
+      "step": 92
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.574976672697987e-06,
+      "loss": 0.3524,
+      "step": 94
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 8.614712701594175e-06,
+      "loss": 0.3584,
+      "step": 96
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.653629372258186e-06,
+      "loss": 0.3351,
+      "step": 98
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.691759793521874e-06,
+      "loss": 0.3522,
+      "step": 100
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.729135107090682e-06,
+      "loss": 0.3544,
+      "step": 102
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.765784640355151e-06,
+      "loss": 0.3408,
+      "step": 104
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8.80173604464618e-06,
+      "loss": 0.3519,
+      "step": 106
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 8.837015420566862e-06,
+      "loss": 0.3417,
+      "step": 108
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 8.87164743182396e-06,
+      "loss": 0.3555,
+      "step": 110
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 8.90565540880254e-06,
+      "loss": 0.3477,
+      "step": 112
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 8.93906144297322e-06,
+      "loss": 0.3298,
+      "step": 114
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 8.971886473088772e-06,
+      "loss": 0.3431,
+      "step": 116
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.004150364012388e-06,
+      "loss": 0.3504,
+      "step": 118
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.035871978920727e-06,
+      "loss": 0.3327,
+      "step": 120
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.067069245538941e-06,
+      "loss": 0.3284,
+      "step": 122
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.09775921698996e-06,
+      "loss": 0.3345,
+      "step": 124
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.127958127775227e-06,
+      "loss": 0.3464,
+      "step": 126
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.157681445346895e-06,
+      "loss": 0.336,
+      "step": 128
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.186943917681705e-06,
+      "loss": 0.3546,
+      "step": 130
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.215759617222812e-06,
+      "loss": 0.3194,
+      "step": 132
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.244141981517345e-06,
+      "loss": 0.3296,
+      "step": 134
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.272103850843403e-06,
+      "loss": 0.3331,
+      "step": 136
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.299657503090295e-06,
+      "loss": 0.3362,
+      "step": 138
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.326814686129093e-06,
+      "loss": 0.3414,
+      "step": 140
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.353586647887207e-06,
+      "loss": 0.3249,
+      "step": 142
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.379984164319582e-06,
+      "loss": 0.3334,
+      "step": 144
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.406017565450707e-06,
+      "loss": 0.3294,
+      "step": 146
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.43169675964485e-06,
+      "loss": 0.3436,
+      "step": 148
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.457031256247281e-06,
+      "loss": 0.3216,
+      "step": 150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.48203018672594e-06,
+      "loss": 0.3509,
+      "step": 152
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.50670232443118e-06,
+      "loss": 0.326,
+      "step": 154
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.53105610308056e-06,
+      "loss": 0.3391,
+      "step": 156
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.555099634066188e-06,
+      "loss": 0.3264,
+      "step": 158
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.578840722673449e-06,
+      "loss": 0.3245,
+      "step": 160
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.602286883292267e-06,
+      "loss": 0.333,
+      "step": 162
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.625445353695127e-06,
+      "loss": 0.3491,
+      "step": 164
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.648323108449636e-06,
+      "loss": 0.34,
+      "step": 166
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.670926871527948e-06,
+      "loss": 0.3343,
+      "step": 168
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.693263128169957e-06,
+      "loss": 0.3311,
+      "step": 170
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.715338136052716e-06,
+      "loss": 0.333,
+      "step": 172
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.73715793581418e-06,
+      "loss": 0.3002,
+      "step": 174
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.758728360975532e-06,
+      "loss": 0.3271,
+      "step": 176
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.780055047302923e-06,
+      "loss": 0.323,
+      "step": 178
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.801143441646136e-06,
+      "loss": 0.3562,
+      "step": 180
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.821998810288924e-06,
+      "loss": 0.3228,
+      "step": 182
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.842626246843015e-06,
+      "loss": 0.3422,
+      "step": 184
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.863030679715369e-06,
+      "loss": 0.3296,
+      "step": 186
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.883216879176116e-06,
+      "loss": 0.3176,
+      "step": 188
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.903189464052494e-06,
+      "loss": 0.3297,
+      "step": 190
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.922952908072303e-06,
+      "loss": 0.3246,
+      "step": 192
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.942511545878664e-06,
+      "loss": 0.3261,
+      "step": 194
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.961869578736312e-06,
+      "loss": 0.3258,
+      "step": 196
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.98103107994822e-06,
+      "loss": 0.3269,
+      "step": 198
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1e-05,
+      "loss": 0.324,
+      "step": 200
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1e-05,
+      "loss": 0.3106,
+      "step": 202
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1e-05,
+      "loss": 0.3086,
+      "step": 204
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1e-05,
+      "loss": 0.3269,
+      "step": 206
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1e-05,
+      "loss": 0.3396,
+      "step": 208
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1e-05,
+      "loss": 0.3249,
+      "step": 210
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1e-05,
+      "loss": 0.3294,
+      "step": 212
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1e-05,
+      "loss": 0.3502,
+      "step": 214
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1e-05,
+      "loss": 0.3329,
+      "step": 216
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1e-05,
+      "loss": 0.3501,
+      "step": 218
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1e-05,
+      "loss": 0.3375,
+      "step": 220
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1e-05,
+      "loss": 0.3326,
+      "step": 222
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1e-05,
+      "loss": 0.3312,
+      "step": 224
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1e-05,
+      "loss": 0.3246,
+      "step": 226
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1e-05,
+      "loss": 0.3142,
+      "step": 228
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1e-05,
+      "loss": 0.3246,
+      "step": 230
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1e-05,
+      "loss": 0.329,
+      "step": 232
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1e-05,
+      "loss": 0.3446,
+      "step": 234
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1e-05,
+      "loss": 0.3205,
+      "step": 236
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1e-05,
+      "loss": 0.3066,
+      "step": 238
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1e-05,
+      "loss": 0.3267,
+      "step": 240
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1e-05,
+      "loss": 0.3169,
+      "step": 242
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1e-05,
+      "loss": 0.333,
+      "step": 244
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1e-05,
+      "loss": 0.3155,
+      "step": 246
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1e-05,
+      "loss": 0.3263,
+      "step": 248
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1e-05,
+      "loss": 0.3154,
+      "step": 250
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1e-05,
+      "loss": 0.3303,
+      "step": 252
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1e-05,
+      "loss": 0.3298,
+      "step": 254
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1e-05,
+      "loss": 0.3319,
+      "step": 256
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1e-05,
+      "loss": 0.3178,
+      "step": 258
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1e-05,
+      "loss": 0.3178,
+      "step": 260
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1e-05,
+      "loss": 0.3163,
+      "step": 262
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1e-05,
+      "loss": 0.2977,
+      "step": 264
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1e-05,
+      "loss": 0.3184,
+      "step": 266
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1e-05,
+      "loss": 0.3359,
+      "step": 268
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1e-05,
+      "loss": 0.321,
+      "step": 270
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1e-05,
+      "loss": 0.3275,
+      "step": 272
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1e-05,
+      "loss": 0.3198,
+      "step": 274
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1e-05,
+      "loss": 0.3352,
+      "step": 276
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1e-05,
+      "loss": 0.3387,
+      "step": 278
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1e-05,
+      "loss": 0.3176,
+      "step": 280
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1e-05,
+      "loss": 0.3278,
+      "step": 282
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1e-05,
+      "loss": 0.2959,
+      "step": 284
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1e-05,
+      "loss": 0.3213,
+      "step": 286
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1e-05,
+      "loss": 0.3154,
+      "step": 288
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1e-05,
+      "loss": 0.3158,
+      "step": 290
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1e-05,
+      "loss": 0.3068,
+      "step": 292
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1e-05,
+      "loss": 0.3178,
+      "step": 294
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1e-05,
+      "loss": 0.3241,
+      "step": 296
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1e-05,
+      "loss": 0.3192,
+      "step": 298
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1e-05,
+      "loss": 0.3238,
+      "step": 300
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1e-05,
+      "loss": 0.3259,
+      "step": 302
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1e-05,
+      "loss": 0.2884,
+      "step": 304
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1e-05,
+      "loss": 0.3148,
+      "step": 306
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1e-05,
+      "loss": 0.3133,
+      "step": 308
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1e-05,
+      "loss": 0.3141,
+      "step": 310
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1e-05,
+      "loss": 0.3187,
+      "step": 312
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1e-05,
+      "loss": 0.3211,
+      "step": 314
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1e-05,
+      "loss": 0.3198,
+      "step": 316
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1e-05,
+      "loss": 0.316,
+      "step": 318
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1e-05,
+      "loss": 0.329,
+      "step": 320
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1e-05,
+      "loss": 0.3008,
+      "step": 322
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1e-05,
+      "loss": 0.3184,
+      "step": 324
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1e-05,
+      "loss": 0.3329,
+      "step": 326
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1e-05,
+      "loss": 0.3106,
+      "step": 328
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1e-05,
+      "loss": 0.3133,
+      "step": 330
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1e-05,
+      "loss": 0.3238,
+      "step": 332
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1e-05,
+      "loss": 0.3145,
+      "step": 334
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1e-05,
+      "loss": 0.3053,
+      "step": 336
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1e-05,
+      "loss": 0.3025,
+      "step": 338
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1e-05,
+      "loss": 0.2953,
+      "step": 340
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1e-05,
+      "loss": 0.302,
+      "step": 342
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1e-05,
+      "loss": 0.2956,
+      "step": 344
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1e-05,
+      "loss": 0.2763,
+      "step": 346
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1e-05,
+      "loss": 0.2848,
+      "step": 348
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1e-05,
+      "loss": 0.2664,
+      "step": 350
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1e-05,
+      "loss": 0.2641,
+      "step": 352
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1e-05,
+      "loss": 0.2783,
+      "step": 354
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1e-05,
+      "loss": 0.2757,
+      "step": 356
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1e-05,
+      "loss": 0.2647,
+      "step": 358
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1e-05,
+      "loss": 0.2725,
+      "step": 360
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1e-05,
+      "loss": 0.277,
+      "step": 362
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1e-05,
+      "loss": 0.2648,
+      "step": 364
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1e-05,
+      "loss": 0.2593,
+      "step": 366
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1e-05,
+      "loss": 0.2654,
+      "step": 368
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1e-05,
+      "loss": 0.2574,
+      "step": 370
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1e-05,
+      "loss": 0.2528,
+      "step": 372
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1e-05,
+      "loss": 0.2415,
+      "step": 374
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1e-05,
+      "loss": 0.2493,
+      "step": 376
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1e-05,
+      "loss": 0.2543,
+      "step": 378
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1e-05,
+      "loss": 0.259,
+      "step": 380
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1e-05,
+      "loss": 0.2445,
+      "step": 382
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1e-05,
+      "loss": 0.2476,
+      "step": 384
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1e-05,
+      "loss": 0.2388,
+      "step": 386
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1e-05,
+      "loss": 0.2398,
+      "step": 388
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1e-05,
+      "loss": 0.2559,
+      "step": 390
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1e-05,
+      "loss": 0.2398,
+      "step": 392
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1e-05,
+      "loss": 0.245,
+      "step": 394
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1e-05,
+      "loss": 0.2502,
+      "step": 396
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1e-05,
+      "loss": 0.2541,
+      "step": 398
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1e-05,
+      "loss": 0.2433,
+      "step": 400
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1e-05,
+      "loss": 0.2486,
+      "step": 402
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1e-05,
+      "loss": 0.2297,
+      "step": 404
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1e-05,
+      "loss": 0.2286,
+      "step": 406
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1e-05,
+      "loss": 0.2425,
+      "step": 408
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1e-05,
+      "loss": 0.2271,
+      "step": 410
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1e-05,
+      "loss": 0.2394,
+      "step": 412
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1e-05,
+      "loss": 0.2446,
+      "step": 414
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1e-05,
+      "loss": 0.2342,
+      "step": 416
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1e-05,
+      "loss": 0.2423,
+      "step": 418
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1e-05,
+      "loss": 0.2334,
+      "step": 420
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1e-05,
+      "loss": 0.2213,
+      "step": 422
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1e-05,
+      "loss": 0.2254,
+      "step": 424
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1e-05,
+      "loss": 0.2385,
+      "step": 426
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1e-05,
+      "loss": 0.2439,
+      "step": 428
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1e-05,
+      "loss": 0.2314,
+      "step": 430
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1e-05,
+      "loss": 0.2423,
+      "step": 432
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1e-05,
+      "loss": 0.2387,
+      "step": 434
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1e-05,
+      "loss": 0.2283,
+      "step": 436
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1e-05,
+      "loss": 0.2358,
+      "step": 438
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1e-05,
+      "loss": 0.2271,
+      "step": 440
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1e-05,
+      "loss": 0.2403,
+      "step": 442
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1e-05,
+      "loss": 0.2365,
+      "step": 444
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1e-05,
+      "loss": 0.2206,
+      "step": 446
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1e-05,
+      "loss": 0.2329,
+      "step": 448
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1e-05,
+      "loss": 0.23,
+      "step": 450
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1e-05,
+      "loss": 0.2177,
+      "step": 452
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1e-05,
+      "loss": 0.219,
+      "step": 454
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1e-05,
+      "loss": 0.226,
+      "step": 456
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1e-05,
+      "loss": 0.2267,
+      "step": 458
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1e-05,
+      "loss": 0.2249,
+      "step": 460
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1e-05,
+      "loss": 0.2368,
+      "step": 462
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1e-05,
+      "loss": 0.2146,
+      "step": 464
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1e-05,
+      "loss": 0.218,
+      "step": 466
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1e-05,
+      "loss": 0.2304,
+      "step": 468
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1e-05,
+      "loss": 0.2314,
+      "step": 470
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1e-05,
+      "loss": 0.2295,
+      "step": 472
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1e-05,
+      "loss": 0.22,
+      "step": 474
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1e-05,
+      "loss": 0.2172,
+      "step": 476
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1e-05,
+      "loss": 0.2244,
+      "step": 478
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1e-05,
+      "loss": 0.2301,
+      "step": 480
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1e-05,
+      "loss": 0.2069,
+      "step": 482
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1e-05,
+      "loss": 0.2342,
+      "step": 484
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1e-05,
+      "loss": 0.2162,
+      "step": 486
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1e-05,
+      "loss": 0.2184,
+      "step": 488
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1e-05,
+      "loss": 0.2369,
+      "step": 490
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1e-05,
+      "loss": 0.2053,
+      "step": 492
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1e-05,
+      "loss": 0.2148,
+      "step": 494
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1e-05,
+      "loss": 0.227,
+      "step": 496
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1e-05,
+      "loss": 0.2252,
+      "step": 498
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1e-05,
+      "loss": 0.2183,
+      "step": 500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1e-05,
+      "loss": 0.2222,
+      "step": 502
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1e-05,
+      "loss": 0.2158,
+      "step": 504
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1e-05,
+      "loss": 0.1991,
+      "step": 506
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1e-05,
+      "loss": 0.2093,
+      "step": 508
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1e-05,
+      "loss": 0.2021,
+      "step": 510
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1e-05,
+      "loss": 0.2392,
+      "step": 512
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1e-05,
+      "loss": 0.2119,
+      "step": 514
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1e-05,
+      "loss": 0.2261,
+      "step": 516
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1e-05,
+      "loss": 0.2138,
+      "step": 518
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1e-05,
+      "loss": 0.2029,
+      "step": 520
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1e-05,
+      "loss": 0.2107,
+      "step": 522
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1e-05,
+      "loss": 0.2078,
+      "step": 524
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1e-05,
+      "loss": 0.2187,
+      "step": 526
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1e-05,
+      "loss": 0.2174,
+      "step": 528
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1e-05,
+      "loss": 0.2165,
+      "step": 530
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1e-05,
+      "loss": 0.2098,
+      "step": 532
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1e-05,
+      "loss": 0.199,
+      "step": 534
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1e-05,
+      "loss": 0.2002,
+      "step": 536
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1e-05,
+      "loss": 0.2137,
+      "step": 538
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1e-05,
+      "loss": 0.2176,
+      "step": 540
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1e-05,
+      "loss": 0.2153,
+      "step": 542
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1e-05,
+      "loss": 0.2164,
+      "step": 544
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1e-05,
+      "loss": 0.2305,
+      "step": 546
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1e-05,
+      "loss": 0.2182,
+      "step": 548
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1e-05,
+      "loss": 0.2228,
+      "step": 550
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1e-05,
+      "loss": 0.2207,
+      "step": 552
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1e-05,
+      "loss": 0.224,
+      "step": 554
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1e-05,
+      "loss": 0.2201,
+      "step": 556
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1e-05,
+      "loss": 0.2137,
+      "step": 558
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1e-05,
+      "loss": 0.2097,
+      "step": 560
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1e-05,
+      "loss": 0.2155,
+      "step": 562
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1e-05,
+      "loss": 0.2166,
+      "step": 564
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1e-05,
+      "loss": 0.2302,
+      "step": 566
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1e-05,
+      "loss": 0.2078,
+      "step": 568
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1e-05,
+      "loss": 0.1972,
+      "step": 570
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1e-05,
+      "loss": 0.2198,
+      "step": 572
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1e-05,
+      "loss": 0.213,
+      "step": 574
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1e-05,
+      "loss": 0.2183,
+      "step": 576
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1e-05,
+      "loss": 0.2044,
+      "step": 578
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1e-05,
+      "loss": 0.2163,
+      "step": 580
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1e-05,
+      "loss": 0.2031,
+      "step": 582
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1e-05,
+      "loss": 0.2228,
+      "step": 584
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1e-05,
+      "loss": 0.2271,
+      "step": 586
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1e-05,
+      "loss": 0.2196,
+      "step": 588
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1e-05,
+      "loss": 0.2134,
+      "step": 590
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1e-05,
+      "loss": 0.2019,
+      "step": 592
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1e-05,
+      "loss": 0.1986,
+      "step": 594
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1e-05,
+      "loss": 0.1943,
+      "step": 596
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1e-05,
+      "loss": 0.206,
+      "step": 598
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1e-05,
+      "loss": 0.2154,
+      "step": 600
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1e-05,
+      "loss": 0.2103,
+      "step": 602
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1e-05,
+      "loss": 0.2167,
+      "step": 604
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1e-05,
+      "loss": 0.209,
+      "step": 606
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1e-05,
+      "loss": 0.2208,
+      "step": 608
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1e-05,
+      "loss": 0.2252,
+      "step": 610
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1e-05,
+      "loss": 0.2092,
+      "step": 612
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1e-05,
+      "loss": 0.2099,
+      "step": 614
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1e-05,
+      "loss": 0.1955,
+      "step": 616
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1e-05,
+      "loss": 0.2176,
+      "step": 618
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1e-05,
+      "loss": 0.2053,
+      "step": 620
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1e-05,
+      "loss": 0.2119,
+      "step": 622
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1e-05,
+      "loss": 0.1986,
+      "step": 624
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1e-05,
+      "loss": 0.2136,
+      "step": 626
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1e-05,
+      "loss": 0.2154,
+      "step": 628
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1e-05,
+      "loss": 0.2091,
+      "step": 630
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1e-05,
+      "loss": 0.2161,
+      "step": 632
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1e-05,
+      "loss": 0.2107,
+      "step": 634
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1e-05,
+      "loss": 0.1814,
+      "step": 636
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1e-05,
+      "loss": 0.2097,
+      "step": 638
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1e-05,
+      "loss": 0.2078,
+      "step": 640
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1e-05,
+      "loss": 0.1985,
+      "step": 642
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1e-05,
+      "loss": 0.2115,
+      "step": 644
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1e-05,
+      "loss": 0.2128,
+      "step": 646
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1e-05,
+      "loss": 0.2133,
+      "step": 648
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1e-05,
+      "loss": 0.2109,
+      "step": 650
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1e-05,
+      "loss": 0.2133,
+      "step": 652
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1e-05,
+      "loss": 0.198,
+      "step": 654
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1e-05,
+      "loss": 0.2068,
+      "step": 656
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1e-05,
+      "loss": 0.2222,
+      "step": 658
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1e-05,
+      "loss": 0.2035,
+      "step": 660
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1e-05,
+      "loss": 0.2067,
+      "step": 662
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1e-05,
+      "loss": 0.207,
+      "step": 664
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1992,
+  "num_train_epochs": 6,
+  "save_steps": 64.0,
+  "total_flos": 148901009686528.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da0167127a217efe26c78d229b99ad905ad18eecd77581e01cd9a087834755f
+size 6456