Upload folder using huggingface_hub

checkpoint-368/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Q-bert/MetaMath-Cybertron-Starling",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-368/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

checkpoint-368/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c68ab1637cc76cb2685098e0743942f879bf0e1713b829c970af35d2bc20fc
+size 4987196936

checkpoint-368/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ded1f96c34542ef4209054ec534def862c8f9a718a7dc104d81e6f7b0f27b4a
+size 4899116440

checkpoint-368/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394cb7b4d884c5929df6eed045eb422f0499bade6b6138d20e6fe7d06e53fb80
+size 4999813120

checkpoint-368/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ccde43bbe3258f8ab2afb86b32248b904eec31fe96fba75b2b8e5896df86ca
+size 4999813128

checkpoint-368/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d8f0b3069b6f812319d86711f6ca997df041ef1ab33ce75bfe87d83e41c3d2
+size 4832007496

checkpoint-368/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ce7ccd6bb65003d8bb9e2078cccd18c2f23c40d12dae0890c6880c5d67d0c4
+size 4249014896

checkpoint-368/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 28966928384
+  },
+  "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-00003-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-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-00003-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-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-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-00003-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-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-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-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-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-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-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-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.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-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-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-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-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"
+  }
+}

checkpoint-368/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3bc9b0ab27b2362bf90201dcfde069b967d5cd3063c598f73bb197ca552f1a
+size 14512103111

checkpoint-368/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62645c695530bea3f09200c274e27a94375cae128377db5b017b297143c54c49
+size 14575

checkpoint-368/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43511c766e65787ff21d339307ae7a4b16c22b0e1f725eed3ffd1310d2a3ac7
+size 627

checkpoint-368/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-368/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-368/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-368/trainer_state.json

@@ -0,0 +1,2229 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5006802721088436,
+  "eval_steps": 500,
+  "global_step": 368,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3980952380952381e-05,
+      "loss": 1.9251,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3961904761904762e-05,
+      "loss": 2.237,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3942857142857142e-05,
+      "loss": 2.3403,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3923809523809523e-05,
+      "loss": 2.004,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3904761904761905e-05,
+      "loss": 2.0853,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3885714285714286e-05,
+      "loss": 1.946,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3866666666666667e-05,
+      "loss": 1.941,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3847619047619048e-05,
+      "loss": 1.7827,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3828571428571428e-05,
+      "loss": 2.0452,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.380952380952381e-05,
+      "loss": 1.7634,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.379047619047619e-05,
+      "loss": 1.9573,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3771428571428572e-05,
+      "loss": 1.9773,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3752380952380953e-05,
+      "loss": 1.9236,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3733333333333333e-05,
+      "loss": 1.8623,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3714285714285714e-05,
+      "loss": 1.8837,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3695238095238095e-05,
+      "loss": 2.029,
+      "step": 16
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3676190476190477e-05,
+      "loss": 2.0832,
+      "step": 17
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3657142857142858e-05,
+      "loss": 1.5689,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3638095238095238e-05,
+      "loss": 1.8034,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3619047619047619e-05,
+      "loss": 1.8121,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.36e-05,
+      "loss": 1.8425,
+      "step": 21
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3580952380952382e-05,
+      "loss": 1.8582,
+      "step": 22
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3561904761904763e-05,
+      "loss": 1.8883,
+      "step": 23
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3542857142857144e-05,
+      "loss": 1.7498,
+      "step": 24
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3523809523809524e-05,
+      "loss": 1.804,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.3504761904761905e-05,
+      "loss": 1.893,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.3485714285714286e-05,
+      "loss": 1.8625,
+      "step": 27
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.3466666666666668e-05,
+      "loss": 1.6711,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.3447619047619047e-05,
+      "loss": 1.7258,
+      "step": 29
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.3428571428571429e-05,
+      "loss": 1.4927,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.340952380952381e-05,
+      "loss": 1.8962,
+      "step": 31
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.339047619047619e-05,
+      "loss": 1.5401,
+      "step": 32
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.337142857142857e-05,
+      "loss": 1.7157,
+      "step": 33
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3352380952380952e-05,
+      "loss": 1.8139,
+      "step": 34
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3333333333333332e-05,
+      "loss": 1.6017,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3314285714285713e-05,
+      "loss": 1.812,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3295238095238094e-05,
+      "loss": 1.8849,
+      "step": 37
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3276190476190475e-05,
+      "loss": 1.7949,
+      "step": 38
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3257142857142857e-05,
+      "loss": 1.68,
+      "step": 39
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3238095238095238e-05,
+      "loss": 1.6812,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3219047619047618e-05,
+      "loss": 1.8958,
+      "step": 41
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3199999999999999e-05,
+      "loss": 1.6719,
+      "step": 42
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.318095238095238e-05,
+      "loss": 1.7752,
+      "step": 43
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3161904761904762e-05,
+      "loss": 1.7632,
+      "step": 44
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3142857142857143e-05,
+      "loss": 1.5865,
+      "step": 45
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3123809523809522e-05,
+      "loss": 1.9588,
+      "step": 46
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3104761904761904e-05,
+      "loss": 1.767,
+      "step": 47
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3085714285714285e-05,
+      "loss": 1.8413,
+      "step": 48
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3066666666666666e-05,
+      "loss": 1.7801,
+      "step": 49
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3047619047619048e-05,
+      "loss": 1.4807,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3028571428571427e-05,
+      "loss": 1.718,
+      "step": 51
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3009523809523809e-05,
+      "loss": 1.6581,
+      "step": 52
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.299047619047619e-05,
+      "loss": 1.611,
+      "step": 53
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.2971428571428571e-05,
+      "loss": 1.7558,
+      "step": 54
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.2952380952380952e-05,
+      "loss": 1.8626,
+      "step": 55
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2933333333333334e-05,
+      "loss": 1.781,
+      "step": 56
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2914285714285713e-05,
+      "loss": 1.705,
+      "step": 57
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2895238095238095e-05,
+      "loss": 1.7269,
+      "step": 58
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2876190476190476e-05,
+      "loss": 1.7764,
+      "step": 59
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 1.7602,
+      "step": 60
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2838095238095239e-05,
+      "loss": 1.8244,
+      "step": 61
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2819047619047618e-05,
+      "loss": 1.7506,
+      "step": 62
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.28e-05,
+      "loss": 1.9183,
+      "step": 63
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.278095238095238e-05,
+      "loss": 1.8333,
+      "step": 64
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2761904761904762e-05,
+      "loss": 1.5797,
+      "step": 65
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2742857142857143e-05,
+      "loss": 1.5009,
+      "step": 66
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2723809523809525e-05,
+      "loss": 1.4625,
+      "step": 67
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2704761904761904e-05,
+      "loss": 1.9483,
+      "step": 68
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2685714285714286e-05,
+      "loss": 1.3773,
+      "step": 69
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2666666666666667e-05,
+      "loss": 1.4853,
+      "step": 70
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2647619047619048e-05,
+      "loss": 1.5423,
+      "step": 71
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.262857142857143e-05,
+      "loss": 1.2449,
+      "step": 72
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2609523809523809e-05,
+      "loss": 1.9732,
+      "step": 73
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.259047619047619e-05,
+      "loss": 1.5281,
+      "step": 74
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2571428571428572e-05,
+      "loss": 1.8673,
+      "step": 75
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2552380952380953e-05,
+      "loss": 1.5986,
+      "step": 76
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2533333333333334e-05,
+      "loss": 1.7682,
+      "step": 77
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.2514285714285714e-05,
+      "loss": 1.893,
+      "step": 78
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.2495238095238095e-05,
+      "loss": 1.5008,
+      "step": 79
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.2476190476190476e-05,
+      "loss": 1.7897,
+      "step": 80
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.2457142857142858e-05,
+      "loss": 1.8012,
+      "step": 81
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.2438095238095239e-05,
+      "loss": 1.7117,
+      "step": 82
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.241904761904762e-05,
+      "loss": 1.7093,
+      "step": 83
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.24e-05,
+      "loss": 1.5255,
+      "step": 84
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.2380952380952381e-05,
+      "loss": 1.4508,
+      "step": 85
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.2361904761904762e-05,
+      "loss": 1.6286,
+      "step": 86
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.2342857142857144e-05,
+      "loss": 1.6495,
+      "step": 87
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.2323809523809525e-05,
+      "loss": 1.4856,
+      "step": 88
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.2304761904761905e-05,
+      "loss": 1.6728,
+      "step": 89
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.2285714285714286e-05,
+      "loss": 1.4032,
+      "step": 90
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.2266666666666667e-05,
+      "loss": 1.6083,
+      "step": 91
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.2247619047619047e-05,
+      "loss": 1.5496,
+      "step": 92
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.2228571428571428e-05,
+      "loss": 2.0419,
+      "step": 93
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.220952380952381e-05,
+      "loss": 1.5236,
+      "step": 94
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.2190476190476189e-05,
+      "loss": 1.3895,
+      "step": 95
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.217142857142857e-05,
+      "loss": 1.6532,
+      "step": 96
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.2152380952380952e-05,
+      "loss": 1.6868,
+      "step": 97
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.2133333333333333e-05,
+      "loss": 1.46,
+      "step": 98
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.2114285714285714e-05,
+      "loss": 1.6373,
+      "step": 99
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.2095238095238094e-05,
+      "loss": 1.4497,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.2076190476190475e-05,
+      "loss": 1.6194,
+      "step": 101
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.2057142857142856e-05,
+      "loss": 1.7623,
+      "step": 102
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.2038095238095238e-05,
+      "loss": 1.6722,
+      "step": 103
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.2019047619047619e-05,
+      "loss": 1.765,
+      "step": 104
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 1.9492,
+      "step": 105
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.198095238095238e-05,
+      "loss": 1.2779,
+      "step": 106
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.1961904761904761e-05,
+      "loss": 1.5185,
+      "step": 107
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.1942857142857142e-05,
+      "loss": 1.685,
+      "step": 108
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.1923809523809524e-05,
+      "loss": 1.7304,
+      "step": 109
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.1904761904761903e-05,
+      "loss": 1.6961,
+      "step": 110
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.1885714285714285e-05,
+      "loss": 1.3989,
+      "step": 111
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.1866666666666666e-05,
+      "loss": 1.6383,
+      "step": 112
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.1847619047619047e-05,
+      "loss": 1.6153,
+      "step": 113
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1828571428571429e-05,
+      "loss": 1.7371,
+      "step": 114
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.180952380952381e-05,
+      "loss": 1.7609,
+      "step": 115
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.179047619047619e-05,
+      "loss": 1.4269,
+      "step": 116
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.177142857142857e-05,
+      "loss": 1.7976,
+      "step": 117
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1752380952380952e-05,
+      "loss": 1.538,
+      "step": 118
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1733333333333333e-05,
+      "loss": 1.6206,
+      "step": 119
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1714285714285715e-05,
+      "loss": 1.7221,
+      "step": 120
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1695238095238094e-05,
+      "loss": 1.2271,
+      "step": 121
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.1676190476190476e-05,
+      "loss": 1.8847,
+      "step": 122
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.1657142857142857e-05,
+      "loss": 2.1748,
+      "step": 123
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.1638095238095238e-05,
+      "loss": 1.6654,
+      "step": 124
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.161904761904762e-05,
+      "loss": 1.3367,
+      "step": 125
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.16e-05,
+      "loss": 1.5722,
+      "step": 126
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.158095238095238e-05,
+      "loss": 1.5672,
+      "step": 127
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.1561904761904762e-05,
+      "loss": 1.7614,
+      "step": 128
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.1542857142857143e-05,
+      "loss": 1.6648,
+      "step": 129
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.1523809523809524e-05,
+      "loss": 1.8454,
+      "step": 130
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.1504761904761906e-05,
+      "loss": 1.2734,
+      "step": 131
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.1485714285714285e-05,
+      "loss": 1.3313,
+      "step": 132
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.1466666666666666e-05,
+      "loss": 1.1914,
+      "step": 133
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.1447619047619048e-05,
+      "loss": 1.6754,
+      "step": 134
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 1.6821,
+      "step": 135
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.140952380952381e-05,
+      "loss": 1.9894,
+      "step": 136
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.139047619047619e-05,
+      "loss": 1.7721,
+      "step": 137
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.1371428571428571e-05,
+      "loss": 1.644,
+      "step": 138
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.1352380952380953e-05,
+      "loss": 0.942,
+      "step": 139
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.1333333333333334e-05,
+      "loss": 1.3515,
+      "step": 140
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.1314285714285715e-05,
+      "loss": 1.5084,
+      "step": 141
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.1295238095238096e-05,
+      "loss": 1.9172,
+      "step": 142
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.1276190476190476e-05,
+      "loss": 1.6386,
+      "step": 143
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.1257142857142857e-05,
+      "loss": 1.5719,
+      "step": 144
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.1238095238095239e-05,
+      "loss": 1.557,
+      "step": 145
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.121904761904762e-05,
+      "loss": 1.6815,
+      "step": 146
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 1.6925,
+      "step": 147
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.118095238095238e-05,
+      "loss": 1.7414,
+      "step": 148
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.1161904761904762e-05,
+      "loss": 1.5588,
+      "step": 149
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.1142857142857143e-05,
+      "loss": 1.5205,
+      "step": 150
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.1123809523809525e-05,
+      "loss": 1.6307,
+      "step": 151
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.1104761904761904e-05,
+      "loss": 1.2504,
+      "step": 152
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.1085714285714286e-05,
+      "loss": 1.8199,
+      "step": 153
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.1066666666666667e-05,
+      "loss": 1.4118,
+      "step": 154
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.1047619047619046e-05,
+      "loss": 1.4379,
+      "step": 155
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.1028571428571428e-05,
+      "loss": 1.1513,
+      "step": 156
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.1009523809523809e-05,
+      "loss": 1.4012,
+      "step": 157
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.099047619047619e-05,
+      "loss": 1.3337,
+      "step": 158
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.097142857142857e-05,
+      "loss": 1.2861,
+      "step": 159
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.0952380952380951e-05,
+      "loss": 1.1884,
+      "step": 160
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.0933333333333333e-05,
+      "loss": 1.5143,
+      "step": 161
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.0914285714285714e-05,
+      "loss": 1.6417,
+      "step": 162
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.0895238095238095e-05,
+      "loss": 1.6076,
+      "step": 163
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.0876190476190475e-05,
+      "loss": 1.3847,
+      "step": 164
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.0857142857142856e-05,
+      "loss": 1.5988,
+      "step": 165
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.0838095238095237e-05,
+      "loss": 1.5277,
+      "step": 166
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.0819047619047619e-05,
+      "loss": 1.5894,
+      "step": 167
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.08e-05,
+      "loss": 1.4294,
+      "step": 168
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.078095238095238e-05,
+      "loss": 1.5011,
+      "step": 169
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.076190476190476e-05,
+      "loss": 1.3573,
+      "step": 170
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.0742857142857142e-05,
+      "loss": 1.6822,
+      "step": 171
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.0723809523809523e-05,
+      "loss": 1.5523,
+      "step": 172
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.0704761904761905e-05,
+      "loss": 1.6135,
+      "step": 173
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.0685714285714286e-05,
+      "loss": 1.981,
+      "step": 174
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.0666666666666666e-05,
+      "loss": 1.5314,
+      "step": 175
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.0647619047619047e-05,
+      "loss": 1.1368,
+      "step": 176
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.0628571428571428e-05,
+      "loss": 1.763,
+      "step": 177
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.060952380952381e-05,
+      "loss": 1.1155,
+      "step": 178
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.059047619047619e-05,
+      "loss": 1.5571,
+      "step": 179
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.057142857142857e-05,
+      "loss": 1.6422,
+      "step": 180
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.0552380952380952e-05,
+      "loss": 1.5116,
+      "step": 181
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.0533333333333333e-05,
+      "loss": 1.3852,
+      "step": 182
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.0514285714285714e-05,
+      "loss": 1.5127,
+      "step": 183
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.0495238095238096e-05,
+      "loss": 1.4374,
+      "step": 184
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.0476190476190477e-05,
+      "loss": 1.4862,
+      "step": 185
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.0457142857142856e-05,
+      "loss": 1.271,
+      "step": 186
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.0438095238095238e-05,
+      "loss": 1.424,
+      "step": 187
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.0419047619047619e-05,
+      "loss": 1.3103,
+      "step": 188
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.04e-05,
+      "loss": 1.5764,
+      "step": 189
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.0380952380952382e-05,
+      "loss": 1.2966,
+      "step": 190
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.0361904761904761e-05,
+      "loss": 1.4407,
+      "step": 191
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.0342857142857143e-05,
+      "loss": 1.4769,
+      "step": 192
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.0323809523809524e-05,
+      "loss": 1.8485,
+      "step": 193
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.0304761904761905e-05,
+      "loss": 1.3984,
+      "step": 194
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.0285714285714286e-05,
+      "loss": 1.6489,
+      "step": 195
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.0266666666666666e-05,
+      "loss": 1.6047,
+      "step": 196
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.0247619047619047e-05,
+      "loss": 1.3263,
+      "step": 197
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.0228571428571429e-05,
+      "loss": 1.1799,
+      "step": 198
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.020952380952381e-05,
+      "loss": 1.7125,
+      "step": 199
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.0190476190476191e-05,
+      "loss": 1.3331,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.0171428571428573e-05,
+      "loss": 1.474,
+      "step": 201
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.0152380952380952e-05,
+      "loss": 1.3566,
+      "step": 202
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.0133333333333333e-05,
+      "loss": 1.2508,
+      "step": 203
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.0114285714285715e-05,
+      "loss": 1.5821,
+      "step": 204
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.0095238095238096e-05,
+      "loss": 1.7047,
+      "step": 205
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.0076190476190477e-05,
+      "loss": 1.5179,
+      "step": 206
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.0057142857142857e-05,
+      "loss": 1.5492,
+      "step": 207
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.0038095238095238e-05,
+      "loss": 1.4274,
+      "step": 208
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.001904761904762e-05,
+      "loss": 1.4075,
+      "step": 209
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1e-05,
+      "loss": 1.4878,
+      "step": 210
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.980952380952382e-06,
+      "loss": 1.4027,
+      "step": 211
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.961904761904762e-06,
+      "loss": 1.4672,
+      "step": 212
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.942857142857143e-06,
+      "loss": 1.3631,
+      "step": 213
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.923809523809524e-06,
+      "loss": 1.4177,
+      "step": 214
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.904761904761904e-06,
+      "loss": 1.4329,
+      "step": 215
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.885714285714285e-06,
+      "loss": 1.5616,
+      "step": 216
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.866666666666667e-06,
+      "loss": 1.5772,
+      "step": 217
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.847619047619046e-06,
+      "loss": 1.6318,
+      "step": 218
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.828571428571427e-06,
+      "loss": 1.368,
+      "step": 219
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.809523809523809e-06,
+      "loss": 1.2774,
+      "step": 220
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.79047619047619e-06,
+      "loss": 1.3747,
+      "step": 221
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.771428571428571e-06,
+      "loss": 1.3974,
+      "step": 222
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.752380952380951e-06,
+      "loss": 1.5687,
+      "step": 223
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.733333333333332e-06,
+      "loss": 1.5798,
+      "step": 224
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.714285714285713e-06,
+      "loss": 1.7257,
+      "step": 225
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.695238095238095e-06,
+      "loss": 0.996,
+      "step": 226
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.676190476190476e-06,
+      "loss": 2.1266,
+      "step": 227
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.657142857142857e-06,
+      "loss": 1.7335,
+      "step": 228
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.638095238095237e-06,
+      "loss": 1.4647,
+      "step": 229
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.619047619047618e-06,
+      "loss": 1.0974,
+      "step": 230
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.6e-06,
+      "loss": 1.1022,
+      "step": 231
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.580952380952381e-06,
+      "loss": 1.2352,
+      "step": 232
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.561904761904762e-06,
+      "loss": 1.5827,
+      "step": 233
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.542857142857142e-06,
+      "loss": 1.7707,
+      "step": 234
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 1.6125,
+      "step": 235
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.504761904761904e-06,
+      "loss": 1.8655,
+      "step": 236
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.485714285714286e-06,
+      "loss": 1.4079,
+      "step": 237
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.466666666666667e-06,
+      "loss": 1.4635,
+      "step": 238
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.447619047619047e-06,
+      "loss": 1.4203,
+      "step": 239
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.428571428571428e-06,
+      "loss": 1.5604,
+      "step": 240
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.409523809523809e-06,
+      "loss": 1.4702,
+      "step": 241
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.39047619047619e-06,
+      "loss": 1.5907,
+      "step": 242
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.371428571428572e-06,
+      "loss": 1.6619,
+      "step": 243
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.352380952380953e-06,
+      "loss": 1.5003,
+      "step": 244
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.333333333333333e-06,
+      "loss": 1.7973,
+      "step": 245
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.314285714285714e-06,
+      "loss": 1.6517,
+      "step": 246
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.295238095238095e-06,
+      "loss": 1.666,
+      "step": 247
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.276190476190477e-06,
+      "loss": 1.3698,
+      "step": 248
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.257142857142858e-06,
+      "loss": 1.623,
+      "step": 249
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.238095238095237e-06,
+      "loss": 1.1884,
+      "step": 250
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.219047619047619e-06,
+      "loss": 1.2523,
+      "step": 251
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.2e-06,
+      "loss": 1.5694,
+      "step": 252
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.180952380952381e-06,
+      "loss": 1.4466,
+      "step": 253
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.161904761904763e-06,
+      "loss": 1.6821,
+      "step": 254
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.142857142857142e-06,
+      "loss": 1.398,
+      "step": 255
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.123809523809523e-06,
+      "loss": 1.6264,
+      "step": 256
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.104761904761905e-06,
+      "loss": 1.5653,
+      "step": 257
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.085714285714286e-06,
+      "loss": 1.6115,
+      "step": 258
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.066666666666667e-06,
+      "loss": 1.455,
+      "step": 259
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.047619047619049e-06,
+      "loss": 1.4232,
+      "step": 260
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.028571428571428e-06,
+      "loss": 1.5055,
+      "step": 261
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.00952380952381e-06,
+      "loss": 1.7067,
+      "step": 262
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.990476190476191e-06,
+      "loss": 1.7505,
+      "step": 263
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.971428571428572e-06,
+      "loss": 1.1468,
+      "step": 264
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.952380952380953e-06,
+      "loss": 1.5362,
+      "step": 265
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.933333333333333e-06,
+      "loss": 1.7492,
+      "step": 266
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.914285714285714e-06,
+      "loss": 1.2201,
+      "step": 267
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.895238095238096e-06,
+      "loss": 1.3609,
+      "step": 268
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.876190476190477e-06,
+      "loss": 1.4403,
+      "step": 269
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.857142857142858e-06,
+      "loss": 1.5651,
+      "step": 270
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.838095238095238e-06,
+      "loss": 1.5318,
+      "step": 271
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.819047619047619e-06,
+      "loss": 1.1585,
+      "step": 272
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3241,
+      "step": 273
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.780952380952382e-06,
+      "loss": 1.4923,
+      "step": 274
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.761904761904761e-06,
+      "loss": 1.7976,
+      "step": 275
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.742857142857143e-06,
+      "loss": 1.372,
+      "step": 276
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.723809523809524e-06,
+      "loss": 1.22,
+      "step": 277
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.704761904761904e-06,
+      "loss": 1.4038,
+      "step": 278
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.685714285714285e-06,
+      "loss": 1.5937,
+      "step": 279
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.666666666666666e-06,
+      "loss": 1.3512,
+      "step": 280
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.647619047619047e-06,
+      "loss": 1.0502,
+      "step": 281
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.628571428571427e-06,
+      "loss": 1.2045,
+      "step": 282
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.609523809523808e-06,
+      "loss": 1.369,
+      "step": 283
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.59047619047619e-06,
+      "loss": 1.5638,
+      "step": 284
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.6589,
+      "step": 285
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.552380952380952e-06,
+      "loss": 1.1079,
+      "step": 286
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.533333333333334e-06,
+      "loss": 1.4133,
+      "step": 287
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.514285714285713e-06,
+      "loss": 1.6174,
+      "step": 288
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.495238095238094e-06,
+      "loss": 1.6332,
+      "step": 289
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.476190476190476e-06,
+      "loss": 1.5578,
+      "step": 290
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.457142857142857e-06,
+      "loss": 1.3662,
+      "step": 291
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.438095238095238e-06,
+      "loss": 1.7247,
+      "step": 292
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.419047619047618e-06,
+      "loss": 1.6704,
+      "step": 293
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.4e-06,
+      "loss": 1.2688,
+      "step": 294
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.38095238095238e-06,
+      "loss": 1.2547,
+      "step": 295
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.361904761904762e-06,
+      "loss": 1.4751,
+      "step": 296
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.342857142857143e-06,
+      "loss": 1.425,
+      "step": 297
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.323809523809523e-06,
+      "loss": 1.6818,
+      "step": 298
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.304761904761904e-06,
+      "loss": 1.5462,
+      "step": 299
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.285714285714285e-06,
+      "loss": 1.1402,
+      "step": 300
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.266666666666667e-06,
+      "loss": 1.3696,
+      "step": 301
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.247619047619048e-06,
+      "loss": 1.404,
+      "step": 302
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.22857142857143e-06,
+      "loss": 1.3068,
+      "step": 303
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.209523809523809e-06,
+      "loss": 1.4081,
+      "step": 304
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.19047619047619e-06,
+      "loss": 1.1629,
+      "step": 305
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.171428571428571e-06,
+      "loss": 1.6461,
+      "step": 306
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.152380952380953e-06,
+      "loss": 1.2648,
+      "step": 307
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.133333333333334e-06,
+      "loss": 1.2813,
+      "step": 308
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.114285714285714e-06,
+      "loss": 1.438,
+      "step": 309
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.095238095238095e-06,
+      "loss": 1.4388,
+      "step": 310
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.076190476190476e-06,
+      "loss": 1.3703,
+      "step": 311
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.057142857142857e-06,
+      "loss": 1.3313,
+      "step": 312
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.038095238095239e-06,
+      "loss": 1.2477,
+      "step": 313
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.019047619047618e-06,
+      "loss": 1.3834,
+      "step": 314
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8e-06,
+      "loss": 1.2783,
+      "step": 315
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 7.980952380952381e-06,
+      "loss": 1.4858,
+      "step": 316
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 7.961904761904762e-06,
+      "loss": 1.342,
+      "step": 317
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 7.942857142857144e-06,
+      "loss": 1.3243,
+      "step": 318
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 7.923809523809525e-06,
+      "loss": 1.0396,
+      "step": 319
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.904761904761904e-06,
+      "loss": 1.288,
+      "step": 320
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.885714285714286e-06,
+      "loss": 1.3156,
+      "step": 321
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.866666666666667e-06,
+      "loss": 1.5605,
+      "step": 322
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.847619047619048e-06,
+      "loss": 1.5266,
+      "step": 323
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.82857142857143e-06,
+      "loss": 1.0976,
+      "step": 324
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.80952380952381e-06,
+      "loss": 1.2879,
+      "step": 325
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.79047619047619e-06,
+      "loss": 1.3833,
+      "step": 326
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.771428571428572e-06,
+      "loss": 1.4636,
+      "step": 327
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.752380952380953e-06,
+      "loss": 1.1288,
+      "step": 328
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.733333333333334e-06,
+      "loss": 1.0436,
+      "step": 329
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.714285714285714e-06,
+      "loss": 0.9859,
+      "step": 330
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.695238095238095e-06,
+      "loss": 1.3709,
+      "step": 331
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.676190476190477e-06,
+      "loss": 1.3816,
+      "step": 332
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.657142857142858e-06,
+      "loss": 1.1793,
+      "step": 333
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.63809523809524e-06,
+      "loss": 1.3626,
+      "step": 334
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 1.3073,
+      "step": 335
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.599999999999999e-06,
+      "loss": 1.0394,
+      "step": 336
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.5809523809523805e-06,
+      "loss": 1.414,
+      "step": 337
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.561904761904762e-06,
+      "loss": 1.3723,
+      "step": 338
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.542857142857143e-06,
+      "loss": 1.5456,
+      "step": 339
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.523809523809524e-06,
+      "loss": 1.4463,
+      "step": 340
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.504761904761904e-06,
+      "loss": 1.4268,
+      "step": 341
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.485714285714285e-06,
+      "loss": 1.3708,
+      "step": 342
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.466666666666667e-06,
+      "loss": 1.2043,
+      "step": 343
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.447619047619048e-06,
+      "loss": 1.3896,
+      "step": 344
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.428571428571429e-06,
+      "loss": 0.9627,
+      "step": 345
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.4095238095238105e-06,
+      "loss": 1.2312,
+      "step": 346
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.39047619047619e-06,
+      "loss": 1.0419,
+      "step": 347
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.371428571428571e-06,
+      "loss": 1.1359,
+      "step": 348
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.352380952380953e-06,
+      "loss": 1.7454,
+      "step": 349
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.333333333333334e-06,
+      "loss": 1.2688,
+      "step": 350
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.3142857142857144e-06,
+      "loss": 1.5696,
+      "step": 351
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.295238095238095e-06,
+      "loss": 1.2027,
+      "step": 352
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.276190476190476e-06,
+      "loss": 1.4311,
+      "step": 353
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.257142857142857e-06,
+      "loss": 1.559,
+      "step": 354
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.238095238095238e-06,
+      "loss": 1.2771,
+      "step": 355
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.219047619047619e-06,
+      "loss": 1.3038,
+      "step": 356
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.199999999999999e-06,
+      "loss": 1.2849,
+      "step": 357
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.18095238095238e-06,
+      "loss": 1.2649,
+      "step": 358
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.161904761904761e-06,
+      "loss": 1.3374,
+      "step": 359
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 1.4303,
+      "step": 360
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.123809523809524e-06,
+      "loss": 1.1511,
+      "step": 361
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.104761904761905e-06,
+      "loss": 1.3124,
+      "step": 362
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.085714285714285e-06,
+      "loss": 1.2916,
+      "step": 363
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 7.066666666666666e-06,
+      "loss": 1.2252,
+      "step": 364
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 7.0476190476190475e-06,
+      "loss": 1.361,
+      "step": 365
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 7.028571428571429e-06,
+      "loss": 1.7486,
+      "step": 366
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 7.00952380952381e-06,
+      "loss": 1.044,
+      "step": 367
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.9904761904761905e-06,
+      "loss": 1.2656,
+      "step": 368
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 735,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 368,
+  "total_flos": 6.430858236710093e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-368/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c02a266eaaac473153c7e532affb8c471047897acfd36d32333188866944b6
+size 4219

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Q-bert/MetaMath-Cybertron-Starling",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11c935e5b5b17d97838dd1a09daa6b694074bccfe7a31a26c99cee6d10c0c68
+size 4987196936

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7325f507dbdb623ba6a255a825b068a2d83353ed3222eef4cf6261563e83cdb1
+size 4899116440

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52f3048cb01cba1bf2d96d8788dc6944009ae19db5b62368df0ebda7ec6a799
+size 4999813120

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d5812105e13f1750db53839310d5854020314f881b778881d00384420c3a36
+size 4999813128

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5eadc8a4a46ff6d6194eeb6d2242aec99f6edfae2db293b21ba2d00eb3dcae
+size 4832007496

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d1ea4a73f3b4f08748b7b2909c793e435c5c0ba9aaf551250375b9b06edf96
+size 4249014896

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 28966928384
+  },
+  "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-00003-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-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-00003-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-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-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-00003-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-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-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-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-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-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-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-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.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-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-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-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-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 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": "</s>",
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c02a266eaaac473153c7e532affb8c471047897acfd36d32333188866944b6
+size 4219