Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForEncoderDecoder2"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128257
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8f0ef1463d703471b0bac341a92f55bfb0947cadec4f47bbfb0bd1c2ec61ed
+size 4976707520

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed9086f88edd8261f560f43a277bce27f62cadbd17077d956de76b3426c885b
+size 4999803552

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d645861d1b36c0ad4c62ba0ea2303d52048082aa3f7828af13b35358a7d9a6fb
+size 4915916976

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca67c34874746f34689352d74fce733f5908bf4901c5555d17412f320aa4f0b
+size 4920065288

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beccd3aa1e376a821184d0ca19fc8eec8ae9fde85d32f251884079a52634e1b7
+size 4915916144

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:202a0acad6cb7bc4bc5d601c5c9b92dad83d598a503c6e27bf5d3eb021ef9c95
+size 4915916176

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778cdcef56c674ed1a7ca8ab1c83a005bc3c5169c1f6174c4018f5a1438f5aa1
+size 2476822152

model.safetensors.index.json

@@ -0,0 +1,589 @@
+{
+  "metadata": {
+    "total_size": 32121077760
+  },
+  "weight_map": {
+    "encoder.lm_head.weight": "model-00004-of-00007.safetensors",
+    "encoder.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.30.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "encoder.model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "encoder.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "encoder.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.norm.weight": "model-00004-of-00007.safetensors",
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cc13315f24c28015d695b6cde08bb1cd6fea4cbc435998485ed6fbe4c91285
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b023e05bc2d12b91dc436d4922b990d50ec8dc56d40dc3e36b3bb34fc81341
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe1694f053edd7d7a56ecc0b94d196cce360db4e180e18ac7c07e77f53cd675
+size 1064

trainer_state.json

@@ -0,0 +1,978 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9993073193257908,
+  "eval_steps": 500,
+  "global_step": 541,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0073885938582313555,
+      "grad_norm": 35.5,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 3.1173,
+      "step": 4
+    },
+    {
+      "epoch": 0.014777187716462711,
+      "grad_norm": 33.75,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 3.0688,
+      "step": 8
+    },
+    {
+      "epoch": 0.022165781574694066,
+      "grad_norm": 27.25,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 2.8447,
+      "step": 12
+    },
+    {
+      "epoch": 0.029554375432925422,
+      "grad_norm": 21.125,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 2.2541,
+      "step": 16
+    },
+    {
+      "epoch": 0.03694296929115678,
+      "grad_norm": 19.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.6668,
+      "step": 20
+    },
+    {
+      "epoch": 0.04433156314938813,
+      "grad_norm": 7.625,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.9365,
+      "step": 24
+    },
+    {
+      "epoch": 0.051720157007619484,
+      "grad_norm": 5.34375,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.6331,
+      "step": 28
+    },
+    {
+      "epoch": 0.059108750865850844,
+      "grad_norm": 3.53125,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.5437,
+      "step": 32
+    },
+    {
+      "epoch": 0.0664973447240822,
+      "grad_norm": 3.109375,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.4885,
+      "step": 36
+    },
+    {
+      "epoch": 0.07388593858231356,
+      "grad_norm": 3.078125,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4844,
+      "step": 40
+    },
+    {
+      "epoch": 0.0812745324405449,
+      "grad_norm": 2.9375,
+      "learning_rate": 8.8e-06,
+      "loss": 0.4414,
+      "step": 44
+    },
+    {
+      "epoch": 0.08866312629877626,
+      "grad_norm": 2.6875,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.4578,
+      "step": 48
+    },
+    {
+      "epoch": 0.09605172015700762,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.04e-05,
+      "loss": 0.4403,
+      "step": 52
+    },
+    {
+      "epoch": 0.10344031401523897,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.4154,
+      "step": 56
+    },
+    {
+      "epoch": 0.11082890787347033,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.2e-05,
+      "loss": 0.4355,
+      "step": 60
+    },
+    {
+      "epoch": 0.11821750173170169,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.4011,
+      "step": 64
+    },
+    {
+      "epoch": 0.12560609558993305,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.3987,
+      "step": 68
+    },
+    {
+      "epoch": 0.1329946894481644,
+      "grad_norm": 2.859375,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.4105,
+      "step": 72
+    },
+    {
+      "epoch": 0.14038328330639574,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.4073,
+      "step": 76
+    },
+    {
+      "epoch": 0.1477718771646271,
+      "grad_norm": 2.296875,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4145,
+      "step": 80
+    },
+    {
+      "epoch": 0.15516047102285846,
+      "grad_norm": 2.25,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.4038,
+      "step": 84
+    },
+    {
+      "epoch": 0.1625490648810898,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.76e-05,
+      "loss": 0.4027,
+      "step": 88
+    },
+    {
+      "epoch": 0.16993765873932118,
+      "grad_norm": 2.125,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.3993,
+      "step": 92
+    },
+    {
+      "epoch": 0.17732625259755253,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.4072,
+      "step": 96
+    },
+    {
+      "epoch": 0.18471484645578387,
+      "grad_norm": 2.3125,
+      "learning_rate": 2e-05,
+      "loss": 0.3966,
+      "step": 100
+    },
+    {
+      "epoch": 0.19210344031401524,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.9999659601637828e-05,
+      "loss": 0.3952,
+      "step": 104
+    },
+    {
+      "epoch": 0.1994920341722466,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.9998638429725526e-05,
+      "loss": 0.3997,
+      "step": 108
+    },
+    {
+      "epoch": 0.20688062803047794,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.9996936553784137e-05,
+      "loss": 0.4091,
+      "step": 112
+    },
+    {
+      "epoch": 0.2142692218887093,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.999455408967682e-05,
+      "loss": 0.404,
+      "step": 116
+    },
+    {
+      "epoch": 0.22165781574694066,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.999149119960095e-05,
+      "loss": 0.4082,
+      "step": 120
+    },
+    {
+      "epoch": 0.229046409605172,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.9987748092077082e-05,
+      "loss": 0.3819,
+      "step": 124
+    },
+    {
+      "epoch": 0.23643500346340338,
+      "grad_norm": 1.9296875,
+      "learning_rate": 1.998332502193475e-05,
+      "loss": 0.3985,
+      "step": 128
+    },
+    {
+      "epoch": 0.24382359732163472,
+      "grad_norm": 2.21875,
+      "learning_rate": 1.9978222290295116e-05,
+      "loss": 0.4103,
+      "step": 132
+    },
+    {
+      "epoch": 0.2512121911798661,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.9972440244550485e-05,
+      "loss": 0.3708,
+      "step": 136
+    },
+    {
+      "epoch": 0.2586007850380974,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.9965979278340638e-05,
+      "loss": 0.4049,
+      "step": 140
+    },
+    {
+      "epoch": 0.2659893788963288,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.995883983152603e-05,
+      "loss": 0.3924,
+      "step": 144
+    },
+    {
+      "epoch": 0.27337797275456016,
+      "grad_norm": 2.0,
+      "learning_rate": 1.995102239015787e-05,
+      "loss": 0.4132,
+      "step": 148
+    },
+    {
+      "epoch": 0.2807665666127915,
+      "grad_norm": 2.171875,
+      "learning_rate": 1.9942527486445e-05,
+      "loss": 0.3873,
+      "step": 152
+    },
+    {
+      "epoch": 0.28815516047102285,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.9933355698717683e-05,
+      "loss": 0.403,
+      "step": 156
+    },
+    {
+      "epoch": 0.2955437543292542,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.9923507651388224e-05,
+      "loss": 0.3738,
+      "step": 160
+    },
+    {
+      "epoch": 0.30293234818748555,
+      "grad_norm": 1.9765625,
+      "learning_rate": 1.991298401490846e-05,
+      "loss": 0.4014,
+      "step": 164
+    },
+    {
+      "epoch": 0.3103209420457169,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.9901785505724117e-05,
+      "loss": 0.3864,
+      "step": 168
+    },
+    {
+      "epoch": 0.3177095359039483,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.988991288622603e-05,
+      "loss": 0.3689,
+      "step": 172
+    },
+    {
+      "epoch": 0.3250981297621796,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.9877366964698242e-05,
+      "loss": 0.3784,
+      "step": 176
+    },
+    {
+      "epoch": 0.332486723620411,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.9864148595262988e-05,
+      "loss": 0.369,
+      "step": 180
+    },
+    {
+      "epoch": 0.33987531747864236,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.985025867782252e-05,
+      "loss": 0.373,
+      "step": 184
+    },
+    {
+      "epoch": 0.3472639113368737,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.9835698157997877e-05,
+      "loss": 0.3568,
+      "step": 188
+    },
+    {
+      "epoch": 0.35465250519510505,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.9820468027064478e-05,
+      "loss": 0.3855,
+      "step": 192
+    },
+    {
+      "epoch": 0.3620410990533364,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.9804569321884638e-05,
+      "loss": 0.3731,
+      "step": 196
+    },
+    {
+      "epoch": 0.36942969291156774,
+      "grad_norm": 2.125,
+      "learning_rate": 1.978800312483701e-05,
+      "loss": 0.3738,
+      "step": 200
+    },
+    {
+      "epoch": 0.3768182867697991,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.9770770563742854e-05,
+      "loss": 0.3719,
+      "step": 204
+    },
+    {
+      "epoch": 0.3842068806280305,
+      "grad_norm": 2.125,
+      "learning_rate": 1.975287281178929e-05,
+      "loss": 0.3838,
+      "step": 208
+    },
+    {
+      "epoch": 0.3915954744862618,
+      "grad_norm": 1.8984375,
+      "learning_rate": 1.9734311087449408e-05,
+      "loss": 0.3605,
+      "step": 212
+    },
+    {
+      "epoch": 0.3989840683444932,
+      "grad_norm": 1.921875,
+      "learning_rate": 1.9715086654399317e-05,
+      "loss": 0.3785,
+      "step": 216
+    },
+    {
+      "epoch": 0.40637266220272455,
+      "grad_norm": 1.734375,
+      "learning_rate": 1.9695200821432126e-05,
+      "loss": 0.3627,
+      "step": 220
+    },
+    {
+      "epoch": 0.4137612560609559,
+      "grad_norm": 2.125,
+      "learning_rate": 1.9674654942368824e-05,
+      "loss": 0.357,
+      "step": 224
+    },
+    {
+      "epoch": 0.42114984991918725,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.965345041596613e-05,
+      "loss": 0.387,
+      "step": 228
+    },
+    {
+      "epoch": 0.4285384437774186,
+      "grad_norm": 2.265625,
+      "learning_rate": 1.963158868582126e-05,
+      "loss": 0.3789,
+      "step": 232
+    },
+    {
+      "epoch": 0.43592703763564994,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.9609071240273637e-05,
+      "loss": 0.3792,
+      "step": 236
+    },
+    {
+      "epoch": 0.4433156314938813,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.958589961230358e-05,
+      "loss": 0.3735,
+      "step": 240
+    },
+    {
+      "epoch": 0.4507042253521127,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.9562075379427926e-05,
+      "loss": 0.387,
+      "step": 244
+    },
+    {
+      "epoch": 0.458092819210344,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.953760016359265e-05,
+      "loss": 0.385,
+      "step": 248
+    },
+    {
+      "epoch": 0.4654814130685754,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.951247563106243e-05,
+      "loss": 0.3725,
+      "step": 252
+    },
+    {
+      "epoch": 0.47287000692680675,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.9486703492307207e-05,
+      "loss": 0.3739,
+      "step": 256
+    },
+    {
+      "epoch": 0.48025860078503807,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.9460285501885744e-05,
+      "loss": 0.3721,
+      "step": 260
+    },
+    {
+      "epoch": 0.48764719464326944,
+      "grad_norm": 1.7578125,
+      "learning_rate": 1.943322345832618e-05,
+      "loss": 0.3764,
+      "step": 264
+    },
+    {
+      "epoch": 0.4950357885015008,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.9405519204003577e-05,
+      "loss": 0.3491,
+      "step": 268
+    },
+    {
+      "epoch": 0.5024243823597322,
+      "grad_norm": 1.828125,
+      "learning_rate": 1.9377174625014485e-05,
+      "loss": 0.3924,
+      "step": 272
+    },
+    {
+      "epoch": 0.5098129762179635,
+      "grad_norm": 1.96875,
+      "learning_rate": 1.9348191651048565e-05,
+      "loss": 0.3416,
+      "step": 276
+    },
+    {
+      "epoch": 0.5172015700761948,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.9318572255257192e-05,
+      "loss": 0.3718,
+      "step": 280
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.9288318454119122e-05,
+      "loss": 0.3684,
+      "step": 284
+    },
+    {
+      "epoch": 0.5319787577926576,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.9257432307303232e-05,
+      "loss": 0.3725,
+      "step": 288
+    },
+    {
+      "epoch": 0.5393673516508889,
+      "grad_norm": 1.7421875,
+      "learning_rate": 1.9225915917528277e-05,
+      "loss": 0.3816,
+      "step": 292
+    },
+    {
+      "epoch": 0.5467559455091203,
+      "grad_norm": 1.9921875,
+      "learning_rate": 1.919377143041975e-05,
+      "loss": 0.3814,
+      "step": 296
+    },
+    {
+      "epoch": 0.5541445393673516,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.916100103436381e-05,
+      "loss": 0.3533,
+      "step": 300
+    },
+    {
+      "epoch": 0.561533133225583,
+      "grad_norm": 1.9296875,
+      "learning_rate": 1.9127606960358274e-05,
+      "loss": 0.3694,
+      "step": 304
+    },
+    {
+      "epoch": 0.5689217270838144,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.9093591481860772e-05,
+      "loss": 0.3755,
+      "step": 308
+    },
+    {
+      "epoch": 0.5763103209420457,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.9058956914633933e-05,
+      "loss": 0.385,
+      "step": 312
+    },
+    {
+      "epoch": 0.583698914800277,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.9023705616587747e-05,
+      "loss": 0.3513,
+      "step": 316
+    },
+    {
+      "epoch": 0.5910875086585085,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.8987839987619042e-05,
+      "loss": 0.3838,
+      "step": 320
+    },
+    {
+      "epoch": 0.5984761025167398,
+      "grad_norm": 1.921875,
+      "learning_rate": 1.895136246944809e-05,
+      "loss": 0.3572,
+      "step": 324
+    },
+    {
+      "epoch": 0.6058646963749711,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.8914275545452377e-05,
+      "loss": 0.3766,
+      "step": 328
+    },
+    {
+      "epoch": 0.6132532902332025,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.887658174049754e-05,
+      "loss": 0.3733,
+      "step": 332
+    },
+    {
+      "epoch": 0.6206418840914338,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.8838283620765476e-05,
+      "loss": 0.3438,
+      "step": 336
+    },
+    {
+      "epoch": 0.6280304779496652,
+      "grad_norm": 1.828125,
+      "learning_rate": 1.879938379357962e-05,
+      "loss": 0.3589,
+      "step": 340
+    },
+    {
+      "epoch": 0.6354190718078966,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.8759884907227485e-05,
+      "loss": 0.3486,
+      "step": 344
+    },
+    {
+      "epoch": 0.6428076656661279,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.87197896507803e-05,
+      "loss": 0.359,
+      "step": 348
+    },
+    {
+      "epoch": 0.6501962595243592,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.867910075390999e-05,
+      "loss": 0.3461,
+      "step": 352
+    },
+    {
+      "epoch": 0.6575848533825907,
+      "grad_norm": 1.828125,
+      "learning_rate": 1.8637820986703335e-05,
+      "loss": 0.3516,
+      "step": 356
+    },
+    {
+      "epoch": 0.664973447240822,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.8595953159473357e-05,
+      "loss": 0.3521,
+      "step": 360
+    },
+    {
+      "epoch": 0.6723620410990533,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.8553500122568023e-05,
+      "loss": 0.3536,
+      "step": 364
+    },
+    {
+      "epoch": 0.6797506349572847,
+      "grad_norm": 1.7578125,
+      "learning_rate": 1.8510464766176178e-05,
+      "loss": 0.3578,
+      "step": 368
+    },
+    {
+      "epoch": 0.687139228815516,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.8466850020130786e-05,
+      "loss": 0.3491,
+      "step": 372
+    },
+    {
+      "epoch": 0.6945278226737474,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.8422658853709475e-05,
+      "loss": 0.3551,
+      "step": 376
+    },
+    {
+      "epoch": 0.7019164165319788,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.8377894275432376e-05,
+      "loss": 0.3497,
+      "step": 380
+    },
+    {
+      "epoch": 0.7093050103902101,
+      "grad_norm": 1.96875,
+      "learning_rate": 1.833255933285732e-05,
+      "loss": 0.3664,
+      "step": 384
+    },
+    {
+      "epoch": 0.7166936042484414,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.8286657112372342e-05,
+      "loss": 0.3769,
+      "step": 388
+    },
+    {
+      "epoch": 0.7240821981066728,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.8240190738985578e-05,
+      "loss": 0.3586,
+      "step": 392
+    },
+    {
+      "epoch": 0.7314707919649042,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.819316337611251e-05,
+      "loss": 0.3612,
+      "step": 396
+    },
+    {
+      "epoch": 0.7388593858231355,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.8145578225360594e-05,
+      "loss": 0.3575,
+      "step": 400
+    },
+    {
+      "epoch": 0.7462479796813669,
+      "grad_norm": 1.7578125,
+      "learning_rate": 1.809743852631131e-05,
+      "loss": 0.3572,
+      "step": 404
+    },
+    {
+      "epoch": 0.7536365735395982,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.8048747556299595e-05,
+      "loss": 0.375,
+      "step": 408
+    },
+    {
+      "epoch": 0.7610251673978295,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.7999508630190742e-05,
+      "loss": 0.3633,
+      "step": 412
+    },
+    {
+      "epoch": 0.768413761256061,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.7949725100154707e-05,
+      "loss": 0.3662,
+      "step": 416
+    },
+    {
+      "epoch": 0.7758023551142923,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.789940035543792e-05,
+      "loss": 0.3508,
+      "step": 420
+    },
+    {
+      "epoch": 0.7831909489725236,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.7848537822132498e-05,
+      "loss": 0.3513,
+      "step": 424
+    },
+    {
+      "epoch": 0.790579542830755,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.7797140962943062e-05,
+      "loss": 0.3558,
+      "step": 428
+    },
+    {
+      "epoch": 0.7979681366889864,
+      "grad_norm": 1.8984375,
+      "learning_rate": 1.7745213276950947e-05,
+      "loss": 0.3648,
+      "step": 432
+    },
+    {
+      "epoch": 0.8053567305472177,
+      "grad_norm": 2.0,
+      "learning_rate": 1.7692758299376002e-05,
+      "loss": 0.3584,
+      "step": 436
+    },
+    {
+      "epoch": 0.8127453244054491,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.7639779601335916e-05,
+      "loss": 0.3601,
+      "step": 440
+    },
+    {
+      "epoch": 0.8201339182636804,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.7586280789603104e-05,
+      "loss": 0.3664,
+      "step": 444
+    },
+    {
+      "epoch": 0.8275225121219117,
+      "grad_norm": 1.7421875,
+      "learning_rate": 1.753226550635914e-05,
+      "loss": 0.3371,
+      "step": 448
+    },
+    {
+      "epoch": 0.8349111059801432,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.7477737428946814e-05,
+      "loss": 0.3533,
+      "step": 452
+    },
+    {
+      "epoch": 0.8422996998383745,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.742270026961978e-05,
+      "loss": 0.3477,
+      "step": 456
+    },
+    {
+      "epoch": 0.8496882936966058,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.736715777528981e-05,
+      "loss": 0.3471,
+      "step": 460
+    },
+    {
+      "epoch": 0.8570768875548372,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.7311113727271728e-05,
+      "loss": 0.3361,
+      "step": 464
+    },
+    {
+      "epoch": 0.8644654814130686,
+      "grad_norm": 1.7890625,
+      "learning_rate": 1.725457194102596e-05,
+      "loss": 0.3327,
+      "step": 468
+    },
+    {
+      "epoch": 0.8718540752712999,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.71975362658988e-05,
+      "loss": 0.3411,
+      "step": 472
+    },
+    {
+      "epoch": 0.8792426691295313,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.7140010584860322e-05,
+      "loss": 0.3582,
+      "step": 476
+    },
+    {
+      "epoch": 0.8866312629877626,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.708199881424005e-05,
+      "loss": 0.3464,
+      "step": 480
+    },
+    {
+      "epoch": 0.8940198568459939,
+      "grad_norm": 1.7421875,
+      "learning_rate": 1.7023504903460325e-05,
+      "loss": 0.3534,
+      "step": 484
+    },
+    {
+      "epoch": 0.9014084507042254,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.696453283476743e-05,
+      "loss": 0.3791,
+      "step": 488
+    },
+    {
+      "epoch": 0.9087970445624567,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.6905086622960488e-05,
+      "loss": 0.3647,
+      "step": 492
+    },
+    {
+      "epoch": 0.916185638420688,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.6845170315118124e-05,
+      "loss": 0.3719,
+      "step": 496
+    },
+    {
+      "epoch": 0.9235742322789194,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.678478799032295e-05,
+      "loss": 0.3428,
+      "step": 500
+    },
+    {
+      "epoch": 0.9309628261371508,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.6723943759383857e-05,
+      "loss": 0.3496,
+      "step": 504
+    },
+    {
+      "epoch": 0.9383514199953821,
+      "grad_norm": 1.75,
+      "learning_rate": 1.666264176455616e-05,
+      "loss": 0.347,
+      "step": 508
+    },
+    {
+      "epoch": 0.9457400138536135,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.660088617925959e-05,
+      "loss": 0.3331,
+      "step": 512
+    },
+    {
+      "epoch": 0.9531286077118448,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.6538681207794153e-05,
+      "loss": 0.3611,
+      "step": 516
+    },
+    {
+      "epoch": 0.9605172015700761,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.6476031085053937e-05,
+      "loss": 0.3658,
+      "step": 520
+    },
+    {
+      "epoch": 0.9679057954283076,
+      "grad_norm": 1.875,
+      "learning_rate": 1.6412940076238782e-05,
+      "loss": 0.3569,
+      "step": 524
+    },
+    {
+      "epoch": 0.9752943892865389,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.6349412476563893e-05,
+      "loss": 0.3687,
+      "step": 528
+    },
+    {
+      "epoch": 0.9826829831447702,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.628545261096745e-05,
+      "loss": 0.3644,
+      "step": 532
+    },
+    {
+      "epoch": 0.9900715770030016,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.622106483381615e-05,
+      "loss": 0.3331,
+      "step": 536
+    },
+    {
+      "epoch": 0.997460170861233,
+      "grad_norm": 1.75,
+      "learning_rate": 1.615625352860877e-05,
+      "loss": 0.3317,
+      "step": 540
+    }
+  ],
+  "logging_steps": 4,
+  "max_steps": 1623,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1982217680707912e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840367e8c92b2a0e10e8e82e133ab663c89d1d1accfd635f8673020a8200df93
+size 5432