Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/workspace/philhoon/models/kv-fusion/tqa-kv-llama3-base",
+  "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:cc3424a3750d4c63a681d799b3f86795a6c49e72d4ea578285d545b7eea4e7dc
+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 sha256:5d23d40fb65f1ca99948815bd3580101c849f3479434a0f41ca62358edc777b1
+size 4920065288

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b17b6f8973370b4be2694bea1b0116f04de8a26e7832ebdf418108813a6fd0
+size 4915916144

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba62fab11f0555d4da19f0e9267a9d3afb30b2b7fb21700c3765a9b0f5dae7d
+size 4915916176

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2ff3a1ccfc5a0979cae306460670caf3a62e4d3e585620a930d051c090fe56
+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:d64e49b3ee0a2ad04ed003c8bb8a3d9725e80ce6025f8bd12d180bebb6937e79
+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": 1.8984375,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.2922,
+      "step": 4
+    },
+    {
+      "epoch": 0.014777187716462711,
+      "grad_norm": 2.078125,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.3078,
+      "step": 8
+    },
+    {
+      "epoch": 0.022165781574694066,
+      "grad_norm": 2.390625,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.2979,
+      "step": 12
+    },
+    {
+      "epoch": 0.029554375432925422,
+      "grad_norm": 2.078125,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.2788,
+      "step": 16
+    },
+    {
+      "epoch": 0.03694296929115678,
+      "grad_norm": 1.9921875,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.3001,
+      "step": 20
+    },
+    {
+      "epoch": 0.04433156314938813,
+      "grad_norm": 1.828125,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.304,
+      "step": 24
+    },
+    {
+      "epoch": 0.051720157007619484,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.2816,
+      "step": 28
+    },
+    {
+      "epoch": 0.059108750865850844,
+      "grad_norm": 1.9375,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.277,
+      "step": 32
+    },
+    {
+      "epoch": 0.0664973447240822,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.2677,
+      "step": 36
+    },
+    {
+      "epoch": 0.07388593858231356,
+      "grad_norm": 1.96875,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2739,
+      "step": 40
+    },
+    {
+      "epoch": 0.0812745324405449,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.76e-05,
+      "loss": 0.2485,
+      "step": 44
+    },
+    {
+      "epoch": 0.08866312629877626,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.2675,
+      "step": 48
+    },
+    {
+      "epoch": 0.09605172015700762,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.9999181232057437e-05,
+      "loss": 0.2547,
+      "step": 52
+    },
+    {
+      "epoch": 0.10344031401523897,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.9992631892952108e-05,
+      "loss": 0.2516,
+      "step": 56
+    },
+    {
+      "epoch": 0.11082890787347033,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.9979537504476945e-05,
+      "loss": 0.2558,
+      "step": 60
+    },
+    {
+      "epoch": 0.11821750173170169,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.995990664329323e-05,
+      "loss": 0.2382,
+      "step": 64
+    },
+    {
+      "epoch": 0.12560609558993305,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.993375216737042e-05,
+      "loss": 0.2376,
+      "step": 68
+    },
+    {
+      "epoch": 0.1329946894481644,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.9901091207564326e-05,
+      "loss": 0.2359,
+      "step": 72
+    },
+    {
+      "epoch": 0.14038328330639574,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.986194515639662e-05,
+      "loss": 0.2217,
+      "step": 76
+    },
+    {
+      "epoch": 0.1477718771646271,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.981633965404302e-05,
+      "loss": 0.2247,
+      "step": 80
+    },
+    {
+      "epoch": 0.15516047102285846,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.9764304571539266e-05,
+      "loss": 0.2082,
+      "step": 84
+    },
+    {
+      "epoch": 0.1625490648810898,
+      "grad_norm": 1.875,
+      "learning_rate": 1.9705873991215973e-05,
+      "loss": 0.2053,
+      "step": 88
+    },
+    {
+      "epoch": 0.16993765873932118,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.9641086184375148e-05,
+      "loss": 0.1989,
+      "step": 92
+    },
+    {
+      "epoch": 0.17732625259755253,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.956998358622293e-05,
+      "loss": 0.2069,
+      "step": 96
+    },
+    {
+      "epoch": 0.18471484645578387,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.9492612768075094e-05,
+      "loss": 0.2001,
+      "step": 100
+    },
+    {
+      "epoch": 0.19210344031401524,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.940902440685339e-05,
+      "loss": 0.1971,
+      "step": 104
+    },
+    {
+      "epoch": 0.1994920341722466,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.9319273251892805e-05,
+      "loss": 0.2056,
+      "step": 108
+    },
+    {
+      "epoch": 0.20688062803047794,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.922341808908144e-05,
+      "loss": 0.2129,
+      "step": 112
+    },
+    {
+      "epoch": 0.2142692218887093,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.912152170235646e-05,
+      "loss": 0.2068,
+      "step": 116
+    },
+    {
+      "epoch": 0.22165781574694066,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.9013650832581424e-05,
+      "loss": 0.203,
+      "step": 120
+    },
+    {
+      "epoch": 0.229046409605172,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.8899876133831835e-05,
+      "loss": 0.1934,
+      "step": 124
+    },
+    {
+      "epoch": 0.23643500346340338,
+      "grad_norm": 1.9140625,
+      "learning_rate": 1.8780272127117606e-05,
+      "loss": 0.1941,
+      "step": 128
+    },
+    {
+      "epoch": 0.24382359732163472,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.865491715157273e-05,
+      "loss": 0.2016,
+      "step": 132
+    },
+    {
+      "epoch": 0.2512121911798661,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.852389331314411e-05,
+      "loss": 0.1838,
+      "step": 136
+    },
+    {
+      "epoch": 0.2586007850380974,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.838728643081321e-05,
+      "loss": 0.2002,
+      "step": 140
+    },
+    {
+      "epoch": 0.2659893788963288,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.8245185980385673e-05,
+      "loss": 0.1916,
+      "step": 144
+    },
+    {
+      "epoch": 0.27337797275456016,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.809768503588578e-05,
+      "loss": 0.2103,
+      "step": 148
+    },
+    {
+      "epoch": 0.2807665666127915,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.7944880208594156e-05,
+      "loss": 0.1959,
+      "step": 152
+    },
+    {
+      "epoch": 0.28815516047102285,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.7786871583768536e-05,
+      "loss": 0.1975,
+      "step": 156
+    },
+    {
+      "epoch": 0.2955437543292542,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.7623762655089208e-05,
+      "loss": 0.1788,
+      "step": 160
+    },
+    {
+      "epoch": 0.30293234818748555,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.745566025687193e-05,
+      "loss": 0.1997,
+      "step": 164
+    },
+    {
+      "epoch": 0.3103209420457169,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.728267449409278e-05,
+      "loss": 0.1971,
+      "step": 168
+    },
+    {
+      "epoch": 0.3177095359039483,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.7104918670270763e-05,
+      "loss": 0.1835,
+      "step": 172
+    },
+    {
+      "epoch": 0.3250981297621796,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.692250921325544e-05,
+      "loss": 0.1883,
+      "step": 176
+    },
+    {
+      "epoch": 0.332486723620411,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.6735565598968114e-05,
+      "loss": 0.1825,
+      "step": 180
+    },
+    {
+      "epoch": 0.33987531747864236,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.6544210273146608e-05,
+      "loss": 0.1931,
+      "step": 184
+    },
+    {
+      "epoch": 0.3472639113368737,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.6348568571144816e-05,
+      "loss": 0.183,
+      "step": 188
+    },
+    {
+      "epoch": 0.35465250519510505,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.6148768635839623e-05,
+      "loss": 0.1966,
+      "step": 192
+    },
+    {
+      "epoch": 0.3620410990533364,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.5944941333698912e-05,
+      "loss": 0.188,
+      "step": 196
+    },
+    {
+      "epoch": 0.36942969291156774,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.5737220169065656e-05,
+      "loss": 0.1858,
+      "step": 200
+    },
+    {
+      "epoch": 0.3768182867697991,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.552574119671423e-05,
+      "loss": 0.1842,
+      "step": 204
+    },
+    {
+      "epoch": 0.3842068806280305,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.5310642932736253e-05,
+      "loss": 0.1899,
+      "step": 208
+    },
+    {
+      "epoch": 0.3915954744862618,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.5092066263814245e-05,
+      "loss": 0.1785,
+      "step": 212
+    },
+    {
+      "epoch": 0.3989840683444932,
+      "grad_norm": 1.875,
+      "learning_rate": 1.487015435494263e-05,
+      "loss": 0.1949,
+      "step": 216
+    },
+    {
+      "epoch": 0.40637266220272455,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.464505255565643e-05,
+      "loss": 0.1787,
+      "step": 220
+    },
+    {
+      "epoch": 0.4137612560609559,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.4416908304829142e-05,
+      "loss": 0.173,
+      "step": 224
+    },
+    {
+      "epoch": 0.42114984991918725,
+      "grad_norm": 1.9453125,
+      "learning_rate": 1.4185871034102117e-05,
+      "loss": 0.1945,
+      "step": 228
+    },
+    {
+      "epoch": 0.4285384437774186,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.3952092070008669e-05,
+      "loss": 0.1949,
+      "step": 232
+    },
+    {
+      "epoch": 0.43592703763564994,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.3715724534857127e-05,
+      "loss": 0.1824,
+      "step": 236
+    },
+    {
+      "epoch": 0.4433156314938813,
+      "grad_norm": 1.625,
+      "learning_rate": 1.347692324643759e-05,
+      "loss": 0.1844,
+      "step": 240
+    },
+    {
+      "epoch": 0.4507042253521127,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.323584461661823e-05,
+      "loss": 0.193,
+      "step": 244
+    },
+    {
+      "epoch": 0.458092819210344,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.2992646548897442e-05,
+      "loss": 0.195,
+      "step": 248
+    },
+    {
+      "epoch": 0.4654814130685754,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.2747488334979064e-05,
+      "loss": 0.1844,
+      "step": 252
+    },
+    {
+      "epoch": 0.47287000692680675,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.2500530550438232e-05,
+      "loss": 0.1919,
+      "step": 256
+    },
+    {
+      "epoch": 0.48025860078503807,
+      "grad_norm": 1.75,
+      "learning_rate": 1.2251934949546446e-05,
+      "loss": 0.1966,
+      "step": 260
+    },
+    {
+      "epoch": 0.48764719464326944,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.200186435932449e-05,
+      "loss": 0.1924,
+      "step": 264
+    },
+    {
+      "epoch": 0.4950357885015008,
+      "grad_norm": 1.390625,
+      "learning_rate": 1.1750482572892781e-05,
+      "loss": 0.1744,
+      "step": 268
+    },
+    {
+      "epoch": 0.5024243823597322,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.1497954242188913e-05,
+      "loss": 0.2026,
+      "step": 272
+    },
+    {
+      "epoch": 0.5098129762179635,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.1244444770122707e-05,
+      "loss": 0.1669,
+      "step": 276
+    },
+    {
+      "epoch": 0.5172015700761948,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.0990120202239324e-05,
+      "loss": 0.187,
+      "step": 280
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.073514711796155e-05,
+      "loss": 0.1832,
+      "step": 284
+    },
+    {
+      "epoch": 0.5319787577926576,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.0479692521482316e-05,
+      "loss": 0.1834,
+      "step": 288
+    },
+    {
+      "epoch": 0.5393673516508889,
+      "grad_norm": 1.828125,
+      "learning_rate": 1.0223923732379049e-05,
+      "loss": 0.1929,
+      "step": 292
+    },
+    {
+      "epoch": 0.5467559455091203,
+      "grad_norm": 1.71875,
+      "learning_rate": 9.96800827602143e-06,
+      "loss": 0.1922,
+      "step": 296
+    },
+    {
+      "epoch": 0.5541445393673516,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.712113773844361e-06,
+      "loss": 0.1787,
+      "step": 300
+    },
+    {
+      "epoch": 0.561533133225583,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.456407833558019e-06,
+      "loss": 0.1795,
+      "step": 304
+    },
+    {
+      "epoch": 0.5689217270838144,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.201057939366896e-06,
+      "loss": 0.1902,
+      "step": 308
+    },
+    {
+      "epoch": 0.5763103209420457,
+      "grad_norm": 1.9765625,
+      "learning_rate": 8.94623134226972e-06,
+      "loss": 0.2048,
+      "step": 312
+    },
+    {
+      "epoch": 0.583698914800277,
+      "grad_norm": 1.6796875,
+      "learning_rate": 8.692094950512145e-06,
+      "loss": 0.1799,
+      "step": 316
+    },
+    {
+      "epoch": 0.5910875086585085,
+      "grad_norm": 1.75,
+      "learning_rate": 8.438815220263942e-06,
+      "loss": 0.1958,
+      "step": 320
+    },
+    {
+      "epoch": 0.5984761025167398,
+      "grad_norm": 1.640625,
+      "learning_rate": 8.186558046592247e-06,
+      "loss": 0.1917,
+      "step": 324
+    },
+    {
+      "epoch": 0.6058646963749711,
+      "grad_norm": 1.7421875,
+      "learning_rate": 7.935488654802395e-06,
+      "loss": 0.2007,
+      "step": 328
+    },
+    {
+      "epoch": 0.6132532902332025,
+      "grad_norm": 1.703125,
+      "learning_rate": 7.685771492217387e-06,
+      "loss": 0.1977,
+      "step": 332
+    },
+    {
+      "epoch": 0.6206418840914338,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.437570120466943e-06,
+      "loss": 0.173,
+      "step": 336
+    },
+    {
+      "epoch": 0.6280304779496652,
+      "grad_norm": 1.625,
+      "learning_rate": 7.1910471083566725e-06,
+      "loss": 0.1826,
+      "step": 340
+    },
+    {
+      "epoch": 0.6354190718078966,
+      "grad_norm": 1.875,
+      "learning_rate": 6.946363925387546e-06,
+      "loss": 0.1842,
+      "step": 344
+    },
+    {
+      "epoch": 0.6428076656661279,
+      "grad_norm": 1.546875,
+      "learning_rate": 6.7036808359953585e-06,
+      "loss": 0.1834,
+      "step": 348
+    },
+    {
+      "epoch": 0.6501962595243592,
+      "grad_norm": 1.6875,
+      "learning_rate": 6.463156794579543e-06,
+      "loss": 0.189,
+      "step": 352
+    },
+    {
+      "epoch": 0.6575848533825907,
+      "grad_norm": 1.71875,
+      "learning_rate": 6.224949341390017e-06,
+      "loss": 0.1825,
+      "step": 356
+    },
+    {
+      "epoch": 0.664973447240822,
+      "grad_norm": 1.8203125,
+      "learning_rate": 5.989214499340267e-06,
+      "loss": 0.1802,
+      "step": 360
+    },
+    {
+      "epoch": 0.6723620410990533,
+      "grad_norm": 1.765625,
+      "learning_rate": 5.756106671814301e-06,
+      "loss": 0.1877,
+      "step": 364
+    },
+    {
+      "epoch": 0.6797506349572847,
+      "grad_norm": 1.7421875,
+      "learning_rate": 5.52577854153435e-06,
+      "loss": 0.1963,
+      "step": 368
+    },
+    {
+      "epoch": 0.687139228815516,
+      "grad_norm": 1.703125,
+      "learning_rate": 5.298380970555584e-06,
+      "loss": 0.1854,
+      "step": 372
+    },
+    {
+      "epoch": 0.6945278226737474,
+      "grad_norm": 1.6796875,
+      "learning_rate": 5.074062901453352e-06,
+      "loss": 0.1864,
+      "step": 376
+    },
+    {
+      "epoch": 0.7019164165319788,
+      "grad_norm": 1.7421875,
+      "learning_rate": 4.852971259767642e-06,
+      "loss": 0.1905,
+      "step": 380
+    },
+    {
+      "epoch": 0.7093050103902101,
+      "grad_norm": 1.84375,
+      "learning_rate": 4.635250857768696e-06,
+      "loss": 0.1988,
+      "step": 384
+    },
+    {
+      "epoch": 0.7166936042484414,
+      "grad_norm": 1.7265625,
+      "learning_rate": 4.4210442996067724e-06,
+      "loss": 0.1995,
+      "step": 388
+    },
+    {
+      "epoch": 0.7240821981066728,
+      "grad_norm": 1.703125,
+      "learning_rate": 4.210491887908201e-06,
+      "loss": 0.1927,
+      "step": 392
+    },
+    {
+      "epoch": 0.7314707919649042,
+      "grad_norm": 1.78125,
+      "learning_rate": 4.0037315318789e-06,
+      "loss": 0.1926,
+      "step": 396
+    },
+    {
+      "epoch": 0.7388593858231355,
+      "grad_norm": 1.890625,
+      "learning_rate": 3.800898656975599e-06,
+      "loss": 0.1961,
+      "step": 400
+    },
+    {
+      "epoch": 0.7462479796813669,
+      "grad_norm": 1.9921875,
+      "learning_rate": 3.602126116203819e-06,
+      "loss": 0.1981,
+      "step": 404
+    },
+    {
+      "epoch": 0.7536365735395982,
+      "grad_norm": 1.6484375,
+      "learning_rate": 3.407544103100824e-06,
+      "loss": 0.2058,
+      "step": 408
+    },
+    {
+      "epoch": 0.7610251673978295,
+      "grad_norm": 1.953125,
+      "learning_rate": 3.217280066460472e-06,
+      "loss": 0.2083,
+      "step": 412
+    },
+    {
+      "epoch": 0.768413761256061,
+      "grad_norm": 1.84375,
+      "learning_rate": 3.0314586268558486e-06,
+      "loss": 0.2052,
+      "step": 416
+    },
+    {
+      "epoch": 0.7758023551142923,
+      "grad_norm": 1.796875,
+      "learning_rate": 2.8502014950143376e-06,
+      "loss": 0.1999,
+      "step": 420
+    },
+    {
+      "epoch": 0.7831909489725236,
+      "grad_norm": 1.890625,
+      "learning_rate": 2.6736273920986166e-06,
+      "loss": 0.1983,
+      "step": 424
+    },
+    {
+      "epoch": 0.790579542830755,
+      "grad_norm": 1.78125,
+      "learning_rate": 2.5018519719457725e-06,
+      "loss": 0.2031,
+      "step": 428
+    },
+    {
+      "epoch": 0.7979681366889864,
+      "grad_norm": 1.8828125,
+      "learning_rate": 2.334987745315478e-06,
+      "loss": 0.2108,
+      "step": 432
+    },
+    {
+      "epoch": 0.8053567305472177,
+      "grad_norm": 1.8671875,
+      "learning_rate": 2.1731440061968536e-06,
+      "loss": 0.2072,
+      "step": 436
+    },
+    {
+      "epoch": 0.8127453244054491,
+      "grad_norm": 2.28125,
+      "learning_rate": 2.016426760222259e-06,
+      "loss": 0.2121,
+      "step": 440
+    },
+    {
+      "epoch": 0.8201339182636804,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.8649386552349136e-06,
+      "loss": 0.2142,
+      "step": 444
+    },
+    {
+      "epoch": 0.8275225121219117,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.718778914055873e-06,
+      "loss": 0.1974,
+      "step": 448
+    },
+    {
+      "epoch": 0.8349111059801432,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.5780432694942815e-06,
+      "loss": 0.2049,
+      "step": 452
+    },
+    {
+      "epoch": 0.8422996998383745,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.4428239016435953e-06,
+      "loss": 0.1979,
+      "step": 456
+    },
+    {
+      "epoch": 0.8496882936966058,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.3132093775047616e-06,
+      "loss": 0.2086,
+      "step": 460
+    },
+    {
+      "epoch": 0.8570768875548372,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.1892845929759412e-06,
+      "loss": 0.2019,
+      "step": 464
+    },
+    {
+      "epoch": 0.8644654814130686,
+      "grad_norm": 1.8046875,
+      "learning_rate": 1.07113071724675e-06,
+      "loss": 0.2005,
+      "step": 468
+    },
+    {
+      "epoch": 0.8718540752712999,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.588251396334524e-07,
+      "loss": 0.206,
+      "step": 472
+    },
+    {
+      "epoch": 0.8792426691295313,
+      "grad_norm": 1.953125,
+      "learning_rate": 8.524414188899266e-07,
+      "loss": 0.2248,
+      "step": 476
+    },
+    {
+      "epoch": 0.8866312629877626,
+      "grad_norm": 1.8984375,
+      "learning_rate": 7.520492350275876e-07,
+      "loss": 0.207,
+      "step": 480
+    },
+    {
+      "epoch": 0.8940198568459939,
+      "grad_norm": 1.875,
+      "learning_rate": 6.577143436758659e-07,
+      "loss": 0.2118,
+      "step": 484
+    },
+    {
+      "epoch": 0.9014084507042254,
+      "grad_norm": 1.8203125,
+      "learning_rate": 5.694985330130698e-07,
+      "loss": 0.2358,
+      "step": 488
+    },
+    {
+      "epoch": 0.9087970445624567,
+      "grad_norm": 2.109375,
+      "learning_rate": 4.874595832959061e-07,
+      "loss": 0.2224,
+      "step": 492
+    },
+    {
+      "epoch": 0.916185638420688,
+      "grad_norm": 1.9609375,
+      "learning_rate": 4.1165122901414055e-07,
+      "loss": 0.2375,
+      "step": 496
+    },
+    {
+      "epoch": 0.9235742322789194,
+      "grad_norm": 1.859375,
+      "learning_rate": 3.4212312369516496e-07,
+      "loss": 0.2169,
+      "step": 500
+    },
+    {
+      "epoch": 0.9309628261371508,
+      "grad_norm": 1.953125,
+      "learning_rate": 2.789208073815608e-07,
+      "loss": 0.2191,
+      "step": 504
+    },
+    {
+      "epoch": 0.9383514199953821,
+      "grad_norm": 2.125,
+      "learning_rate": 2.220856768029367e-07,
+      "loss": 0.2225,
+      "step": 508
+    },
+    {
+      "epoch": 0.9457400138536135,
+      "grad_norm": 2.078125,
+      "learning_rate": 1.7165495826158896e-07,
+      "loss": 0.2143,
+      "step": 512
+    },
+    {
+      "epoch": 0.9531286077118448,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.276616832497346e-07,
+      "loss": 0.2324,
+      "step": 516
+    },
+    {
+      "epoch": 0.9605172015700761,
+      "grad_norm": 2.0,
+      "learning_rate": 9.013466681429994e-08,
+      "loss": 0.2411,
+      "step": 520
+    },
+    {
+      "epoch": 0.9679057954283076,
+      "grad_norm": 2.03125,
+      "learning_rate": 5.9098488683417834e-08,
+      "loss": 0.234,
+      "step": 524
+    },
+    {
+      "epoch": 0.9752943892865389,
+      "grad_norm": 2.234375,
+      "learning_rate": 3.457347716701587e-08,
+      "loss": 0.2513,
+      "step": 528
+    },
+    {
+      "epoch": 0.9826829831447702,
+      "grad_norm": 2.0,
+      "learning_rate": 1.6575695842027116e-08,
+      "loss": 0.2358,
+      "step": 532
+    },
+    {
+      "epoch": 0.9900715770030016,
+      "grad_norm": 2.109375,
+      "learning_rate": 5.116933030946403e-09,
+      "loss": 0.2242,
+      "step": 536
+    },
+    {
+      "epoch": 0.997460170861233,
+      "grad_norm": 1.96875,
+      "learning_rate": 2.0469408062440131e-10,
+      "loss": 0.225,
+      "step": 540
+    }
+  ],
+  "logging_steps": 4,
+  "max_steps": 541,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1973917830354567e+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 sha256:34d6f42e99ee872f7ee7ed0133096e38ffb889c51307d445c54d726ee98d550f
+size 5432