Upload folder using huggingface_hub

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "../../models/moe/routing/onlyRouterTrue_aveSVLossFalse_lr5e-03",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 7168,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "num_local_experts": 8,
+  "output_router_logits": true,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "router_aux_loss_coef": 0.0,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "use_cache": true,
+  "vocab_size": 99584
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61351c91a915689400aeb5f9a41b0a0d601706ad0fba739ad9f7d51e38d9e43b
+size 4988379392

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d4aea22fe1e0ace2aa78b880f8e26baf0fc1c1a8756d5805a30679799aa098
+size 4987299352

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b7e202b6a0a2c9aa482321ad9315891a3b79e7b6d8d57a9c8a28bc4e8f98e3
+size 4991535416

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9af63037c8a97b40004960955d22f5de9391211a71e9383832ab8d2683ebb8
+size 3566400304

model.safetensors.index.json

@@ -0,0 +1,754 @@
+{
+  "metadata": {
+    "total_size": 18533519360
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

trainer_state.json

@@ -0,0 +1,767 @@
+{
+  "best_metric": 0.2237541824579239,
+  "best_model_checkpoint": "../../models/moe/moe/onlyRouterTrue_aveSVLossFalse_lr5e-03_ralc0.00/checkpoint-13692",
+  "epoch": 1.0,
+  "eval_steps": 3423,
+  "global_step": 13692,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010005842827928718,
+      "grad_norm": 3.4739856719970703,
+      "learning_rate": 4.9987649590704944e-05,
+      "loss": 0.6176,
+      "step": 137
+    },
+    {
+      "epoch": 0.020011685655857436,
+      "grad_norm": 2.701633930206299,
+      "learning_rate": 4.9950610565428546e-05,
+      "loss": 0.5809,
+      "step": 274
+    },
+    {
+      "epoch": 0.03001752848378615,
+      "grad_norm": 2.7198803424835205,
+      "learning_rate": 4.988891951994058e-05,
+      "loss": 0.572,
+      "step": 411
+    },
+    {
+      "epoch": 0.04002337131171487,
+      "grad_norm": 2.594041109085083,
+      "learning_rate": 4.9802637407013966e-05,
+      "loss": 0.5511,
+      "step": 548
+    },
+    {
+      "epoch": 0.05002921413964359,
+      "grad_norm": 2.6721420288085938,
+      "learning_rate": 4.969184947620146e-05,
+      "loss": 0.5502,
+      "step": 685
+    },
+    {
+      "epoch": 0.0600350569675723,
+      "grad_norm": 2.6376290321350098,
+      "learning_rate": 4.9556665189606316e-05,
+      "loss": 0.5266,
+      "step": 822
+    },
+    {
+      "epoch": 0.07004089979550102,
+      "grad_norm": 2.9528913497924805,
+      "learning_rate": 4.93972181137301e-05,
+      "loss": 0.536,
+      "step": 959
+    },
+    {
+      "epoch": 0.08004674262342974,
+      "grad_norm": 2.715660810470581,
+      "learning_rate": 4.9213665787504655e-05,
+      "loss": 0.5056,
+      "step": 1096
+    },
+    {
+      "epoch": 0.09005258545135846,
+      "grad_norm": 3.309116840362549,
+      "learning_rate": 4.900618956663845e-05,
+      "loss": 0.5124,
+      "step": 1233
+    },
+    {
+      "epoch": 0.10005842827928718,
+      "grad_norm": 2.226123332977295,
+      "learning_rate": 4.877499444443122e-05,
+      "loss": 0.5199,
+      "step": 1370
+    },
+    {
+      "epoch": 0.1100642711072159,
+      "grad_norm": 3.922006130218506,
+      "learning_rate": 4.852030884923388e-05,
+      "loss": 0.4957,
+      "step": 1507
+    },
+    {
+      "epoch": 0.1200701139351446,
+      "grad_norm": 3.2229082584381104,
+      "learning_rate": 4.82423844187538e-05,
+      "loss": 0.4864,
+      "step": 1644
+    },
+    {
+      "epoch": 0.13007595676307332,
+      "grad_norm": 1.936515212059021,
+      "learning_rate": 4.7941495751428536e-05,
+      "loss": 0.4653,
+      "step": 1781
+    },
+    {
+      "epoch": 0.14008179959100203,
+      "grad_norm": 2.966193199157715,
+      "learning_rate": 4.7617940135113606e-05,
+      "loss": 0.4722,
+      "step": 1918
+    },
+    {
+      "epoch": 0.15008764241893077,
+      "grad_norm": 3.2486863136291504,
+      "learning_rate": 4.7272037253352276e-05,
+      "loss": 0.4477,
+      "step": 2055
+    },
+    {
+      "epoch": 0.16009348524685948,
+      "grad_norm": 2.4895386695861816,
+      "learning_rate": 4.690412886951786e-05,
+      "loss": 0.4657,
+      "step": 2192
+    },
+    {
+      "epoch": 0.1700993280747882,
+      "grad_norm": 2.049923896789551,
+      "learning_rate": 4.651457848914021e-05,
+      "loss": 0.4538,
+      "step": 2329
+    },
+    {
+      "epoch": 0.1801051709027169,
+      "grad_norm": 2.0172815322875977,
+      "learning_rate": 4.610377100075045e-05,
+      "loss": 0.4317,
+      "step": 2466
+    },
+    {
+      "epoch": 0.19011101373064562,
+      "grad_norm": 2.2022132873535156,
+      "learning_rate": 4.5672112295598404e-05,
+      "loss": 0.4336,
+      "step": 2603
+    },
+    {
+      "epoch": 0.20011685655857436,
+      "grad_norm": 4.102416038513184,
+      "learning_rate": 4.5220028866618837e-05,
+      "loss": 0.4226,
+      "step": 2740
+    },
+    {
+      "epoch": 0.21012269938650308,
+      "grad_norm": 2.130418539047241,
+      "learning_rate": 4.4747967387042424e-05,
+      "loss": 0.4242,
+      "step": 2877
+    },
+    {
+      "epoch": 0.2201285422144318,
+      "grad_norm": 2.399773120880127,
+      "learning_rate": 4.4256394269067967e-05,
+      "loss": 0.4097,
+      "step": 3014
+    },
+    {
+      "epoch": 0.2301343850423605,
+      "grad_norm": 1.86017644405365,
+      "learning_rate": 4.3745795203031904e-05,
+      "loss": 0.4034,
+      "step": 3151
+    },
+    {
+      "epoch": 0.2401402278702892,
+      "grad_norm": 1.667731761932373,
+      "learning_rate": 4.321667467753034e-05,
+      "loss": 0.4108,
+      "step": 3288
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.48173779249191284,
+      "eval_runtime": 367.5367,
+      "eval_samples_per_second": 31.393,
+      "eval_steps_per_second": 7.85,
+      "step": 3423
+    },
+    {
+      "epoch": 0.2501460706982179,
+      "grad_norm": 5.194522857666016,
+      "learning_rate": 4.2669555480967783e-05,
+      "loss": 0.3973,
+      "step": 3425
+    },
+    {
+      "epoch": 0.26015191352614664,
+      "grad_norm": 2.7280290126800537,
+      "learning_rate": 4.210497818502509e-05,
+      "loss": 0.409,
+      "step": 3562
+    },
+    {
+      "epoch": 0.27015775635407535,
+      "grad_norm": 2.3584136962890625,
+      "learning_rate": 4.152350061055695e-05,
+      "loss": 0.3855,
+      "step": 3699
+    },
+    {
+      "epoch": 0.28016359918200406,
+      "grad_norm": 3.4275765419006348,
+      "learning_rate": 4.092569727644661e-05,
+      "loss": 0.4029,
+      "step": 3836
+    },
+    {
+      "epoch": 0.29016944200993283,
+      "grad_norm": 2.14209246635437,
+      "learning_rate": 4.031215883196239e-05,
+      "loss": 0.3836,
+      "step": 3973
+    },
+    {
+      "epoch": 0.30017528483786154,
+      "grad_norm": 2.825669288635254,
+      "learning_rate": 3.968349147317693e-05,
+      "loss": 0.3842,
+      "step": 4110
+    },
+    {
+      "epoch": 0.31018112766579026,
+      "grad_norm": 2.3074870109558105,
+      "learning_rate": 3.904031634402552e-05,
+      "loss": 0.3601,
+      "step": 4247
+    },
+    {
+      "epoch": 0.32018697049371897,
+      "grad_norm": 2.8916587829589844,
+      "learning_rate": 3.838326892259564e-05,
+      "loss": 0.38,
+      "step": 4384
+    },
+    {
+      "epoch": 0.3301928133216477,
+      "grad_norm": 1.9778506755828857,
+      "learning_rate": 3.7712998393253786e-05,
+      "loss": 0.3611,
+      "step": 4521
+    },
+    {
+      "epoch": 0.3401986561495764,
+      "grad_norm": 2.735363721847534,
+      "learning_rate": 3.703016700522999e-05,
+      "loss": 0.3653,
+      "step": 4658
+    },
+    {
+      "epoch": 0.3502044989775051,
+      "grad_norm": 3.4953627586364746,
+      "learning_rate": 3.6335449418293985e-05,
+      "loss": 0.3754,
+      "step": 4795
+    },
+    {
+      "epoch": 0.3602103418054338,
+      "grad_norm": 4.839205265045166,
+      "learning_rate": 3.562953203616925e-05,
+      "loss": 0.3468,
+      "step": 4932
+    },
+    {
+      "epoch": 0.37021618463336253,
+      "grad_norm": 2.1916751861572266,
+      "learning_rate": 3.491311232834357e-05,
+      "loss": 0.3524,
+      "step": 5069
+    },
+    {
+      "epoch": 0.38022202746129125,
+      "grad_norm": 3.1856038570404053,
+      "learning_rate": 3.418689814094646e-05,
+      "loss": 0.3501,
+      "step": 5206
+    },
+    {
+      "epoch": 0.39022787028921996,
+      "grad_norm": 1.9597059488296509,
+      "learning_rate": 3.345160699737394e-05,
+      "loss": 0.3474,
+      "step": 5343
+    },
+    {
+      "epoch": 0.4002337131171487,
+      "grad_norm": 2.523240566253662,
+      "learning_rate": 3.2707965389351925e-05,
+      "loss": 0.3355,
+      "step": 5480
+    },
+    {
+      "epoch": 0.41023955594507744,
+      "grad_norm": 16.007722854614258,
+      "learning_rate": 3.195670805913866e-05,
+      "loss": 0.3285,
+      "step": 5617
+    },
+    {
+      "epoch": 0.42024539877300615,
+      "grad_norm": 4.493948936462402,
+      "learning_rate": 3.119857727357527e-05,
+      "loss": 0.3232,
+      "step": 5754
+    },
+    {
+      "epoch": 0.43025124160093486,
+      "grad_norm": 3.0784451961517334,
+      "learning_rate": 3.0434322090701827e-05,
+      "loss": 0.3264,
+      "step": 5891
+    },
+    {
+      "epoch": 0.4402570844288636,
+      "grad_norm": 2.9652538299560547,
+      "learning_rate": 2.9664697619663472e-05,
+      "loss": 0.3147,
+      "step": 6028
+    },
+    {
+      "epoch": 0.4502629272567923,
+      "grad_norm": 2.1190903186798096,
+      "learning_rate": 2.8890464274637876e-05,
+      "loss": 0.3096,
+      "step": 6165
+    },
+    {
+      "epoch": 0.460268770084721,
+      "grad_norm": 7.0982985496521,
+      "learning_rate": 2.8112387023521115e-05,
+      "loss": 0.2968,
+      "step": 6302
+    },
+    {
+      "epoch": 0.4702746129126497,
+      "grad_norm": 1.3744592666625977,
+      "learning_rate": 2.733123463211434e-05,
+      "loss": 0.3036,
+      "step": 6439
+    },
+    {
+      "epoch": 0.4802804557405784,
+      "grad_norm": 1.526167631149292,
+      "learning_rate": 2.6547778904558018e-05,
+      "loss": 0.3069,
+      "step": 6576
+    },
+    {
+      "epoch": 0.49028629856850714,
+      "grad_norm": 1.452222466468811,
+      "learning_rate": 2.5762793920764124e-05,
+      "loss": 0.2992,
+      "step": 6713
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.3556436002254486,
+      "eval_runtime": 367.6162,
+      "eval_samples_per_second": 31.386,
+      "eval_steps_per_second": 7.848,
+      "step": 6846
+    },
+    {
+      "epoch": 0.5002921413964359,
+      "grad_norm": 2.3508574962615967,
+      "learning_rate": 2.4977055271599893e-05,
+      "loss": 0.2923,
+      "step": 6850
+    },
+    {
+      "epoch": 0.5102979842243646,
+      "grad_norm": 2.161405324935913,
+      "learning_rate": 2.4191339292578617e-05,
+      "loss": 0.2866,
+      "step": 6987
+    },
+    {
+      "epoch": 0.5203038270522933,
+      "grad_norm": 1.180467963218689,
+      "learning_rate": 2.340642229681474e-05,
+      "loss": 0.2874,
+      "step": 7124
+    },
+    {
+      "epoch": 0.530309669880222,
+      "grad_norm": 2.1960806846618652,
+      "learning_rate": 2.262307980800109e-05,
+      "loss": 0.2649,
+      "step": 7261
+    },
+    {
+      "epoch": 0.5403155127081507,
+      "grad_norm": 1.662766933441162,
+      "learning_rate": 2.1842085794166068e-05,
+      "loss": 0.268,
+      "step": 7398
+    },
+    {
+      "epoch": 0.5503213555360794,
+      "grad_norm": 1.6623494625091553,
+      "learning_rate": 2.1064211902967904e-05,
+      "loss": 0.2538,
+      "step": 7535
+    },
+    {
+      "epoch": 0.5603271983640081,
+      "grad_norm": 1.6007744073867798,
+      "learning_rate": 2.02902266992815e-05,
+      "loss": 0.2654,
+      "step": 7672
+    },
+    {
+      "epoch": 0.570333041191937,
+      "grad_norm": 2.0483551025390625,
+      "learning_rate": 1.9520894905831154e-05,
+      "loss": 0.2567,
+      "step": 7809
+    },
+    {
+      "epoch": 0.5803388840198657,
+      "grad_norm": 1.1370702981948853,
+      "learning_rate": 1.8756976647619502e-05,
+      "loss": 0.2558,
+      "step": 7946
+    },
+    {
+      "epoch": 0.5903447268477944,
+      "grad_norm": 1.3925893306732178,
+      "learning_rate": 1.7999226700899093e-05,
+      "loss": 0.239,
+      "step": 8083
+    },
+    {
+      "epoch": 0.6003505696757231,
+      "grad_norm": 1.1552609205245972,
+      "learning_rate": 1.7248393747428747e-05,
+      "loss": 0.2389,
+      "step": 8220
+    },
+    {
+      "epoch": 0.6103564125036518,
+      "grad_norm": 1.9827595949172974,
+      "learning_rate": 1.6505219634751472e-05,
+      "loss": 0.2439,
+      "step": 8357
+    },
+    {
+      "epoch": 0.6203622553315805,
+      "grad_norm": 1.7899774312973022,
+      "learning_rate": 1.5770438643224794e-05,
+      "loss": 0.2471,
+      "step": 8494
+    },
+    {
+      "epoch": 0.6303680981595092,
+      "grad_norm": 1.239159345626831,
+      "learning_rate": 1.5044776760527727e-05,
+      "loss": 0.2329,
+      "step": 8631
+    },
+    {
+      "epoch": 0.6403739409874379,
+      "grad_norm": 1.22818922996521,
+      "learning_rate": 1.4328950964361143e-05,
+      "loss": 0.2316,
+      "step": 8768
+    },
+    {
+      "epoch": 0.6503797838153667,
+      "grad_norm": 1.210986614227295,
+      "learning_rate": 1.3623668514050391e-05,
+      "loss": 0.2221,
+      "step": 8905
+    },
+    {
+      "epoch": 0.6603856266432954,
+      "grad_norm": 3.446089506149292,
+      "learning_rate": 1.2929626251749854e-05,
+      "loss": 0.2269,
+      "step": 9042
+    },
+    {
+      "epoch": 0.6703914694712241,
+      "grad_norm": 2.4413158893585205,
+      "learning_rate": 1.2247509913940128e-05,
+      "loss": 0.2209,
+      "step": 9179
+    },
+    {
+      "epoch": 0.6803973122991528,
+      "grad_norm": 1.9606636762619019,
+      "learning_rate": 1.1577993453897933e-05,
+      "loss": 0.221,
+      "step": 9316
+    },
+    {
+      "epoch": 0.6904031551270815,
+      "grad_norm": 0.8826603293418884,
+      "learning_rate": 1.0921738375808166e-05,
+      "loss": 0.2041,
+      "step": 9453
+    },
+    {
+      "epoch": 0.7004089979550102,
+      "grad_norm": 1.2856823205947876,
+      "learning_rate": 1.0279393081176122e-05,
+      "loss": 0.2022,
+      "step": 9590
+    },
+    {
+      "epoch": 0.7104148407829389,
+      "grad_norm": 0.5094468593597412,
+      "learning_rate": 9.651592228185622e-06,
+      "loss": 0.2023,
+      "step": 9727
+    },
+    {
+      "epoch": 0.7204206836108676,
+      "grad_norm": 1.4797954559326172,
+      "learning_rate": 9.038956104635871e-06,
+      "loss": 0.1961,
+      "step": 9864
+    },
+    {
+      "epoch": 0.7304265264387964,
+      "grad_norm": 1.850120186805725,
+      "learning_rate": 8.442090015076842e-06,
+      "loss": 0.2063,
+      "step": 10001
+    },
+    {
+      "epoch": 0.7404323692667251,
+      "grad_norm": 1.438025712966919,
+      "learning_rate": 7.861583682748586e-06,
+      "loss": 0.1903,
+      "step": 10138
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.254038542509079,
+      "eval_runtime": 367.4989,
+      "eval_samples_per_second": 31.396,
+      "eval_steps_per_second": 7.85,
+      "step": 10269
+    },
+    {
+      "epoch": 0.7504382120946538,
+      "grad_norm": 1.2179102897644043,
+      "learning_rate": 7.298010666915303e-06,
+      "loss": 0.1885,
+      "step": 10275
+    },
+    {
+      "epoch": 0.7604440549225825,
+      "grad_norm": 1.099284291267395,
+      "learning_rate": 6.751927796170044e-06,
+      "loss": 0.2005,
+      "step": 10412
+    },
+    {
+      "epoch": 0.7704498977505112,
+      "grad_norm": 1.2008761167526245,
+      "learning_rate": 6.2238746182698375e-06,
+      "loss": 0.1702,
+      "step": 10549
+    },
+    {
+      "epoch": 0.7804557405784399,
+      "grad_norm": 1.5368109941482544,
+      "learning_rate": 5.7143728670448095e-06,
+      "loss": 0.1947,
+      "step": 10686
+    },
+    {
+      "epoch": 0.7904615834063686,
+      "grad_norm": 1.0241951942443848,
+      "learning_rate": 5.223925946908093e-06,
+      "loss": 0.1809,
+      "step": 10823
+    },
+    {
+      "epoch": 0.8004674262342975,
+      "grad_norm": 1.369369387626648,
+      "learning_rate": 4.7530184354757675e-06,
+      "loss": 0.1889,
+      "step": 10960
+    },
+    {
+      "epoch": 0.8104732690622262,
+      "grad_norm": 0.7070077061653137,
+      "learning_rate": 4.30211560478837e-06,
+      "loss": 0.1796,
+      "step": 11097
+    },
+    {
+      "epoch": 0.8204791118901549,
+      "grad_norm": 1.7389978170394897,
+      "learning_rate": 3.871662961606784e-06,
+      "loss": 0.1843,
+      "step": 11234
+    },
+    {
+      "epoch": 0.8304849547180836,
+      "grad_norm": 0.9540761709213257,
+      "learning_rate": 3.4620858072370504e-06,
+      "loss": 0.1764,
+      "step": 11371
+    },
+    {
+      "epoch": 0.8404907975460123,
+      "grad_norm": 1.6178034543991089,
+      "learning_rate": 3.073788817318707e-06,
+      "loss": 0.1785,
+      "step": 11508
+    },
+    {
+      "epoch": 0.850496640373941,
+      "grad_norm": 1.0763949155807495,
+      "learning_rate": 2.7071556419920514e-06,
+      "loss": 0.1715,
+      "step": 11645
+    },
+    {
+      "epoch": 0.8605024832018697,
+      "grad_norm": 1.0416216850280762,
+      "learning_rate": 2.3625485268391893e-06,
+      "loss": 0.1609,
+      "step": 11782
+    },
+    {
+      "epoch": 0.8705083260297984,
+      "grad_norm": 1.1292046308517456,
+      "learning_rate": 2.040307954973572e-06,
+      "loss": 0.1739,
+      "step": 11919
+    },
+    {
+      "epoch": 0.8805141688577272,
+      "grad_norm": 1.6674988269805908,
+      "learning_rate": 1.7407523106315244e-06,
+      "loss": 0.155,
+      "step": 12056
+    },
+    {
+      "epoch": 0.8905200116856559,
+      "grad_norm": 0.8487703800201416,
+      "learning_rate": 1.4641775645981849e-06,
+      "loss": 0.1687,
+      "step": 12193
+    },
+    {
+      "epoch": 0.9005258545135846,
+      "grad_norm": 0.9765934944152832,
+      "learning_rate": 1.210856981778688e-06,
+      "loss": 0.1561,
+      "step": 12330
+    },
+    {
+      "epoch": 0.9105316973415133,
+      "grad_norm": 0.9121004343032837,
+      "learning_rate": 9.810408512034908e-07,
+      "loss": 0.1621,
+      "step": 12467
+    },
+    {
+      "epoch": 0.920537540169442,
+      "grad_norm": 1.1236246824264526,
+      "learning_rate": 7.749562387346088e-07,
+      "loss": 0.1749,
+      "step": 12604
+    },
+    {
+      "epoch": 0.9305433829973707,
+      "grad_norm": 1.0239607095718384,
+      "learning_rate": 5.928067627171158e-07,
+      "loss": 0.165,
+      "step": 12741
+    },
+    {
+      "epoch": 0.9405492258252994,
+      "grad_norm": 1.127655029296875,
+      "learning_rate": 4.347723927975417e-07,
+      "loss": 0.1662,
+      "step": 12878
+    },
+    {
+      "epoch": 0.9505550686532281,
+      "grad_norm": 0.9149182438850403,
+      "learning_rate": 3.01009272107991e-07,
+      "loss": 0.164,
+      "step": 13015
+    },
+    {
+      "epoch": 0.9605609114811569,
+      "grad_norm": 1.0919889211654663,
+      "learning_rate": 1.9164956299158322e-07,
+      "loss": 0.1723,
+      "step": 13152
+    },
+    {
+      "epoch": 0.9705667543090856,
+      "grad_norm": 2.5338237285614014,
+      "learning_rate": 1.0680131642176183e-07,
+      "loss": 0.1584,
+      "step": 13289
+    },
+    {
+      "epoch": 0.9805725971370143,
+      "grad_norm": 0.7331089377403259,
+      "learning_rate": 4.6548365244375446e-08,
+      "loss": 0.17,
+      "step": 13426
+    },
+    {
+      "epoch": 0.990578439964943,
+      "grad_norm": 1.282274603843689,
+      "learning_rate": 1.0950241348084422e-08,
+      "loss": 0.1564,
+      "step": 13563
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2237541824579239,
+      "eval_runtime": 366.8443,
+      "eval_samples_per_second": 31.452,
+      "eval_steps_per_second": 7.864,
+      "step": 13692
+    },
+    {
+      "epoch": 1.0,
+      "step": 13692,
+      "total_flos": 2.405329205216464e+19,
+      "train_loss": 0.3085681435799271,
+      "train_runtime": 41531.0913,
+      "train_samples_per_second": 2.637,
+      "train_steps_per_second": 0.33
+    }
+  ],
+  "logging_steps": 137,
+  "max_steps": 13692,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3423,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.405329205216464e+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 sha256:5f587753ccef3612b7d0f7899e81af61598b3e06ec3aaf4ff41332eed819d9e8
+size 7416