Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "collective-v0.1-chinese-roleplay-8b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "transformers_version": "4.40.2"
+}

latest

@@ -0,0 +1 @@
+global_step2500

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea3d3ba78467c1b6453df4d41c6ed3a8fa39ab99bfe699019046febbebb8326
+size 4976698592

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288cb313ea49abba6c3e5b251babc06a0e2dcd659295a181fcc47a4ec8cfc152
+size 4999802616

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b18e5c88c0c70fd346a5309372fae56e2505a7f98dc3093ab729a443e889bd
+size 4915916080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed2c759045afdd6ce9aebbf293e751dbb3e2c0b0d13af564156d9e6b9188f99
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.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.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.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.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.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.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.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.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-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.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.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.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.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.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.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.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.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.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-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.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.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"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c49abc3bdedbec1fc8e1028ef422150f19ee7470d7b542e1ad8869fc044d2af
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df12ca4106ff0831785a55b5da88f6c86f6f67bd3d09b2dced4f20b539b14f72
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fc0786faff729a3a1582f98b806b68d4f0b76aebb25cbad4431b73176b11c1
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3117e1218a2dd3f7f8c516a840af48f6b93660d852cca124269f78c21f8577c
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdaa30c82476bf6a65e4eb9ca2ae7b95f1b38f41a6f5b2f1cbdda9af86a4a7a0
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09cdde6931807139efa184e8a98108b74bb05730bc511336966b254b68dc93ee
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a2268136932c55b3857d38c7cf3fc4bd3cdad532c156b9addebc6d26374374a
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56cd9a502015b79e0ab94c92a04bd96c99aaf79ef8d64bf81d81eb702c10c2a8
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83649e8ab139de24dbe5eb9bccdeb154d16fbc40548ad16b8a8aefa2273ffb7
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set system_message = '#Role\nname: CollectiveAI 助手\n\n#Init\nYou act as CollectiveAI 助手, 你的职责是回答用户的问题' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|>\\n\\n' + system_message + '<|eot_id|>' }}{% endif %}{% set before = namespace(role='system') %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{'<|start_header_id|>user<|end_header_id|>\\n\\n' + content  + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n' }}{% elif message['role'] == 'assistant' and before.role == 'user' %}{{ content + '<|eot_id|>' }}{% elif message['role'] == 'assistant' and before.role != 'user' %}{{'<|start_header_id|>assistant<|end_header_id|>\\n\\n' + content + '<|eot_id|>' }}{% endif %}{% set before.role = message['role'] %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,1971 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7543859649122808,
+  "eval_steps": 100,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007017543859649123,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 1.3034,
+      "step": 10
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 11.65329647064209,
+      "learning_rate": 9.999987849060752e-07,
+      "loss": 1.3006,
+      "step": 20
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 8.014320373535156,
+      "learning_rate": 9.999632438442366e-07,
+      "loss": 1.233,
+      "step": 30
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "grad_norm": 7.890571594238281,
+      "learning_rate": 9.998660418225644e-07,
+      "loss": 1.1962,
+      "step": 40
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 7.12827205657959,
+      "learning_rate": 9.997081019722536e-07,
+      "loss": 1.2213,
+      "step": 50
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 7.200845718383789,
+      "learning_rate": 9.99489443484293e-07,
+      "loss": 1.1679,
+      "step": 60
+    },
+    {
+      "epoch": 0.04912280701754386,
+      "grad_norm": 7.650635242462158,
+      "learning_rate": 9.992100929274846e-07,
+      "loss": 1.1699,
+      "step": 70
+    },
+    {
+      "epoch": 0.056140350877192984,
+      "grad_norm": 7.227153778076172,
+      "learning_rate": 9.988700842452145e-07,
+      "loss": 1.1207,
+      "step": 80
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 7.5115532875061035,
+      "learning_rate": 9.984694587513297e-07,
+      "loss": 1.1387,
+      "step": 90
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 7.4819512367248535,
+      "learning_rate": 9.980082651251174e-07,
+      "loss": 1.1544,
+      "step": 100
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "eval_loss": 1.1328155994415283,
+      "eval_runtime": 27.6835,
+      "eval_samples_per_second": 173.388,
+      "eval_steps_per_second": 2.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.07719298245614035,
+      "grad_norm": 7.3147759437561035,
+      "learning_rate": 9.9748655940539e-07,
+      "loss": 1.1726,
+      "step": 110
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 7.672832489013672,
+      "learning_rate": 9.969044049836765e-07,
+      "loss": 1.115,
+      "step": 120
+    },
+    {
+      "epoch": 0.0912280701754386,
+      "grad_norm": 7.895420551300049,
+      "learning_rate": 9.962618725965194e-07,
+      "loss": 1.1274,
+      "step": 130
+    },
+    {
+      "epoch": 0.09824561403508772,
+      "grad_norm": 7.362156867980957,
+      "learning_rate": 9.955590403168798e-07,
+      "loss": 1.1401,
+      "step": 140
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 7.586355209350586,
+      "learning_rate": 9.947959935446506e-07,
+      "loss": 1.1543,
+      "step": 150
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 7.309718132019043,
+      "learning_rate": 9.939728249962806e-07,
+      "loss": 1.115,
+      "step": 160
+    },
+    {
+      "epoch": 0.11929824561403508,
+      "grad_norm": 7.269148826599121,
+      "learning_rate": 9.930896346935075e-07,
+      "loss": 1.0933,
+      "step": 170
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 7.365452766418457,
+      "learning_rate": 9.921465299512052e-07,
+      "loss": 1.0965,
+      "step": 180
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 7.434603214263916,
+      "learning_rate": 9.911436253643443e-07,
+      "loss": 1.0972,
+      "step": 190
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 7.557833194732666,
+      "learning_rate": 9.900810427940668e-07,
+      "loss": 1.1182,
+      "step": 200
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "eval_loss": 1.1001578569412231,
+      "eval_runtime": 27.6607,
+      "eval_samples_per_second": 173.531,
+      "eval_steps_per_second": 2.711,
+      "step": 200
+    },
+    {
+      "epoch": 0.14736842105263157,
+      "grad_norm": 7.197221279144287,
+      "learning_rate": 9.889589113528808e-07,
+      "loss": 1.0991,
+      "step": 210
+    },
+    {
+      "epoch": 0.1543859649122807,
+      "grad_norm": 7.870287895202637,
+      "learning_rate": 9.8777736738897e-07,
+      "loss": 1.1135,
+      "step": 220
+    },
+    {
+      "epoch": 0.16140350877192983,
+      "grad_norm": 7.257969379425049,
+      "learning_rate": 9.865365544696286e-07,
+      "loss": 1.1207,
+      "step": 230
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 7.788718223571777,
+      "learning_rate": 9.852366233638143e-07,
+      "loss": 1.1084,
+      "step": 240
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 7.723772048950195,
+      "learning_rate": 9.838777320238312e-07,
+      "loss": 1.0881,
+      "step": 250
+    },
+    {
+      "epoch": 0.1824561403508772,
+      "grad_norm": 6.814189434051514,
+      "learning_rate": 9.824600455661351e-07,
+      "loss": 1.1118,
+      "step": 260
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "grad_norm": 7.434762477874756,
+      "learning_rate": 9.809837362512718e-07,
+      "loss": 1.0948,
+      "step": 270
+    },
+    {
+      "epoch": 0.19649122807017544,
+      "grad_norm": 7.205653190612793,
+      "learning_rate": 9.794489834629454e-07,
+      "loss": 1.0837,
+      "step": 280
+    },
+    {
+      "epoch": 0.20350877192982456,
+      "grad_norm": 7.118565559387207,
+      "learning_rate": 9.77855973686222e-07,
+      "loss": 1.092,
+      "step": 290
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 7.293910503387451,
+      "learning_rate": 9.762049004848705e-07,
+      "loss": 1.1015,
+      "step": 300
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 1.0845627784729004,
+      "eval_runtime": 27.672,
+      "eval_samples_per_second": 173.461,
+      "eval_steps_per_second": 2.71,
+      "step": 300
+    },
+    {
+      "epoch": 0.21754385964912282,
+      "grad_norm": 7.512034893035889,
+      "learning_rate": 9.744959644778421e-07,
+      "loss": 1.0836,
+      "step": 310
+    },
+    {
+      "epoch": 0.22456140350877193,
+      "grad_norm": 7.277877330780029,
+      "learning_rate": 9.727293733148942e-07,
+      "loss": 1.0717,
+      "step": 320
+    },
+    {
+      "epoch": 0.23157894736842105,
+      "grad_norm": 7.781631946563721,
+      "learning_rate": 9.709053416513591e-07,
+      "loss": 1.0391,
+      "step": 330
+    },
+    {
+      "epoch": 0.23859649122807017,
+      "grad_norm": 7.217984199523926,
+      "learning_rate": 9.690240911220617e-07,
+      "loss": 1.1131,
+      "step": 340
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 7.256911277770996,
+      "learning_rate": 9.67085850314389e-07,
+      "loss": 1.0628,
+      "step": 350
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 7.053469657897949,
+      "learning_rate": 9.650908547405143e-07,
+      "loss": 1.0583,
+      "step": 360
+    },
+    {
+      "epoch": 0.2596491228070175,
+      "grad_norm": 7.0806498527526855,
+      "learning_rate": 9.630393468087817e-07,
+      "loss": 1.0714,
+      "step": 370
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 7.368037223815918,
+      "learning_rate": 9.609315757942502e-07,
+      "loss": 1.0629,
+      "step": 380
+    },
+    {
+      "epoch": 0.2736842105263158,
+      "grad_norm": 7.083371639251709,
+      "learning_rate": 9.58767797808406e-07,
+      "loss": 1.0748,
+      "step": 390
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 7.305485248565674,
+      "learning_rate": 9.565482757680414e-07,
+      "loss": 1.0736,
+      "step": 400
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "eval_loss": 1.072194218635559,
+      "eval_runtime": 27.6671,
+      "eval_samples_per_second": 173.491,
+      "eval_steps_per_second": 2.711,
+      "step": 400
+    },
+    {
+      "epoch": 0.28771929824561404,
+      "grad_norm": 7.741823196411133,
+      "learning_rate": 9.542732793633097e-07,
+      "loss": 1.0913,
+      "step": 410
+    },
+    {
+      "epoch": 0.29473684210526313,
+      "grad_norm": 6.781225204467773,
+      "learning_rate": 9.519430850249549e-07,
+      "loss": 1.0826,
+      "step": 420
+    },
+    {
+      "epoch": 0.3017543859649123,
+      "grad_norm": 6.993170738220215,
+      "learning_rate": 9.495579758907229e-07,
+      "loss": 1.0472,
+      "step": 430
+    },
+    {
+      "epoch": 0.3087719298245614,
+      "grad_norm": 6.528597831726074,
+      "learning_rate": 9.471182417709586e-07,
+      "loss": 1.0795,
+      "step": 440
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 7.972232341766357,
+      "learning_rate": 9.446241791133907e-07,
+      "loss": 1.0656,
+      "step": 450
+    },
+    {
+      "epoch": 0.32280701754385965,
+      "grad_norm": 6.81664514541626,
+      "learning_rate": 9.420760909671118e-07,
+      "loss": 1.0888,
+      "step": 460
+    },
+    {
+      "epoch": 0.3298245614035088,
+      "grad_norm": 6.822625160217285,
+      "learning_rate": 9.394742869457546e-07,
+      "loss": 1.0448,
+      "step": 470
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 7.689866065979004,
+      "learning_rate": 9.368190831898723e-07,
+      "loss": 1.0705,
+      "step": 480
+    },
+    {
+      "epoch": 0.34385964912280703,
+      "grad_norm": 6.757457256317139,
+      "learning_rate": 9.341108023285237e-07,
+      "loss": 1.0321,
+      "step": 490
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 9.012947082519531,
+      "learning_rate": 9.313497734400721e-07,
+      "loss": 1.0783,
+      "step": 500
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "eval_loss": 1.060664415359497,
+      "eval_runtime": 27.6699,
+      "eval_samples_per_second": 173.474,
+      "eval_steps_per_second": 2.711,
+      "step": 500
+    },
+    {
+      "epoch": 0.35789473684210527,
+      "grad_norm": 6.598055362701416,
+      "learning_rate": 9.28536332012199e-07,
+      "loss": 1.0526,
+      "step": 510
+    },
+    {
+      "epoch": 0.3649122807017544,
+      "grad_norm": 6.9514360427856445,
+      "learning_rate": 9.2567081990114e-07,
+      "loss": 1.055,
+      "step": 520
+    },
+    {
+      "epoch": 0.3719298245614035,
+      "grad_norm": 7.644222259521484,
+      "learning_rate": 9.227535852901462e-07,
+      "loss": 1.0546,
+      "step": 530
+    },
+    {
+      "epoch": 0.37894736842105264,
+      "grad_norm": 6.849003314971924,
+      "learning_rate": 9.197849826471773e-07,
+      "loss": 1.0819,
+      "step": 540
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 7.057733535766602,
+      "learning_rate": 9.167653726818304e-07,
+      "loss": 1.0708,
+      "step": 550
+    },
+    {
+      "epoch": 0.3929824561403509,
+      "grad_norm": 6.9738287925720215,
+      "learning_rate": 9.136951223015112e-07,
+      "loss": 1.0751,
+      "step": 560
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 7.2269511222839355,
+      "learning_rate": 9.10574604566852e-07,
+      "loss": 1.0437,
+      "step": 570
+    },
+    {
+      "epoch": 0.4070175438596491,
+      "grad_norm": 7.4513654708862305,
+      "learning_rate": 9.074041986463808e-07,
+      "loss": 1.0553,
+      "step": 580
+    },
+    {
+      "epoch": 0.41403508771929826,
+      "grad_norm": 7.455415725708008,
+      "learning_rate": 9.041842897704501e-07,
+      "loss": 1.0671,
+      "step": 590
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 7.012011528015137,
+      "learning_rate": 9.009152691844284e-07,
+      "loss": 1.0663,
+      "step": 600
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": 1.051626205444336,
+      "eval_runtime": 27.657,
+      "eval_samples_per_second": 173.555,
+      "eval_steps_per_second": 2.712,
+      "step": 600
+    },
+    {
+      "epoch": 0.4280701754385965,
+      "grad_norm": 6.606391429901123,
+      "learning_rate": 8.975975341011595e-07,
+      "loss": 1.0385,
+      "step": 610
+    },
+    {
+      "epoch": 0.43508771929824563,
+      "grad_norm": 7.090952396392822,
+      "learning_rate": 8.942314876526991e-07,
+      "loss": 1.0438,
+      "step": 620
+    },
+    {
+      "epoch": 0.4421052631578947,
+      "grad_norm": 7.45530891418457,
+      "learning_rate": 8.908175388413303e-07,
+      "loss": 1.0519,
+      "step": 630
+    },
+    {
+      "epoch": 0.44912280701754387,
+      "grad_norm": 7.6413960456848145,
+      "learning_rate": 8.873561024898667e-07,
+      "loss": 1.0705,
+      "step": 640
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 7.025049209594727,
+      "learning_rate": 8.838475991912481e-07,
+      "loss": 1.0548,
+      "step": 650
+    },
+    {
+      "epoch": 0.4631578947368421,
+      "grad_norm": 7.06046724319458,
+      "learning_rate": 8.802924552574345e-07,
+      "loss": 1.0465,
+      "step": 660
+    },
+    {
+      "epoch": 0.47017543859649125,
+      "grad_norm": 7.351295471191406,
+      "learning_rate": 8.766911026676063e-07,
+      "loss": 1.0575,
+      "step": 670
+    },
+    {
+      "epoch": 0.47719298245614034,
+      "grad_norm": 7.417140960693359,
+      "learning_rate": 8.730439790156751e-07,
+      "loss": 1.0686,
+      "step": 680
+    },
+    {
+      "epoch": 0.4842105263157895,
+      "grad_norm": 7.903563499450684,
+      "learning_rate": 8.693515274571121e-07,
+      "loss": 1.0776,
+      "step": 690
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 8.01221752166748,
+      "learning_rate": 8.656141966551018e-07,
+      "loss": 1.0621,
+      "step": 700
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "eval_loss": 1.043724775314331,
+      "eval_runtime": 27.6712,
+      "eval_samples_per_second": 173.466,
+      "eval_steps_per_second": 2.71,
+      "step": 700
+    },
+    {
+      "epoch": 0.4982456140350877,
+      "grad_norm": 7.052249431610107,
+      "learning_rate": 8.618324407260249e-07,
+      "loss": 1.0738,
+      "step": 710
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 7.37591028213501,
+      "learning_rate": 8.5800671918428e-07,
+      "loss": 1.0607,
+      "step": 720
+    },
+    {
+      "epoch": 0.512280701754386,
+      "grad_norm": 7.373082160949707,
+      "learning_rate": 8.541374968864485e-07,
+      "loss": 1.0602,
+      "step": 730
+    },
+    {
+      "epoch": 0.519298245614035,
+      "grad_norm": 7.446669101715088,
+      "learning_rate": 8.502252439748112e-07,
+      "loss": 1.0462,
+      "step": 740
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 6.634714603424072,
+      "learning_rate": 8.462704358202216e-07,
+      "loss": 1.0308,
+      "step": 750
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 6.623584270477295,
+      "learning_rate": 8.422735529643443e-07,
+      "loss": 1.0462,
+      "step": 760
+    },
+    {
+      "epoch": 0.5403508771929825,
+      "grad_norm": 7.110071659088135,
+      "learning_rate": 8.382350810612663e-07,
+      "loss": 1.0739,
+      "step": 770
+    },
+    {
+      "epoch": 0.5473684210526316,
+      "grad_norm": 7.406259536743164,
+      "learning_rate": 8.341555108184849e-07,
+      "loss": 1.069,
+      "step": 780
+    },
+    {
+      "epoch": 0.5543859649122806,
+      "grad_norm": 7.356163024902344,
+      "learning_rate": 8.300353379372833e-07,
+      "loss": 1.0542,
+      "step": 790
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 7.522149562835693,
+      "learning_rate": 8.258750630524983e-07,
+      "loss": 1.0482,
+      "step": 800
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "eval_loss": 1.0357595682144165,
+      "eval_runtime": 27.6785,
+      "eval_samples_per_second": 173.42,
+      "eval_steps_per_second": 2.71,
+      "step": 800
+    },
+    {
+      "epoch": 0.5684210526315789,
+      "grad_norm": 6.716446399688721,
+      "learning_rate": 8.216751916716899e-07,
+      "loss": 1.0459,
+      "step": 810
+    },
+    {
+      "epoch": 0.5754385964912281,
+      "grad_norm": 7.719761371612549,
+      "learning_rate": 8.174362341137176e-07,
+      "loss": 1.0271,
+      "step": 820
+    },
+    {
+      "epoch": 0.5824561403508772,
+      "grad_norm": 7.073091983795166,
+      "learning_rate": 8.13158705446732e-07,
+      "loss": 1.0483,
+      "step": 830
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 6.979051113128662,
+      "learning_rate": 8.088431254255898e-07,
+      "loss": 1.0293,
+      "step": 840
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 7.095376014709473,
+      "learning_rate": 8.044900184287006e-07,
+      "loss": 1.0387,
+      "step": 850
+    },
+    {
+      "epoch": 0.6035087719298246,
+      "grad_norm": 7.155153274536133,
+      "learning_rate": 8.000999133943092e-07,
+      "loss": 1.0448,
+      "step": 860
+    },
+    {
+      "epoch": 0.6105263157894737,
+      "grad_norm": 7.818843841552734,
+      "learning_rate": 7.956733437562258e-07,
+      "loss": 1.047,
+      "step": 870
+    },
+    {
+      "epoch": 0.6175438596491228,
+      "grad_norm": 7.174437046051025,
+      "learning_rate": 7.912108473790091e-07,
+      "loss": 1.0293,
+      "step": 880
+    },
+    {
+      "epoch": 0.624561403508772,
+      "grad_norm": 7.124237060546875,
+      "learning_rate": 7.867129664926123e-07,
+      "loss": 1.0535,
+      "step": 890
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 7.362142562866211,
+      "learning_rate": 7.821802476264965e-07,
+      "loss": 1.0662,
+      "step": 900
+    },
+    {
+      "epoch": 0.631578947368421,
+      "eval_loss": 1.0292896032333374,
+      "eval_runtime": 27.6513,
+      "eval_samples_per_second": 173.59,
+      "eval_steps_per_second": 2.712,
+      "step": 900
+    },
+    {
+      "epoch": 0.6385964912280702,
+      "grad_norm": 6.185942649841309,
+      "learning_rate": 7.776132415432232e-07,
+      "loss": 1.0311,
+      "step": 910
+    },
+    {
+      "epoch": 0.6456140350877193,
+      "grad_norm": 7.229496955871582,
+      "learning_rate": 7.73012503171533e-07,
+      "loss": 1.0478,
+      "step": 920
+    },
+    {
+      "epoch": 0.6526315789473685,
+      "grad_norm": 6.964082717895508,
+      "learning_rate": 7.683785915389162e-07,
+      "loss": 1.0355,
+      "step": 930
+    },
+    {
+      "epoch": 0.6596491228070176,
+      "grad_norm": 7.6486077308654785,
+      "learning_rate": 7.637120697036865e-07,
+      "loss": 1.0078,
+      "step": 940
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 7.581448554992676,
+      "learning_rate": 7.590135046865651e-07,
+      "loss": 1.0352,
+      "step": 950
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 6.977712154388428,
+      "learning_rate": 7.542834674017831e-07,
+      "loss": 1.0352,
+      "step": 960
+    },
+    {
+      "epoch": 0.6807017543859649,
+      "grad_norm": 7.210628986358643,
+      "learning_rate": 7.495225325877103e-07,
+      "loss": 1.0351,
+      "step": 970
+    },
+    {
+      "epoch": 0.6877192982456141,
+      "grad_norm": 6.860006809234619,
+      "learning_rate": 7.447312787370202e-07,
+      "loss": 1.0244,
+      "step": 980
+    },
+    {
+      "epoch": 0.6947368421052632,
+      "grad_norm": 7.080367088317871,
+      "learning_rate": 7.399102880263983e-07,
+      "loss": 1.0451,
+      "step": 990
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 7.036980152130127,
+      "learning_rate": 7.350601462458024e-07,
+      "loss": 1.0727,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "eval_loss": 1.022666096687317,
+      "eval_runtime": 27.6533,
+      "eval_samples_per_second": 173.578,
+      "eval_steps_per_second": 2.712,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7087719298245614,
+      "grad_norm": 6.67840576171875,
+      "learning_rate": 7.301814427272848e-07,
+      "loss": 1.0636,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7157894736842105,
+      "grad_norm": 7.1095452308654785,
+      "learning_rate": 7.252747702733839e-07,
+      "loss": 1.0088,
+      "step": 1020
+    },
+    {
+      "epoch": 0.7228070175438597,
+      "grad_norm": 7.100186347961426,
+      "learning_rate": 7.203407250850928e-07,
+      "loss": 1.0245,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7298245614035088,
+      "grad_norm": 6.765640735626221,
+      "learning_rate": 7.158771761692464e-07,
+      "loss": 1.0095,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 6.90313720703125,
+      "learning_rate": 7.108927771727661e-07,
+      "loss": 1.0188,
+      "step": 1050
+    },
+    {
+      "epoch": 0.743859649122807,
+      "grad_norm": 6.8065948486328125,
+      "learning_rate": 7.058827529721525e-07,
+      "loss": 1.0339,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7508771929824561,
+      "grad_norm": 6.624533653259277,
+      "learning_rate": 7.008477123264847e-07,
+      "loss": 1.0346,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 7.218606472015381,
+      "learning_rate": 6.957882670345458e-07,
+      "loss": 1.0379,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7649122807017544,
+      "grad_norm": 7.127339839935303,
+      "learning_rate": 6.90705031860483e-07,
+      "loss": 1.0205,
+      "step": 1090
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 6.587140083312988,
+      "learning_rate": 6.855986244591103e-07,
+      "loss": 1.0263,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "eval_loss": 1.0174767971038818,
+      "eval_runtime": 27.6964,
+      "eval_samples_per_second": 173.308,
+      "eval_steps_per_second": 2.708,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7789473684210526,
+      "grad_norm": 6.751448631286621,
+      "learning_rate": 6.804696653008574e-07,
+      "loss": 0.981,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7859649122807018,
+      "grad_norm": 7.036713600158691,
+      "learning_rate": 6.753187775963772e-07,
+      "loss": 1.0488,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7929824561403509,
+      "grad_norm": 6.959472179412842,
+      "learning_rate": 6.701465872208216e-07,
+      "loss": 1.0202,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 7.4908599853515625,
+      "learning_rate": 6.649537226377914e-07,
+      "loss": 1.0356,
+      "step": 1140
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 8.565585136413574,
+      "learning_rate": 6.597408148229741e-07,
+      "loss": 1.0125,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8140350877192982,
+      "grad_norm": 7.0569167137146,
+      "learning_rate": 6.545084971874736e-07,
+      "loss": 1.0654,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8210526315789474,
+      "grad_norm": 6.795130252838135,
+      "learning_rate": 6.492574055008473e-07,
+      "loss": 1.046,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8280701754385965,
+      "grad_norm": 7.272831916809082,
+      "learning_rate": 6.439881778138531e-07,
+      "loss": 1.0238,
+      "step": 1180
+    },
+    {
+      "epoch": 0.8350877192982457,
+      "grad_norm": 6.588538646697998,
+      "learning_rate": 6.387014543809223e-07,
+      "loss": 1.0155,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 6.798887252807617,
+      "learning_rate": 6.333978775823631e-07,
+      "loss": 1.0187,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 1.0141297578811646,
+      "eval_runtime": 27.6602,
+      "eval_samples_per_second": 173.534,
+      "eval_steps_per_second": 2.711,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8491228070175438,
+      "grad_norm": 6.572112083435059,
+      "learning_rate": 6.280780918463057e-07,
+      "loss": 1.0355,
+      "step": 1210
+    },
+    {
+      "epoch": 0.856140350877193,
+      "grad_norm": 7.28840970993042,
+      "learning_rate": 6.227427435703995e-07,
+      "loss": 1.0424,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8631578947368421,
+      "grad_norm": 8.068036079406738,
+      "learning_rate": 6.173924810432704e-07,
+      "loss": 1.0321,
+      "step": 1230
+    },
+    {
+      "epoch": 0.8701754385964913,
+      "grad_norm": 6.726752281188965,
+      "learning_rate": 6.12027954365748e-07,
+      "loss": 1.0431,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 6.742453098297119,
+      "learning_rate": 6.066498153718734e-07,
+      "loss": 1.0178,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8842105263157894,
+      "grad_norm": 6.598849296569824,
+      "learning_rate": 6.01258717549696e-07,
+      "loss": 1.0141,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8912280701754386,
+      "grad_norm": 6.771568775177002,
+      "learning_rate": 5.958553159618692e-07,
+      "loss": 0.9957,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8982456140350877,
+      "grad_norm": 7.0470380783081055,
+      "learning_rate": 5.90440267166055e-07,
+      "loss": 1.0387,
+      "step": 1280
+    },
+    {
+      "epoch": 0.9052631578947369,
+      "grad_norm": 7.024428367614746,
+      "learning_rate": 5.850142291351465e-07,
+      "loss": 1.026,
+      "step": 1290
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 7.074985027313232,
+      "learning_rate": 5.795778611773197e-07,
+      "loss": 1.0121,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "eval_loss": 1.0093048810958862,
+      "eval_runtime": 27.6576,
+      "eval_samples_per_second": 173.551,
+      "eval_steps_per_second": 2.712,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9192982456140351,
+      "grad_norm": 7.012327194213867,
+      "learning_rate": 5.741318238559209e-07,
+      "loss": 1.0331,
+      "step": 1310
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 6.710480690002441,
+      "learning_rate": 5.686767789092041e-07,
+      "loss": 1.012,
+      "step": 1320
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 6.7387919425964355,
+      "learning_rate": 5.632133891699231e-07,
+      "loss": 0.9881,
+      "step": 1330
+    },
+    {
+      "epoch": 0.9403508771929825,
+      "grad_norm": 6.965381145477295,
+      "learning_rate": 5.577423184847931e-07,
+      "loss": 1.0209,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 7.125399589538574,
+      "learning_rate": 5.522642316338268e-07,
+      "loss": 1.0109,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9543859649122807,
+      "grad_norm": 7.273198127746582,
+      "learning_rate": 5.467797942495589e-07,
+      "loss": 1.0108,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9614035087719298,
+      "grad_norm": 6.802534580230713,
+      "learning_rate": 5.412896727361662e-07,
+      "loss": 1.025,
+      "step": 1370
+    },
+    {
+      "epoch": 0.968421052631579,
+      "grad_norm": 7.282257080078125,
+      "learning_rate": 5.357945341884935e-07,
+      "loss": 1.0353,
+      "step": 1380
+    },
+    {
+      "epoch": 0.9754385964912281,
+      "grad_norm": 6.752053260803223,
+      "learning_rate": 5.302950463109969e-07,
+      "loss": 1.0118,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 6.847274303436279,
+      "learning_rate": 5.247918773366111e-07,
+      "loss": 1.0092,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "eval_loss": 1.003943681716919,
+      "eval_runtime": 27.6644,
+      "eval_samples_per_second": 173.508,
+      "eval_steps_per_second": 2.711,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9894736842105263,
+      "grad_norm": 7.226211071014404,
+      "learning_rate": 5.192856959455552e-07,
+      "loss": 1.0278,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9964912280701754,
+      "grad_norm": 6.635247230529785,
+      "learning_rate": 5.137771711840811e-07,
+      "loss": 1.0163,
+      "step": 1420
+    },
+    {
+      "epoch": 1.0035087719298246,
+      "grad_norm": 6.2100605964660645,
+      "learning_rate": 5.082669723831793e-07,
+      "loss": 0.928,
+      "step": 1430
+    },
+    {
+      "epoch": 1.0105263157894737,
+      "grad_norm": 6.735259532928467,
+      "learning_rate": 5.027557690772503e-07,
+      "loss": 0.8903,
+      "step": 1440
+    },
+    {
+      "epoch": 1.0175438596491229,
+      "grad_norm": 7.061236381530762,
+      "learning_rate": 4.972442309227498e-07,
+      "loss": 0.8721,
+      "step": 1450
+    },
+    {
+      "epoch": 1.024561403508772,
+      "grad_norm": 6.729221820831299,
+      "learning_rate": 4.917330276168208e-07,
+      "loss": 0.8759,
+      "step": 1460
+    },
+    {
+      "epoch": 1.0315789473684212,
+      "grad_norm": 6.925577640533447,
+      "learning_rate": 4.86222828815919e-07,
+      "loss": 0.866,
+      "step": 1470
+    },
+    {
+      "epoch": 1.03859649122807,
+      "grad_norm": 6.847450256347656,
+      "learning_rate": 4.807143040544446e-07,
+      "loss": 0.8851,
+      "step": 1480
+    },
+    {
+      "epoch": 1.0456140350877192,
+      "grad_norm": 7.24519157409668,
+      "learning_rate": 4.752081226633888e-07,
+      "loss": 0.8922,
+      "step": 1490
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 6.8135085105896,
+      "learning_rate": 4.697049536890033e-07,
+      "loss": 0.8917,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "eval_loss": 1.0086382627487183,
+      "eval_runtime": 27.6965,
+      "eval_samples_per_second": 173.307,
+      "eval_steps_per_second": 2.708,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0596491228070175,
+      "grad_norm": 6.774071216583252,
+      "learning_rate": 4.6475522990138276e-07,
+      "loss": 0.8773,
+      "step": 1510
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 6.860315799713135,
+      "learning_rate": 4.592596263646712e-07,
+      "loss": 0.9042,
+      "step": 1520
+    },
+    {
+      "epoch": 1.0736842105263158,
+      "grad_norm": 7.362914085388184,
+      "learning_rate": 4.5376897311788825e-07,
+      "loss": 0.8973,
+      "step": 1530
+    },
+    {
+      "epoch": 1.080701754385965,
+      "grad_norm": 6.993128776550293,
+      "learning_rate": 4.48283937320489e-07,
+      "loss": 0.8533,
+      "step": 1540
+    },
+    {
+      "epoch": 1.087719298245614,
+      "grad_norm": 7.575523853302002,
+      "learning_rate": 4.4280518544936224e-07,
+      "loss": 0.8896,
+      "step": 1550
+    },
+    {
+      "epoch": 1.0947368421052632,
+      "grad_norm": 7.457510948181152,
+      "learning_rate": 4.3733338321784777e-07,
+      "loss": 0.873,
+      "step": 1560
+    },
+    {
+      "epoch": 1.1017543859649124,
+      "grad_norm": 6.553786754608154,
+      "learning_rate": 4.3186919549484777e-07,
+      "loss": 0.8735,
+      "step": 1570
+    },
+    {
+      "epoch": 1.1087719298245613,
+      "grad_norm": 7.161813259124756,
+      "learning_rate": 4.264132862240387e-07,
+      "loss": 0.8708,
+      "step": 1580
+    },
+    {
+      "epoch": 1.1157894736842104,
+      "grad_norm": 7.342090129852295,
+      "learning_rate": 4.2096631834319687e-07,
+      "loss": 0.8627,
+      "step": 1590
+    },
+    {
+      "epoch": 1.1228070175438596,
+      "grad_norm": 7.708263874053955,
+      "learning_rate": 4.155289537036466e-07,
+      "loss": 0.8916,
+      "step": 1600
+    },
+    {
+      "epoch": 1.1228070175438596,
+      "eval_loss": 1.0080682039260864,
+      "eval_runtime": 27.6601,
+      "eval_samples_per_second": 173.535,
+      "eval_steps_per_second": 2.711,
+      "step": 1600
+    },
+    {
+      "epoch": 1.1298245614035087,
+      "grad_norm": 6.637975215911865,
+      "learning_rate": 4.101018529898398e-07,
+      "loss": 0.8598,
+      "step": 1610
+    },
+    {
+      "epoch": 1.1368421052631579,
+      "grad_norm": 7.271252155303955,
+      "learning_rate": 4.046856756390766e-07,
+      "loss": 0.8632,
+      "step": 1620
+    },
+    {
+      "epoch": 1.143859649122807,
+      "grad_norm": 6.89381742477417,
+      "learning_rate": 3.99281079761379e-07,
+      "loss": 0.8877,
+      "step": 1630
+    },
+    {
+      "epoch": 1.1508771929824562,
+      "grad_norm": 7.032026290893555,
+      "learning_rate": 3.938887220595252e-07,
+      "loss": 0.879,
+      "step": 1640
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 7.385174751281738,
+      "learning_rate": 3.885092577492542e-07,
+      "loss": 0.8893,
+      "step": 1650
+    },
+    {
+      "epoch": 1.1649122807017545,
+      "grad_norm": 7.389017105102539,
+      "learning_rate": 3.8314334047965207e-07,
+      "loss": 0.8727,
+      "step": 1660
+    },
+    {
+      "epoch": 1.1719298245614036,
+      "grad_norm": 6.653899192810059,
+      "learning_rate": 3.7779162225372846e-07,
+      "loss": 0.8941,
+      "step": 1670
+    },
+    {
+      "epoch": 1.1789473684210527,
+      "grad_norm": 7.119126319885254,
+      "learning_rate": 3.724547533491924e-07,
+      "loss": 0.8676,
+      "step": 1680
+    },
+    {
+      "epoch": 1.1859649122807017,
+      "grad_norm": 7.610691070556641,
+      "learning_rate": 3.671333822394386e-07,
+      "loss": 0.864,
+      "step": 1690
+    },
+    {
+      "epoch": 1.1929824561403508,
+      "grad_norm": 6.851118564605713,
+      "learning_rate": 3.6182815551475223e-07,
+      "loss": 0.885,
+      "step": 1700
+    },
+    {
+      "epoch": 1.1929824561403508,
+      "eval_loss": 1.0073468685150146,
+      "eval_runtime": 27.66,
+      "eval_samples_per_second": 173.536,
+      "eval_steps_per_second": 2.712,
+      "step": 1700
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 7.08779764175415,
+      "learning_rate": 3.565397178037429e-07,
+      "loss": 0.875,
+      "step": 1710
+    },
+    {
+      "epoch": 1.207017543859649,
+      "grad_norm": 6.938493728637695,
+      "learning_rate": 3.5126871169501815e-07,
+      "loss": 0.8823,
+      "step": 1720
+    },
+    {
+      "epoch": 1.2140350877192982,
+      "grad_norm": 7.4112114906311035,
+      "learning_rate": 3.4601577765910175e-07,
+      "loss": 0.8428,
+      "step": 1730
+    },
+    {
+      "epoch": 1.2210526315789474,
+      "grad_norm": 7.859072208404541,
+      "learning_rate": 3.407815539706124e-07,
+      "loss": 0.8659,
+      "step": 1740
+    },
+    {
+      "epoch": 1.2280701754385965,
+      "grad_norm": 6.562801837921143,
+      "learning_rate": 3.3556667663070835e-07,
+      "loss": 0.8654,
+      "step": 1750
+    },
+    {
+      "epoch": 1.2350877192982457,
+      "grad_norm": 7.658775806427002,
+      "learning_rate": 3.303717792898073e-07,
+      "loss": 0.8652,
+      "step": 1760
+    },
+    {
+      "epoch": 1.2421052631578948,
+      "grad_norm": 7.275959491729736,
+      "learning_rate": 3.2519749317059327e-07,
+      "loss": 0.8957,
+      "step": 1770
+    },
+    {
+      "epoch": 1.2491228070175437,
+      "grad_norm": 7.704782485961914,
+      "learning_rate": 3.200444469913172e-07,
+      "loss": 0.8737,
+      "step": 1780
+    },
+    {
+      "epoch": 1.256140350877193,
+      "grad_norm": 7.395431995391846,
+      "learning_rate": 3.1491326688940344e-07,
+      "loss": 0.8542,
+      "step": 1790
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 6.88340425491333,
+      "learning_rate": 3.0980457634536774e-07,
+      "loss": 0.8843,
+      "step": 1800
+    },
+    {
+      "epoch": 1.263157894736842,
+      "eval_loss": 1.0033657550811768,
+      "eval_runtime": 27.6659,
+      "eval_samples_per_second": 173.499,
+      "eval_steps_per_second": 2.711,
+      "step": 1800
+    },
+    {
+      "epoch": 1.2701754385964912,
+      "grad_norm": 6.7408766746521,
+      "learning_rate": 3.0471899610706036e-07,
+      "loss": 0.8331,
+      "step": 1810
+    },
+    {
+      "epoch": 1.2771929824561403,
+      "grad_norm": 7.153403282165527,
+      "learning_rate": 2.996571441142397e-07,
+      "loss": 0.8465,
+      "step": 1820
+    },
+    {
+      "epoch": 1.2842105263157895,
+      "grad_norm": 7.26017427444458,
+      "learning_rate": 2.9461963542348733e-07,
+      "loss": 0.8785,
+      "step": 1830
+    },
+    {
+      "epoch": 1.2912280701754386,
+      "grad_norm": 7.271636486053467,
+      "learning_rate": 2.896070821334736e-07,
+      "loss": 0.8831,
+      "step": 1840
+    },
+    {
+      "epoch": 1.2982456140350878,
+      "grad_norm": 6.8561201095581055,
+      "learning_rate": 2.846200933105829e-07,
+      "loss": 0.8578,
+      "step": 1850
+    },
+    {
+      "epoch": 1.305263157894737,
+      "grad_norm": 7.387796878814697,
+      "learning_rate": 2.7965927491490704e-07,
+      "loss": 0.8439,
+      "step": 1860
+    },
+    {
+      "epoch": 1.312280701754386,
+      "grad_norm": 7.401048183441162,
+      "learning_rate": 2.747252297266162e-07,
+      "loss": 0.8944,
+      "step": 1870
+    },
+    {
+      "epoch": 1.3192982456140352,
+      "grad_norm": 7.2983527183532715,
+      "learning_rate": 2.698185572727151e-07,
+      "loss": 0.8689,
+      "step": 1880
+    },
+    {
+      "epoch": 1.3263157894736843,
+      "grad_norm": 7.557769775390625,
+      "learning_rate": 2.6493985375419775e-07,
+      "loss": 0.885,
+      "step": 1890
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 6.881629943847656,
+      "learning_rate": 2.6008971197360175e-07,
+      "loss": 0.8644,
+      "step": 1900
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "eval_loss": 1.0021144151687622,
+      "eval_runtime": 27.6613,
+      "eval_samples_per_second": 173.527,
+      "eval_steps_per_second": 2.711,
+      "step": 1900
+    },
+    {
+      "epoch": 1.3403508771929824,
+      "grad_norm": 7.333024978637695,
+      "learning_rate": 2.5526872126297986e-07,
+      "loss": 0.8912,
+      "step": 1910
+    },
+    {
+      "epoch": 1.3473684210526315,
+      "grad_norm": 7.045767784118652,
+      "learning_rate": 2.5047746741228977e-07,
+      "loss": 0.8747,
+      "step": 1920
+    },
+    {
+      "epoch": 1.3543859649122807,
+      "grad_norm": 7.227980613708496,
+      "learning_rate": 2.457165325982169e-07,
+      "loss": 0.8647,
+      "step": 1930
+    },
+    {
+      "epoch": 1.3614035087719298,
+      "grad_norm": 7.303330898284912,
+      "learning_rate": 2.4098649531343494e-07,
+      "loss": 0.8657,
+      "step": 1940
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 7.276090621948242,
+      "learning_rate": 2.362879302963135e-07,
+      "loss": 0.8845,
+      "step": 1950
+    },
+    {
+      "epoch": 1.3754385964912281,
+      "grad_norm": 7.321451663970947,
+      "learning_rate": 2.3162140846108363e-07,
+      "loss": 0.8487,
+      "step": 1960
+    },
+    {
+      "epoch": 1.3824561403508773,
+      "grad_norm": 7.5262980461120605,
+      "learning_rate": 2.2698749682846685e-07,
+      "loss": 0.8762,
+      "step": 1970
+    },
+    {
+      "epoch": 1.3894736842105262,
+      "grad_norm": 7.401157855987549,
+      "learning_rate": 2.223867584567766e-07,
+      "loss": 0.8748,
+      "step": 1980
+    },
+    {
+      "epoch": 1.3964912280701753,
+      "grad_norm": 7.1058149337768555,
+      "learning_rate": 2.1781975237350365e-07,
+      "loss": 0.8641,
+      "step": 1990
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 7.203502178192139,
+      "learning_rate": 2.1328703350738765e-07,
+      "loss": 0.8661,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "eval_loss": 1.000258445739746,
+      "eval_runtime": 27.6622,
+      "eval_samples_per_second": 173.522,
+      "eval_steps_per_second": 2.711,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4105263157894736,
+      "grad_norm": 7.68574857711792,
+      "learning_rate": 2.0878915262099096e-07,
+      "loss": 0.8964,
+      "step": 2010
+    },
+    {
+      "epoch": 1.4175438596491228,
+      "grad_norm": 7.339992523193359,
+      "learning_rate": 2.0432665624377433e-07,
+      "loss": 0.8779,
+      "step": 2020
+    },
+    {
+      "epoch": 1.424561403508772,
+      "grad_norm": 7.711989879608154,
+      "learning_rate": 1.999000866056908e-07,
+      "loss": 0.8958,
+      "step": 2030
+    },
+    {
+      "epoch": 1.431578947368421,
+      "grad_norm": 6.8218488693237305,
+      "learning_rate": 1.9550998157129944e-07,
+      "loss": 0.8848,
+      "step": 2040
+    },
+    {
+      "epoch": 1.4385964912280702,
+      "grad_norm": 7.602545261383057,
+      "learning_rate": 1.9115687457441022e-07,
+      "loss": 0.8668,
+      "step": 2050
+    },
+    {
+      "epoch": 1.4456140350877194,
+      "grad_norm": 7.199863433837891,
+      "learning_rate": 1.8684129455326808e-07,
+      "loss": 0.8705,
+      "step": 2060
+    },
+    {
+      "epoch": 1.4526315789473685,
+      "grad_norm": 7.163413047790527,
+      "learning_rate": 1.8256376588628235e-07,
+      "loss": 0.8641,
+      "step": 2070
+    },
+    {
+      "epoch": 1.4596491228070176,
+      "grad_norm": 7.178804397583008,
+      "learning_rate": 1.7832480832830986e-07,
+      "loss": 0.8526,
+      "step": 2080
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 7.084789752960205,
+      "learning_rate": 1.7412493694750173e-07,
+      "loss": 0.8834,
+      "step": 2090
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 7.647516250610352,
+      "learning_rate": 1.6996466206271675e-07,
+      "loss": 0.8712,
+      "step": 2100
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "eval_loss": 1.0002570152282715,
+      "eval_runtime": 27.6725,
+      "eval_samples_per_second": 173.457,
+      "eval_steps_per_second": 2.71,
+      "step": 2100
+    },
+    {
+      "epoch": 1.4807017543859649,
+      "grad_norm": 7.682786464691162,
+      "learning_rate": 1.6584448918151518e-07,
+      "loss": 0.8648,
+      "step": 2110
+    },
+    {
+      "epoch": 1.487719298245614,
+      "grad_norm": 6.9408650398254395,
+      "learning_rate": 1.6176491893873367e-07,
+      "loss": 0.8775,
+      "step": 2120
+    },
+    {
+      "epoch": 1.4947368421052631,
+      "grad_norm": 7.477031230926514,
+      "learning_rate": 1.5772644703565564e-07,
+      "loss": 0.8648,
+      "step": 2130
+    },
+    {
+      "epoch": 1.5017543859649123,
+      "grad_norm": 7.054373741149902,
+      "learning_rate": 1.537295641797785e-07,
+      "loss": 0.8608,
+      "step": 2140
+    },
+    {
+      "epoch": 1.5087719298245614,
+      "grad_norm": 6.98421049118042,
+      "learning_rate": 1.4977475602518874e-07,
+      "loss": 0.8653,
+      "step": 2150
+    },
+    {
+      "epoch": 1.5157894736842106,
+      "grad_norm": 7.556164264678955,
+      "learning_rate": 1.4586250311355132e-07,
+      "loss": 0.8691,
+      "step": 2160
+    },
+    {
+      "epoch": 1.5228070175438595,
+      "grad_norm": 7.721457004547119,
+      "learning_rate": 1.4199328081572e-07,
+      "loss": 0.8853,
+      "step": 2170
+    },
+    {
+      "epoch": 1.5298245614035086,
+      "grad_norm": 7.5607428550720215,
+      "learning_rate": 1.38167559273975e-07,
+      "loss": 0.8647,
+      "step": 2180
+    },
+    {
+      "epoch": 1.5368421052631578,
+      "grad_norm": 7.398414134979248,
+      "learning_rate": 1.3438580334489818e-07,
+      "loss": 0.8524,
+      "step": 2190
+    },
+    {
+      "epoch": 1.543859649122807,
+      "grad_norm": 7.229887008666992,
+      "learning_rate": 1.3064847254288796e-07,
+      "loss": 0.8638,
+      "step": 2200
+    },
+    {
+      "epoch": 1.543859649122807,
+      "eval_loss": 0.9979353547096252,
+      "eval_runtime": 27.6809,
+      "eval_samples_per_second": 173.405,
+      "eval_steps_per_second": 2.709,
+      "step": 2200
+    },
+    {
+      "epoch": 1.550877192982456,
+      "grad_norm": 7.479950428009033,
+      "learning_rate": 1.26956020984325e-07,
+      "loss": 0.8672,
+      "step": 2210
+    },
+    {
+      "epoch": 1.5578947368421052,
+      "grad_norm": 7.526796340942383,
+      "learning_rate": 1.2330889733239368e-07,
+      "loss": 0.8882,
+      "step": 2220
+    },
+    {
+      "epoch": 1.5649122807017544,
+      "grad_norm": 7.098681926727295,
+      "learning_rate": 1.197075447425656e-07,
+      "loss": 0.8564,
+      "step": 2230
+    },
+    {
+      "epoch": 1.5719298245614035,
+      "grad_norm": 7.627535343170166,
+      "learning_rate": 1.16152400808752e-07,
+      "loss": 0.8778,
+      "step": 2240
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 7.635378360748291,
+      "learning_rate": 1.1264389751013325e-07,
+      "loss": 0.8615,
+      "step": 2250
+    },
+    {
+      "epoch": 1.5859649122807018,
+      "grad_norm": 7.256911754608154,
+      "learning_rate": 1.0918246115866964e-07,
+      "loss": 0.8828,
+      "step": 2260
+    },
+    {
+      "epoch": 1.592982456140351,
+      "grad_norm": 7.054688453674316,
+      "learning_rate": 1.0576851234730094e-07,
+      "loss": 0.8602,
+      "step": 2270
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 7.2597479820251465,
+      "learning_rate": 1.0240246589884045e-07,
+      "loss": 0.8588,
+      "step": 2280
+    },
+    {
+      "epoch": 1.6070175438596492,
+      "grad_norm": 7.462535381317139,
+      "learning_rate": 9.90847308155715e-08,
+      "loss": 0.8623,
+      "step": 2290
+    },
+    {
+      "epoch": 1.6140350877192984,
+      "grad_norm": 7.354959487915039,
+      "learning_rate": 9.581571022954987e-08,
+      "loss": 0.8632,
+      "step": 2300
+    },
+    {
+      "epoch": 1.6140350877192984,
+      "eval_loss": 0.9973437786102295,
+      "eval_runtime": 27.6881,
+      "eval_samples_per_second": 173.36,
+      "eval_steps_per_second": 2.709,
+      "step": 2300
+    },
+    {
+      "epoch": 1.6210526315789475,
+      "grad_norm": 7.283778667449951,
+      "learning_rate": 9.259580135361927e-08,
+      "loss": 0.8684,
+      "step": 2310
+    },
+    {
+      "epoch": 1.6280701754385964,
+      "grad_norm": 7.570828914642334,
+      "learning_rate": 8.942539543314798e-08,
+      "loss": 0.8609,
+      "step": 2320
+    },
+    {
+      "epoch": 1.6350877192982456,
+      "grad_norm": 7.366217613220215,
+      "learning_rate": 8.630487769848876e-08,
+      "loss": 0.8722,
+      "step": 2330
+    },
+    {
+      "epoch": 1.6421052631578947,
+      "grad_norm": 7.667774200439453,
+      "learning_rate": 8.32346273181696e-08,
+      "loss": 0.8883,
+      "step": 2340
+    },
+    {
+      "epoch": 1.6491228070175439,
+      "grad_norm": 8.111892700195312,
+      "learning_rate": 8.021501735282266e-08,
+      "loss": 0.8599,
+      "step": 2350
+    },
+    {
+      "epoch": 1.656140350877193,
+      "grad_norm": 7.690216064453125,
+      "learning_rate": 7.724641470985377e-08,
+      "loss": 0.8951,
+      "step": 2360
+    },
+    {
+      "epoch": 1.663157894736842,
+      "grad_norm": 7.080111980438232,
+      "learning_rate": 7.432918009885996e-08,
+      "loss": 0.865,
+      "step": 2370
+    },
+    {
+      "epoch": 1.670175438596491,
+      "grad_norm": 7.580221176147461,
+      "learning_rate": 7.146366798780096e-08,
+      "loss": 0.8905,
+      "step": 2380
+    },
+    {
+      "epoch": 1.6771929824561402,
+      "grad_norm": 6.910195827484131,
+      "learning_rate": 6.865022655992798e-08,
+      "loss": 0.8501,
+      "step": 2390
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 7.176208972930908,
+      "learning_rate": 6.588919767147638e-08,
+      "loss": 0.8461,
+      "step": 2400
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "eval_loss": 0.9966626167297363,
+      "eval_runtime": 27.668,
+      "eval_samples_per_second": 173.486,
+      "eval_steps_per_second": 2.711,
+      "step": 2400
+    },
+    {
+      "epoch": 1.6912280701754385,
+      "grad_norm": 7.764338970184326,
+      "learning_rate": 6.318091681012771e-08,
+      "loss": 0.8711,
+      "step": 2410
+    },
+    {
+      "epoch": 1.6982456140350877,
+      "grad_norm": 8.283316612243652,
+      "learning_rate": 6.052571305424531e-08,
+      "loss": 0.8738,
+      "step": 2420
+    },
+    {
+      "epoch": 1.7052631578947368,
+      "grad_norm": 7.315950870513916,
+      "learning_rate": 5.7923909032888295e-08,
+      "loss": 0.8719,
+      "step": 2430
+    },
+    {
+      "epoch": 1.712280701754386,
+      "grad_norm": 7.591914653778076,
+      "learning_rate": 5.537582088660936e-08,
+      "loss": 0.8708,
+      "step": 2440
+    },
+    {
+      "epoch": 1.719298245614035,
+      "grad_norm": 7.378705978393555,
+      "learning_rate": 5.2881758229041394e-08,
+      "loss": 0.8722,
+      "step": 2450
+    },
+    {
+      "epoch": 1.7263157894736842,
+      "grad_norm": 7.416294097900391,
+      "learning_rate": 5.044202410927706e-08,
+      "loss": 0.8586,
+      "step": 2460
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 7.301969051361084,
+      "learning_rate": 4.805691497504505e-08,
+      "loss": 0.891,
+      "step": 2470
+    },
+    {
+      "epoch": 1.7403508771929825,
+      "grad_norm": 6.946348190307617,
+      "learning_rate": 4.5726720636690195e-08,
+      "loss": 0.8871,
+      "step": 2480
+    },
+    {
+      "epoch": 1.7473684210526317,
+      "grad_norm": 7.327394008636475,
+      "learning_rate": 4.3451724231958645e-08,
+      "loss": 0.8688,
+      "step": 2490
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "grad_norm": 7.17736291885376,
+      "learning_rate": 4.123220219159418e-08,
+      "loss": 0.8729,
+      "step": 2500
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "eval_loss": 0.9957481622695923,
+      "eval_runtime": 27.665,
+      "eval_samples_per_second": 173.504,
+      "eval_steps_per_second": 2.711,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 6.354365204175782e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3e521d51513c2dd80162960b65afc3921da4988a97a3cd9bf7abb5b74239db
+size 6136

zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)