Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "princeton-nlp/Llama-3-Base-8B-SFT",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.45.0"
+}

latest

@@ -0,0 +1 @@
+global_step477

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d1b2d98445096d5a1df6fabcc3d492cecca4ca9ab1b0f00076fe4d2254aad0
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ebeb028e68cf78dca2acd953d11e6c058d47d58695e9417e124ebc260f038d8
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7773fa4c3c09b25a2703c92b509ae210de11d1096d5d7fdb61a3f14185866639
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae33a9c40aaddb51e781ffb3d13c9895924b652267ab3835941f9ae8b69ce6ec
+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:bbe0d720c4c75a6a04213fa3b64bacbe794718a53e2b56ebb67a1a795014dfad
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72452d3138d0ca2ff89429e3294a834ae7a68e8596fc757735ca56ae52509d57
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36e306fb8ebcf53a167bfd6c9af74db410a269ada1e619e3e816f5269543b9d
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb47ce0c6f815a6f8302b0e3819b4c2315ca71dae3138d97fdceb765cdd0a039
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad09778121b10b6180a6de04aa3cb3787a9a03206158a5ab20aac23f41fde3a
+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": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0968dcc0ee8e56c7dccd34a7f51f8065ea0cb9e2cc529e3243d1e5c0a4bdaa0c
+size 17208754

tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "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 loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,1474 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.998691442030882,
+  "eval_steps": 400,
+  "global_step": 477,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010468463752944255,
+      "grad_norm": 89.9968305873071,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": -0.7388366460800171,
+      "logits/rejected": -0.7827404141426086,
+      "logps/chosen": -1.15103280544281,
+      "logps/rejected": -1.2909390926361084,
+      "loss": 1.2935,
+      "rewards/accuracies": 0.581250011920929,
+      "rewards/chosen": -2.30206561088562,
+      "rewards/margins": 0.2798125147819519,
+      "rewards/rejected": -2.581878185272217,
+      "step": 5
+    },
+    {
+      "epoch": 0.02093692750588851,
+      "grad_norm": 24.705919418070632,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": -0.7937806844711304,
+      "logits/rejected": -0.8651958703994751,
+      "logps/chosen": -1.1529361009597778,
+      "logps/rejected": -1.3611778020858765,
+      "loss": 1.314,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -2.3058722019195557,
+      "rewards/margins": 0.41648340225219727,
+      "rewards/rejected": -2.722355604171753,
+      "step": 10
+    },
+    {
+      "epoch": 0.031405391258832765,
+      "grad_norm": 27.735520006717728,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": -0.7491501569747925,
+      "logits/rejected": -0.8338179588317871,
+      "logps/chosen": -1.1712462902069092,
+      "logps/rejected": -1.270825743675232,
+      "loss": 1.2667,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -2.3424925804138184,
+      "rewards/margins": 0.19915875792503357,
+      "rewards/rejected": -2.541651487350464,
+      "step": 15
+    },
+    {
+      "epoch": 0.04187385501177702,
+      "grad_norm": 22.322171681204715,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": -0.7619983553886414,
+      "logits/rejected": -0.9046538472175598,
+      "logps/chosen": -1.1294901371002197,
+      "logps/rejected": -1.2941240072250366,
+      "loss": 1.2696,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -2.2589802742004395,
+      "rewards/margins": 0.32926779985427856,
+      "rewards/rejected": -2.5882480144500732,
+      "step": 20
+    },
+    {
+      "epoch": 0.05234231876472128,
+      "grad_norm": 12.849323230827375,
+      "learning_rate": 3.125e-07,
+      "logits/chosen": -0.772399365901947,
+      "logits/rejected": -0.8519186973571777,
+      "logps/chosen": -1.077214002609253,
+      "logps/rejected": -1.2762653827667236,
+      "loss": 1.2362,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -2.154428005218506,
+      "rewards/margins": 0.39810293912887573,
+      "rewards/rejected": -2.5525307655334473,
+      "step": 25
+    },
+    {
+      "epoch": 0.06281078251766553,
+      "grad_norm": 84.84769866542291,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": -0.7909184694290161,
+      "logits/rejected": -0.8215691447257996,
+      "logps/chosen": -1.059594988822937,
+      "logps/rejected": -1.0990025997161865,
+      "loss": 1.2897,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -2.119189977645874,
+      "rewards/margins": 0.0788152664899826,
+      "rewards/rejected": -2.198005199432373,
+      "step": 30
+    },
+    {
+      "epoch": 0.07327924627060979,
+      "grad_norm": 12.477109087394112,
+      "learning_rate": 4.3749999999999994e-07,
+      "logits/chosen": -0.7678741216659546,
+      "logits/rejected": -0.8405346870422363,
+      "logps/chosen": -0.9820269346237183,
+      "logps/rejected": -1.2532163858413696,
+      "loss": 1.2497,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": -1.9640538692474365,
+      "rewards/margins": 0.5423787236213684,
+      "rewards/rejected": -2.5064327716827393,
+      "step": 35
+    },
+    {
+      "epoch": 0.08374771002355404,
+      "grad_norm": 10.85962784004132,
+      "learning_rate": 5e-07,
+      "logits/chosen": -0.7665027379989624,
+      "logits/rejected": -0.8336607217788696,
+      "logps/chosen": -0.9715523719787598,
+      "logps/rejected": -1.1505324840545654,
+      "loss": 1.2359,
+      "rewards/accuracies": 0.5687500238418579,
+      "rewards/chosen": -1.9431047439575195,
+      "rewards/margins": 0.35795995593070984,
+      "rewards/rejected": -2.301064968109131,
+      "step": 40
+    },
+    {
+      "epoch": 0.0942161737764983,
+      "grad_norm": 10.414385637292323,
+      "learning_rate": 5.625e-07,
+      "logits/chosen": -0.7420114874839783,
+      "logits/rejected": -0.8339902758598328,
+      "logps/chosen": -0.9872716665267944,
+      "logps/rejected": -1.1155823469161987,
+      "loss": 1.2267,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": -1.9745433330535889,
+      "rewards/margins": 0.2566211223602295,
+      "rewards/rejected": -2.2311646938323975,
+      "step": 45
+    },
+    {
+      "epoch": 0.10468463752944256,
+      "grad_norm": 9.651448839940226,
+      "learning_rate": 5.999678242522831e-07,
+      "logits/chosen": -0.7927948832511902,
+      "logits/rejected": -0.8290635943412781,
+      "logps/chosen": -0.9459100961685181,
+      "logps/rejected": -1.2578647136688232,
+      "loss": 1.2207,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -1.8918201923370361,
+      "rewards/margins": 0.6239093542098999,
+      "rewards/rejected": -2.5157294273376465,
+      "step": 50
+    },
+    {
+      "epoch": 0.11515310128238682,
+      "grad_norm": 43.90472722310407,
+      "learning_rate": 5.996059263493219e-07,
+      "logits/chosen": -0.7944079637527466,
+      "logits/rejected": -0.9001775979995728,
+      "logps/chosen": -1.072819471359253,
+      "logps/rejected": -1.181773066520691,
+      "loss": 1.2551,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -2.145638942718506,
+      "rewards/margins": 0.21790704131126404,
+      "rewards/rejected": -2.363546133041382,
+      "step": 55
+    },
+    {
+      "epoch": 0.12562156503533106,
+      "grad_norm": 13.393066662370963,
+      "learning_rate": 5.988423976115163e-07,
+      "logits/chosen": -0.7826106548309326,
+      "logits/rejected": -0.8369284868240356,
+      "logps/chosen": -1.0628390312194824,
+      "logps/rejected": -1.2253072261810303,
+      "loss": 1.2246,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -2.125678062438965,
+      "rewards/margins": 0.32493603229522705,
+      "rewards/rejected": -2.4506144523620605,
+      "step": 60
+    },
+    {
+      "epoch": 0.1360900287882753,
+      "grad_norm": 26.206483702491475,
+      "learning_rate": 5.976782615723061e-07,
+      "logits/chosen": -0.7975456714630127,
+      "logits/rejected": -0.8562803268432617,
+      "logps/chosen": -1.0680768489837646,
+      "logps/rejected": -1.2204017639160156,
+      "loss": 1.2268,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": -2.1361536979675293,
+      "rewards/margins": 0.3046496510505676,
+      "rewards/rejected": -2.4408035278320312,
+      "step": 65
+    },
+    {
+      "epoch": 0.14655849254121958,
+      "grad_norm": 13.41584537004533,
+      "learning_rate": 5.961150787913738e-07,
+      "logits/chosen": -0.8376196622848511,
+      "logits/rejected": -0.9019572138786316,
+      "logps/chosen": -1.0893644094467163,
+      "logps/rejected": -1.2784545421600342,
+      "loss": 1.1754,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": -2.1787288188934326,
+      "rewards/margins": 0.37818047404289246,
+      "rewards/rejected": -2.5569090843200684,
+      "step": 70
+    },
+    {
+      "epoch": 0.15702695629416383,
+      "grad_norm": 32.22425187362688,
+      "learning_rate": 5.941549447626671e-07,
+      "logits/chosen": -0.804112434387207,
+      "logits/rejected": -0.845563530921936,
+      "logps/chosen": -1.0805425643920898,
+      "logps/rejected": -1.3212538957595825,
+      "loss": 1.209,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -2.1610851287841797,
+      "rewards/margins": 0.4814226031303406,
+      "rewards/rejected": -2.642507791519165,
+      "step": 75
+    },
+    {
+      "epoch": 0.16749542004710807,
+      "grad_norm": 8.981853488976475,
+      "learning_rate": 5.918004871053251e-07,
+      "logits/chosen": -0.7968226671218872,
+      "logits/rejected": -0.8211067318916321,
+      "logps/chosen": -1.026604413986206,
+      "logps/rejected": -1.3631267547607422,
+      "loss": 1.1624,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -2.053208827972412,
+      "rewards/margins": 0.673044741153717,
+      "rewards/rejected": -2.7262535095214844,
+      "step": 80
+    },
+    {
+      "epoch": 0.17796388380005235,
+      "grad_norm": 17.367470137588203,
+      "learning_rate": 5.890548620412763e-07,
+      "logits/chosen": -0.8126602172851562,
+      "logits/rejected": -0.8794834017753601,
+      "logps/chosen": -1.0674957036972046,
+      "logps/rejected": -1.3523355722427368,
+      "loss": 1.1625,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -2.134991407394409,
+      "rewards/margins": 0.5696790814399719,
+      "rewards/rejected": -2.7046711444854736,
+      "step": 85
+    },
+    {
+      "epoch": 0.1884323475529966,
+      "grad_norm": 17.833322868673477,
+      "learning_rate": 5.859217501642258e-07,
+      "logits/chosen": -0.840762734413147,
+      "logits/rejected": -0.9274584054946899,
+      "logps/chosen": -1.1602346897125244,
+      "logps/rejected": -1.5290915966033936,
+      "loss": 1.1734,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -2.320469379425049,
+      "rewards/margins": 0.7377143502235413,
+      "rewards/rejected": -3.058183193206787,
+      "step": 90
+    },
+    {
+      "epoch": 0.19890081130594087,
+      "grad_norm": 22.98307788140464,
+      "learning_rate": 5.824053515057091e-07,
+      "logits/chosen": -0.8092079162597656,
+      "logits/rejected": -0.8328098058700562,
+      "logps/chosen": -1.133385419845581,
+      "logps/rejected": -1.4298288822174072,
+      "loss": 1.1919,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -2.266770839691162,
+      "rewards/margins": 0.5928869247436523,
+      "rewards/rejected": -2.8596577644348145,
+      "step": 95
+    },
+    {
+      "epoch": 0.2093692750588851,
+      "grad_norm": 11.026437481785171,
+      "learning_rate": 5.785103799048218e-07,
+      "logits/chosen": -0.8240598440170288,
+      "logits/rejected": -0.8689464330673218,
+      "logps/chosen": -1.147385835647583,
+      "logps/rejected": -1.3535184860229492,
+      "loss": 1.2131,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -2.294771671295166,
+      "rewards/margins": 0.41226544976234436,
+      "rewards/rejected": -2.7070369720458984,
+      "step": 100
+    },
+    {
+      "epoch": 0.21983773881182936,
+      "grad_norm": 9.837343506686455,
+      "learning_rate": 5.742420566891749e-07,
+      "logits/chosen": -0.7966706156730652,
+      "logits/rejected": -0.878908634185791,
+      "logps/chosen": -1.1871858835220337,
+      "logps/rejected": -1.4869831800460815,
+      "loss": 1.1062,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -2.3743717670440674,
+      "rewards/margins": 0.5995948314666748,
+      "rewards/rejected": -2.973966360092163,
+      "step": 105
+    },
+    {
+      "epoch": 0.23030620256477363,
+      "grad_norm": 19.01097451640794,
+      "learning_rate": 5.696061036755478e-07,
+      "logits/chosen": -0.7402995228767395,
+      "logits/rejected": -0.8451690673828125,
+      "logps/chosen": -1.0870535373687744,
+      "logps/rejected": -1.3536127805709839,
+      "loss": 1.1368,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": -2.174107074737549,
+      "rewards/margins": 0.5331184267997742,
+      "rewards/rejected": -2.7072255611419678,
+      "step": 110
+    },
+    {
+      "epoch": 0.24077466631771788,
+      "grad_norm": 89.427421788791,
+      "learning_rate": 5.64608735499618e-07,
+      "logits/chosen": -0.833459734916687,
+      "logits/rejected": -0.829018235206604,
+      "logps/chosen": -1.150940179824829,
+      "logps/rejected": -1.287229061126709,
+      "loss": 1.1596,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -2.301880359649658,
+      "rewards/margins": 0.2725774943828583,
+      "rewards/rejected": -2.574458122253418,
+      "step": 115
+    },
+    {
+      "epoch": 0.2512431300706621,
+      "grad_norm": 31.745365051153907,
+      "learning_rate": 5.592566512850545e-07,
+      "logits/chosen": -0.79100501537323,
+      "logits/rejected": -0.8663417100906372,
+      "logps/chosen": -1.0571635961532593,
+      "logps/rejected": -1.4087059497833252,
+      "loss": 1.1752,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -2.1143271923065186,
+      "rewards/margins": 0.703084409236908,
+      "rewards/rejected": -2.8174118995666504,
+      "step": 120
+    },
+    {
+      "epoch": 0.26171159382360637,
+      "grad_norm": 14.496796822119729,
+      "learning_rate": 5.535570256631384e-07,
+      "logits/chosen": -0.798068642616272,
+      "logits/rejected": -0.7694944143295288,
+      "logps/chosen": -1.171478271484375,
+      "logps/rejected": -1.5117442607879639,
+      "loss": 1.1603,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -2.34295654296875,
+      "rewards/margins": 0.6805320978164673,
+      "rewards/rejected": -3.0234885215759277,
+      "step": 125
+    },
+    {
+      "epoch": 0.2721800575765506,
+      "grad_norm": 11.15517991690276,
+      "learning_rate": 5.475174991549528e-07,
+      "logits/chosen": -0.7599740624427795,
+      "logits/rejected": -0.8051120638847351,
+      "logps/chosen": -1.1963175535202026,
+      "logps/rejected": -1.5290193557739258,
+      "loss": 1.1204,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -2.3926351070404053,
+      "rewards/margins": 0.6654035449028015,
+      "rewards/rejected": -3.0580387115478516,
+      "step": 130
+    },
+    {
+      "epoch": 0.2826485213294949,
+      "grad_norm": 13.030746243741968,
+      "learning_rate": 5.411461679290317e-07,
+      "logits/chosen": -0.7586075663566589,
+      "logits/rejected": -0.7899220585823059,
+      "logps/chosen": -1.0880517959594727,
+      "logps/rejected": -1.4661823511123657,
+      "loss": 1.1668,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": -2.1761035919189453,
+      "rewards/margins": 0.7562611103057861,
+      "rewards/rejected": -2.9323647022247314,
+      "step": 135
+    },
+    {
+      "epoch": 0.29311698508243916,
+      "grad_norm": 12.738817253337984,
+      "learning_rate": 5.34451572948201e-07,
+      "logits/chosen": -0.8128818273544312,
+      "logits/rejected": -0.842110812664032,
+      "logps/chosen": -1.2075114250183105,
+      "logps/rejected": -1.4238183498382568,
+      "loss": 1.2141,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -2.415022850036621,
+      "rewards/margins": 0.4326140284538269,
+      "rewards/rejected": -2.8476366996765137,
+      "step": 140
+    },
+    {
+      "epoch": 0.3035854488353834,
+      "grad_norm": 24.983190739092922,
+      "learning_rate": 5.274426885201582e-07,
+      "logits/chosen": -0.7843077778816223,
+      "logits/rejected": -0.8767129182815552,
+      "logps/chosen": -1.1461377143859863,
+      "logps/rejected": -1.5009636878967285,
+      "loss": 1.1207,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -2.2922754287719727,
+      "rewards/margins": 0.7096518278121948,
+      "rewards/rejected": -3.001927375793457,
+      "step": 145
+    },
+    {
+      "epoch": 0.31405391258832765,
+      "grad_norm": 23.74860585722539,
+      "learning_rate": 5.201289102671411e-07,
+      "logits/chosen": -0.8561376333236694,
+      "logits/rejected": -0.8589056134223938,
+      "logps/chosen": -1.1982135772705078,
+      "logps/rejected": -1.5201013088226318,
+      "loss": 1.1476,
+      "rewards/accuracies": 0.5687500238418579,
+      "rewards/chosen": -2.3964271545410156,
+      "rewards/margins": 0.6437759399414062,
+      "rewards/rejected": -3.0402026176452637,
+      "step": 150
+    },
+    {
+      "epoch": 0.3245223763412719,
+      "grad_norm": 15.03909875634319,
+      "learning_rate": 5.12520042530811e-07,
+      "logits/chosen": -0.7681445479393005,
+      "logits/rejected": -0.8174452781677246,
+      "logps/chosen": -1.2068870067596436,
+      "logps/rejected": -1.6613304615020752,
+      "loss": 1.1179,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -2.413774013519287,
+      "rewards/margins": 0.908886730670929,
+      "rewards/rejected": -3.3226609230041504,
+      "step": 155
+    },
+    {
+      "epoch": 0.33499084009421615,
+      "grad_norm": 14.191169695059497,
+      "learning_rate": 5.046262852292346e-07,
+      "logits/chosen": -0.8029179573059082,
+      "logits/rejected": -0.8746109008789062,
+      "logps/chosen": -1.1898596286773682,
+      "logps/rejected": -1.6815717220306396,
+      "loss": 1.1138,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -2.3797192573547363,
+      "rewards/margins": 0.9834240674972534,
+      "rewards/rejected": -3.3631434440612793,
+      "step": 160
+    },
+    {
+      "epoch": 0.34545930384716045,
+      "grad_norm": 35.93680907186828,
+      "learning_rate": 4.964582201835856e-07,
+      "logits/chosen": -0.7598133087158203,
+      "logits/rejected": -0.7828689813613892,
+      "logps/chosen": -1.1410859823226929,
+      "logps/rejected": -1.5104478597640991,
+      "loss": 1.1132,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -2.2821719646453857,
+      "rewards/margins": 0.7387233972549438,
+      "rewards/rejected": -3.0208957195281982,
+      "step": 165
+    },
+    {
+      "epoch": 0.3559277676001047,
+      "grad_norm": 33.280459458949075,
+      "learning_rate": 4.880267969328908e-07,
+      "logits/chosen": -0.7489741444587708,
+      "logits/rejected": -0.8511075973510742,
+      "logps/chosen": -1.2344070672988892,
+      "logps/rejected": -1.6722608804702759,
+      "loss": 1.1051,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -2.4688141345977783,
+      "rewards/margins": 0.8757076263427734,
+      "rewards/rejected": -3.3445217609405518,
+      "step": 170
+    },
+    {
+      "epoch": 0.36639623135304894,
+      "grad_norm": 13.559524548726696,
+      "learning_rate": 4.793433180558423e-07,
+      "logits/chosen": -0.7471566796302795,
+      "logits/rejected": -0.8381919860839844,
+      "logps/chosen": -1.1587435007095337,
+      "logps/rejected": -1.5522888898849487,
+      "loss": 1.133,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -2.3174870014190674,
+      "rewards/margins": 0.7870910167694092,
+      "rewards/rejected": -3.1045777797698975,
+      "step": 175
+    },
+    {
+      "epoch": 0.3768646951059932,
+      "grad_norm": 19.60609504538111,
+      "learning_rate": 4.704194240193467e-07,
+      "logits/chosen": -0.7779995203018188,
+      "logits/rejected": -0.8208974599838257,
+      "logps/chosen": -1.1914243698120117,
+      "logps/rejected": -1.6478986740112305,
+      "loss": 1.0991,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -2.3828487396240234,
+      "rewards/margins": 0.9129486083984375,
+      "rewards/rejected": -3.295797348022461,
+      "step": 180
+    },
+    {
+      "epoch": 0.38733315885893743,
+      "grad_norm": 15.986798312827595,
+      "learning_rate": 4.6126707757412686e-07,
+      "logits/chosen": -0.7536464333534241,
+      "logits/rejected": -0.836445152759552,
+      "logps/chosen": -1.18105149269104,
+      "logps/rejected": -1.5753639936447144,
+      "loss": 1.0801,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -2.36210298538208,
+      "rewards/margins": 0.788625180721283,
+      "rewards/rejected": -3.1507279872894287,
+      "step": 185
+    },
+    {
+      "epoch": 0.39780162261188173,
+      "grad_norm": 11.085659412542848,
+      "learning_rate": 4.5189854771829086e-07,
+      "logits/chosen": -0.7779768705368042,
+      "logits/rejected": -0.860378623008728,
+      "logps/chosen": -1.174264907836914,
+      "logps/rejected": -1.5782097578048706,
+      "loss": 1.0897,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -2.348529815673828,
+      "rewards/margins": 0.8078898191452026,
+      "rewards/rejected": -3.156419515609741,
+      "step": 190
+    },
+    {
+      "epoch": 0.408270086364826,
+      "grad_norm": 19.478521042945726,
+      "learning_rate": 4.4232639325036807e-07,
+      "logits/chosen": -0.8138440251350403,
+      "logits/rejected": -0.888975977897644,
+      "logps/chosen": -1.1923892498016357,
+      "logps/rejected": -1.6592342853546143,
+      "loss": 1.1171,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -2.3847784996032715,
+      "rewards/margins": 0.933690071105957,
+      "rewards/rejected": -3.3184685707092285,
+      "step": 195
+    },
+    {
+      "epoch": 0.4187385501177702,
+      "grad_norm": 12.673420292445082,
+      "learning_rate": 4.32563445933859e-07,
+      "logits/chosen": -0.7443628311157227,
+      "logits/rejected": -0.7802754044532776,
+      "logps/chosen": -1.211715579032898,
+      "logps/rejected": -1.5577033758163452,
+      "loss": 1.0631,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -2.423431158065796,
+      "rewards/margins": 0.6919752955436707,
+      "rewards/rejected": -3.1154067516326904,
+      "step": 200
+    },
+    {
+      "epoch": 0.42920701387071447,
+      "grad_norm": 18.156036717162227,
+      "learning_rate": 4.226227932958664e-07,
+      "logits/chosen": -0.8596774935722351,
+      "logits/rejected": -0.8864806294441223,
+      "logps/chosen": -1.2197387218475342,
+      "logps/rejected": -1.706209421157837,
+      "loss": 1.0695,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": -2.4394774436950684,
+      "rewards/margins": 0.9729412794113159,
+      "rewards/rejected": -3.412418842315674,
+      "step": 205
+    },
+    {
+      "epoch": 0.4396754776236587,
+      "grad_norm": 18.614311057711063,
+      "learning_rate": 4.1251776108286854e-07,
+      "logits/chosen": -0.7632856965065002,
+      "logits/rejected": -0.7707933187484741,
+      "logps/chosen": -1.2796884775161743,
+      "logps/rejected": -1.6428205966949463,
+      "loss": 1.1264,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -2.5593769550323486,
+      "rewards/margins": 0.7262641191482544,
+      "rewards/rejected": -3.2856411933898926,
+      "step": 210
+    },
+    {
+      "epoch": 0.45014394137660296,
+      "grad_norm": 19.070261616595026,
+      "learning_rate": 4.022618953971514e-07,
+      "logits/chosen": -0.7568240761756897,
+      "logits/rejected": -0.8358641862869263,
+      "logps/chosen": -1.308774709701538,
+      "logps/rejected": -1.6738483905792236,
+      "loss": 1.1102,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -2.617549419403076,
+      "rewards/margins": 0.7301470041275024,
+      "rewards/rejected": -3.3476967811584473,
+      "step": 215
+    },
+    {
+      "epoch": 0.46061240512954726,
+      "grad_norm": 13.160800920164423,
+      "learning_rate": 3.918689445378477e-07,
+      "logits/chosen": -0.7660185098648071,
+      "logits/rejected": -0.8393454551696777,
+      "logps/chosen": -1.2900028228759766,
+      "logps/rejected": -1.7106046676635742,
+      "loss": 1.0429,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -2.580005645751953,
+      "rewards/margins": 0.8412036895751953,
+      "rewards/rejected": -3.4212093353271484,
+      "step": 220
+    },
+    {
+      "epoch": 0.4710808688824915,
+      "grad_norm": 15.467772988868518,
+      "learning_rate": 3.813528405709251e-07,
+      "logits/chosen": -0.7320618629455566,
+      "logits/rejected": -0.7756307125091553,
+      "logps/chosen": -1.3943421840667725,
+      "logps/rejected": -1.8419634103775024,
+      "loss": 1.084,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -2.788684368133545,
+      "rewards/margins": 0.8952423334121704,
+      "rewards/rejected": -3.683926820755005,
+      "step": 225
+    },
+    {
+      "epoch": 0.48154933263543576,
+      "grad_norm": 23.599162652169078,
+      "learning_rate": 3.707276806528282e-07,
+      "logits/chosen": -0.7983018159866333,
+      "logits/rejected": -0.8536737561225891,
+      "logps/chosen": -1.3397753238677979,
+      "logps/rejected": -1.8982980251312256,
+      "loss": 1.0107,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": -2.6795506477355957,
+      "rewards/margins": 1.1170451641082764,
+      "rewards/rejected": -3.796596050262451,
+      "step": 230
+    },
+    {
+      "epoch": 0.49201779638838,
+      "grad_norm": 22.745006961113983,
+      "learning_rate": 3.6000770813281334e-07,
+      "logits/chosen": -0.7526620626449585,
+      "logits/rejected": -0.7841376066207886,
+      "logps/chosen": -1.3173251152038574,
+      "logps/rejected": -1.6973741054534912,
+      "loss": 1.096,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -2.634650230407715,
+      "rewards/margins": 0.7600980401039124,
+      "rewards/rejected": -3.3947482109069824,
+      "step": 235
+    },
+    {
+      "epoch": 0.5024862601413242,
+      "grad_norm": 17.29631229132808,
+      "learning_rate": 3.4920729345930654e-07,
+      "logits/chosen": -0.8024924993515015,
+      "logits/rejected": -0.8705514669418335,
+      "logps/chosen": -1.3106586933135986,
+      "logps/rejected": -1.8416321277618408,
+      "loss": 1.0622,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -2.6213173866271973,
+      "rewards/margins": 1.0619468688964844,
+      "rewards/rejected": -3.6832642555236816,
+      "step": 240
+    },
+    {
+      "epoch": 0.5129547238942685,
+      "grad_norm": 15.697390709369445,
+      "learning_rate": 3.383409149158814e-07,
+      "logits/chosen": -0.8013178110122681,
+      "logits/rejected": -0.8261008262634277,
+      "logps/chosen": -1.2374125719070435,
+      "logps/rejected": -1.8463026285171509,
+      "loss": 1.0412,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -2.474825143814087,
+      "rewards/margins": 1.2177798748016357,
+      "rewards/rejected": -3.6926052570343018,
+      "step": 245
+    },
+    {
+      "epoch": 0.5234231876472127,
+      "grad_norm": 38.568029652024805,
+      "learning_rate": 3.2742313921268035e-07,
+      "logits/chosen": -0.7440148591995239,
+      "logits/rejected": -0.8371674418449402,
+      "logps/chosen": -1.3792295455932617,
+      "logps/rejected": -1.996372938156128,
+      "loss": 1.0533,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -2.7584590911865234,
+      "rewards/margins": 1.234286904335022,
+      "rewards/rejected": -3.992745876312256,
+      "step": 250
+    },
+    {
+      "epoch": 0.533891651400157,
+      "grad_norm": 31.29600689027817,
+      "learning_rate": 3.1646860195929825e-07,
+      "logits/chosen": -0.798254132270813,
+      "logits/rejected": -0.819698691368103,
+      "logps/chosen": -1.4148808717727661,
+      "logps/rejected": -1.9883480072021484,
+      "loss": 1.1126,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -2.8297617435455322,
+      "rewards/margins": 1.1469345092773438,
+      "rewards/rejected": -3.976696014404297,
+      "step": 255
+    },
+    {
+      "epoch": 0.5443601151531012,
+      "grad_norm": 21.255043892106038,
+      "learning_rate": 3.054919880453032e-07,
+      "logits/chosen": -0.8065778017044067,
+      "logits/rejected": -0.8200203776359558,
+      "logps/chosen": -1.3674335479736328,
+      "logps/rejected": -1.8728046417236328,
+      "loss": 1.0948,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -2.7348670959472656,
+      "rewards/margins": 1.0107421875,
+      "rewards/rejected": -3.7456092834472656,
+      "step": 260
+    },
+    {
+      "epoch": 0.5548285789060455,
+      "grad_norm": 15.283609874940026,
+      "learning_rate": 2.9450801195469686e-07,
+      "logits/chosen": -0.7686730027198792,
+      "logits/rejected": -0.7811926603317261,
+      "logps/chosen": -1.3809654712677002,
+      "logps/rejected": -1.8307151794433594,
+      "loss": 1.0502,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -2.7619309425354004,
+      "rewards/margins": 0.8994992971420288,
+      "rewards/rejected": -3.6614303588867188,
+      "step": 265
+    },
+    {
+      "epoch": 0.5652970426589898,
+      "grad_norm": 34.69673151716839,
+      "learning_rate": 2.835313980407017e-07,
+      "logits/chosen": -0.8522397875785828,
+      "logits/rejected": -0.8554953336715698,
+      "logps/chosen": -1.4796664714813232,
+      "logps/rejected": -1.868570327758789,
+      "loss": 1.11,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -2.9593329429626465,
+      "rewards/margins": 0.7778076529502869,
+      "rewards/rejected": -3.737140655517578,
+      "step": 270
+    },
+    {
+      "epoch": 0.575765506411934,
+      "grad_norm": 12.490257980809535,
+      "learning_rate": 2.7257686078731973e-07,
+      "logits/chosen": -0.8593546748161316,
+      "logits/rejected": -0.8926668167114258,
+      "logps/chosen": -1.2937114238739014,
+      "logps/rejected": -2.0442328453063965,
+      "loss": 0.9612,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -2.5874228477478027,
+      "rewards/margins": 1.5010432004928589,
+      "rewards/rejected": -4.088465690612793,
+      "step": 275
+    },
+    {
+      "epoch": 0.5862339701648783,
+      "grad_norm": 17.66798289482467,
+      "learning_rate": 2.6165908508411857e-07,
+      "logits/chosen": -0.7889951467514038,
+      "logits/rejected": -0.8469230532646179,
+      "logps/chosen": -1.3164467811584473,
+      "logps/rejected": -1.873552680015564,
+      "loss": 1.0829,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -2.6328935623168945,
+      "rewards/margins": 1.114211916923523,
+      "rewards/rejected": -3.747105360031128,
+      "step": 280
+    },
+    {
+      "epoch": 0.5967024339178225,
+      "grad_norm": 25.798144103608532,
+      "learning_rate": 2.5079270654069354e-07,
+      "logits/chosen": -0.7999380230903625,
+      "logits/rejected": -0.8465052843093872,
+      "logps/chosen": -1.4005292654037476,
+      "logps/rejected": -1.9563087224960327,
+      "loss": 1.0559,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -2.801058530807495,
+      "rewards/margins": 1.1115590333938599,
+      "rewards/rejected": -3.9126174449920654,
+      "step": 285
+    },
+    {
+      "epoch": 0.6071708976707668,
+      "grad_norm": 26.70646393830588,
+      "learning_rate": 2.399922918671867e-07,
+      "logits/chosen": -0.8188889622688293,
+      "logits/rejected": -0.8326479196548462,
+      "logps/chosen": -1.4042682647705078,
+      "logps/rejected": -1.8107773065567017,
+      "loss": 1.0877,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -2.8085365295410156,
+      "rewards/margins": 0.8130179643630981,
+      "rewards/rejected": -3.6215546131134033,
+      "step": 290
+    },
+    {
+      "epoch": 0.6176393614237111,
+      "grad_norm": 23.426122701316096,
+      "learning_rate": 2.2927231934717176e-07,
+      "logits/chosen": -0.8667086362838745,
+      "logits/rejected": -0.87919682264328,
+      "logps/chosen": -1.4516851902008057,
+      "logps/rejected": -1.7210047245025635,
+      "loss": 1.0425,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -2.9033703804016113,
+      "rewards/margins": 0.5386390686035156,
+      "rewards/rejected": -3.442009449005127,
+      "step": 295
+    },
+    {
+      "epoch": 0.6281078251766553,
+      "grad_norm": 26.456279591360094,
+      "learning_rate": 2.1864715942907487e-07,
+      "logits/chosen": -0.8121633529663086,
+      "logits/rejected": -0.8183205723762512,
+      "logps/chosen": -1.4428894519805908,
+      "logps/rejected": -1.9755233526229858,
+      "loss": 1.0841,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": -2.8857789039611816,
+      "rewards/margins": 1.0652679204940796,
+      "rewards/rejected": -3.9510467052459717,
+      "step": 300
+    },
+    {
+      "epoch": 0.6385762889295996,
+      "grad_norm": 31.787422608248555,
+      "learning_rate": 2.081310554621522e-07,
+      "logits/chosen": -0.812918484210968,
+      "logits/rejected": -0.848720371723175,
+      "logps/chosen": -1.3704057931900024,
+      "logps/rejected": -1.7566410303115845,
+      "loss": 1.0211,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -2.740811586380005,
+      "rewards/margins": 0.7724703550338745,
+      "rewards/rejected": -3.513282060623169,
+      "step": 305
+    },
+    {
+      "epoch": 0.6490447526825438,
+      "grad_norm": 20.39803180345373,
+      "learning_rate": 1.9773810460284862e-07,
+      "logits/chosen": -0.7991079092025757,
+      "logits/rejected": -0.8711285591125488,
+      "logps/chosen": -1.4278900623321533,
+      "logps/rejected": -2.05625581741333,
+      "loss": 0.9925,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -2.8557801246643066,
+      "rewards/margins": 1.256731629371643,
+      "rewards/rejected": -4.11251163482666,
+      "step": 310
+    },
+    {
+      "epoch": 0.6595132164354881,
+      "grad_norm": 22.590110789535018,
+      "learning_rate": 1.874822389171314e-07,
+      "logits/chosen": -0.8574708700180054,
+      "logits/rejected": -0.9009912610054016,
+      "logps/chosen": -1.545143723487854,
+      "logps/rejected": -2.0895230770111084,
+      "loss": 1.0237,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -3.090287446975708,
+      "rewards/margins": 1.088758945465088,
+      "rewards/rejected": -4.179046154022217,
+      "step": 315
+    },
+    {
+      "epoch": 0.6699816801884323,
+      "grad_norm": 19.0520960322845,
+      "learning_rate": 1.7737720670413356e-07,
+      "logits/chosen": -0.8097273111343384,
+      "logits/rejected": -0.8335424661636353,
+      "logps/chosen": -1.5219576358795166,
+      "logps/rejected": -2.0950403213500977,
+      "loss": 1.0412,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -3.043915271759033,
+      "rewards/margins": 1.1461658477783203,
+      "rewards/rejected": -4.190080642700195,
+      "step": 320
+    },
+    {
+      "epoch": 0.6804501439413766,
+      "grad_norm": 28.978881064657845,
+      "learning_rate": 1.6743655406614095e-07,
+      "logits/chosen": -0.8851544260978699,
+      "logits/rejected": -0.8812357187271118,
+      "logps/chosen": -1.505824089050293,
+      "logps/rejected": -2.034778118133545,
+      "loss": 1.0881,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -3.011648178100586,
+      "rewards/margins": 1.0579078197479248,
+      "rewards/rejected": -4.06955623626709,
+      "step": 325
+    },
+    {
+      "epoch": 0.6909186076943209,
+      "grad_norm": 23.915843277630973,
+      "learning_rate": 1.5767360674963198e-07,
+      "logits/chosen": -0.870714008808136,
+      "logits/rejected": -0.8971943855285645,
+      "logps/chosen": -1.3601343631744385,
+      "logps/rejected": -2.0130364894866943,
+      "loss": 1.0087,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -2.720268726348877,
+      "rewards/margins": 1.3058046102523804,
+      "rewards/rejected": -4.026072978973389,
+      "step": 330
+    },
+    {
+      "epoch": 0.7013870714472651,
+      "grad_norm": 26.514246744997322,
+      "learning_rate": 1.4810145228170922e-07,
+      "logits/chosen": -0.8225549459457397,
+      "logits/rejected": -0.8689346313476562,
+      "logps/chosen": -1.4374722242355347,
+      "logps/rejected": -1.9102426767349243,
+      "loss": 1.052,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -2.8749444484710693,
+      "rewards/margins": 0.9455404281616211,
+      "rewards/rejected": -3.8204853534698486,
+      "step": 335
+    },
+    {
+      "epoch": 0.7118555352002094,
+      "grad_norm": 27.7004551617753,
+      "learning_rate": 1.3873292242587306e-07,
+      "logits/chosen": -0.8165398836135864,
+      "logits/rejected": -0.9100580215454102,
+      "logps/chosen": -1.461507797241211,
+      "logps/rejected": -2.0511550903320312,
+      "loss": 1.0709,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -2.923015594482422,
+      "rewards/margins": 1.1792947053909302,
+      "rewards/rejected": -4.1023101806640625,
+      "step": 340
+    },
+    {
+      "epoch": 0.7223239989531536,
+      "grad_norm": 24.617595975995133,
+      "learning_rate": 1.295805759806533e-07,
+      "logits/chosen": -0.8566834330558777,
+      "logits/rejected": -0.8978926539421082,
+      "logps/chosen": -1.5079203844070435,
+      "logps/rejected": -2.044774293899536,
+      "loss": 1.0388,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -3.015840768814087,
+      "rewards/margins": 1.073707938194275,
+      "rewards/rejected": -4.089548587799072,
+      "step": 345
+    },
+    {
+      "epoch": 0.7327924627060979,
+      "grad_norm": 22.995198881906134,
+      "learning_rate": 1.2065668194415777e-07,
+      "logits/chosen": -0.8893098831176758,
+      "logits/rejected": -0.9465163946151733,
+      "logps/chosen": -1.5923842191696167,
+      "logps/rejected": -2.066089153289795,
+      "loss": 0.9896,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -3.1847684383392334,
+      "rewards/margins": 0.947409987449646,
+      "rewards/rejected": -4.13217830657959,
+      "step": 350
+    },
+    {
+      "epoch": 0.7432609264590422,
+      "grad_norm": 22.355221430364576,
+      "learning_rate": 1.1197320306710923e-07,
+      "logits/chosen": -0.8776585459709167,
+      "logits/rejected": -0.9053448438644409,
+      "logps/chosen": -1.5153396129608154,
+      "logps/rejected": -2.0724828243255615,
+      "loss": 1.0507,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -3.030679225921631,
+      "rewards/margins": 1.1142865419387817,
+      "rewards/rejected": -4.144965648651123,
+      "step": 355
+    },
+    {
+      "epoch": 0.7537293902119864,
+      "grad_norm": 23.090030368869293,
+      "learning_rate": 1.035417798164145e-07,
+      "logits/chosen": -0.8465662002563477,
+      "logits/rejected": -0.9114416837692261,
+      "logps/chosen": -1.5818672180175781,
+      "logps/rejected": -2.124342441558838,
+      "loss": 1.0082,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -3.1637344360351562,
+      "rewards/margins": 1.0849504470825195,
+      "rewards/rejected": -4.248684883117676,
+      "step": 360
+    },
+    {
+      "epoch": 0.7641978539649307,
+      "grad_norm": 23.156782358223225,
+      "learning_rate": 9.537371477076535e-08,
+      "logits/chosen": -0.8677560687065125,
+      "logits/rejected": -0.9061796069145203,
+      "logps/chosen": -1.5915837287902832,
+      "logps/rejected": -2.287815570831299,
+      "loss": 0.9867,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -3.1831674575805664,
+      "rewards/margins": 1.3924639225006104,
+      "rewards/rejected": -4.575631141662598,
+      "step": 365
+    },
+    {
+      "epoch": 0.7746663177178749,
+      "grad_norm": 20.328637763728924,
+      "learning_rate": 8.747995746918898e-08,
+      "logits/chosen": -0.8234347105026245,
+      "logits/rejected": -0.8825669288635254,
+      "logps/chosen": -1.5265567302703857,
+      "logps/rejected": -2.1997315883636475,
+      "loss": 0.9162,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -3.0531134605407715,
+      "rewards/margins": 1.3463497161865234,
+      "rewards/rejected": -4.399463176727295,
+      "step": 370
+    },
+    {
+      "epoch": 0.7851347814708192,
+      "grad_norm": 38.958615879066635,
+      "learning_rate": 7.987108973285888e-08,
+      "logits/chosen": -0.8697785139083862,
+      "logits/rejected": -0.8908045887947083,
+      "logps/chosen": -1.508302927017212,
+      "logps/rejected": -2.1442337036132812,
+      "loss": 1.0045,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -3.016605854034424,
+      "rewards/margins": 1.2718614339828491,
+      "rewards/rejected": -4.2884674072265625,
+      "step": 375
+    },
+    {
+      "epoch": 0.7956032452237635,
+      "grad_norm": 40.64376807024019,
+      "learning_rate": 7.255731147984174e-08,
+      "logits/chosen": -0.8699348568916321,
+      "logits/rejected": -0.9192712903022766,
+      "logps/chosen": -1.5248959064483643,
+      "logps/rejected": -2.057331085205078,
+      "loss": 1.0402,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -3.0497918128967285,
+      "rewards/margins": 1.064869999885559,
+      "rewards/rejected": -4.114662170410156,
+      "step": 380
+    },
+    {
+      "epoch": 0.8060717089767077,
+      "grad_norm": 31.79789174489367,
+      "learning_rate": 6.554842705179898e-08,
+      "logits/chosen": -0.8611375093460083,
+      "logits/rejected": -0.8788291215896606,
+      "logps/chosen": -1.4700887203216553,
+      "logps/rejected": -2.0618722438812256,
+      "loss": 1.0386,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -2.9401774406433105,
+      "rewards/margins": 1.183566927909851,
+      "rewards/rejected": -4.123744487762451,
+      "step": 385
+    },
+    {
+      "epoch": 0.816540172729652,
+      "grad_norm": 27.699401276090363,
+      "learning_rate": 5.885383207096832e-08,
+      "logits/chosen": -0.8817920684814453,
+      "logits/rejected": -0.9167042970657349,
+      "logps/chosen": -1.5808578729629517,
+      "logps/rejected": -2.0726354122161865,
+      "loss": 1.0164,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -3.1617157459259033,
+      "rewards/margins": 0.9835556149482727,
+      "rewards/rejected": -4.145270824432373,
+      "step": 390
+    },
+    {
+      "epoch": 0.8270086364825961,
+      "grad_norm": 22.291806094067294,
+      "learning_rate": 5.2482500845047165e-08,
+      "logits/chosen": -0.8046171069145203,
+      "logits/rejected": -0.8632856607437134,
+      "logps/chosen": -1.474746823310852,
+      "logps/rejected": -2.074794292449951,
+      "loss": 1.0014,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -2.949493646621704,
+      "rewards/margins": 1.2000950574874878,
+      "rewards/rejected": -4.149588584899902,
+      "step": 395
+    },
+    {
+      "epoch": 0.8374771002355405,
+      "grad_norm": 32.14293789219742,
+      "learning_rate": 4.644297433686162e-08,
+      "logits/chosen": -0.8459577560424805,
+      "logits/rejected": -0.8775212168693542,
+      "logps/chosen": -1.5837218761444092,
+      "logps/rejected": -2.0384469032287598,
+      "loss": 1.0682,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -3.1674437522888184,
+      "rewards/margins": 0.9094497561454773,
+      "rewards/rejected": -4.0768938064575195,
+      "step": 400
+    },
+    {
+      "epoch": 0.8374771002355405,
+      "eval_logits/chosen": -0.9671933650970459,
+      "eval_logits/rejected": -0.9966414570808411,
+      "eval_logps/chosen": -1.536142349243164,
+      "eval_logps/rejected": -2.0912911891937256,
+      "eval_loss": 0.9954066276550293,
+      "eval_rewards/accuracies": 0.7279999852180481,
+      "eval_rewards/chosen": -3.072284698486328,
+      "eval_rewards/margins": 1.1102983951568604,
+      "eval_rewards/rejected": -4.182582378387451,
+      "eval_runtime": 45.9263,
+      "eval_samples_per_second": 43.548,
+      "eval_steps_per_second": 2.722,
+      "step": 400
+    },
+    {
+      "epoch": 0.8479455639884846,
+      "grad_norm": 23.581025931041157,
+      "learning_rate": 4.074334871494558e-08,
+      "logits/chosen": -0.8318978548049927,
+      "logits/rejected": -0.9007453918457031,
+      "logps/chosen": -1.597597360610962,
+      "logps/rejected": -2.2467799186706543,
+      "loss": 0.9898,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -3.195194721221924,
+      "rewards/margins": 1.2983646392822266,
+      "rewards/rejected": -4.493559837341309,
+      "step": 405
+    },
+    {
+      "epoch": 0.8584140277414289,
+      "grad_norm": 37.34203846776795,
+      "learning_rate": 3.5391264500382e-08,
+      "logits/chosen": -0.8569322824478149,
+      "logits/rejected": -0.8944110870361328,
+      "logps/chosen": -1.6689296960830688,
+      "logps/rejected": -2.2536518573760986,
+      "loss": 0.9821,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -3.3378593921661377,
+      "rewards/margins": 1.16944420337677,
+      "rewards/rejected": -4.507303714752197,
+      "step": 410
+    },
+    {
+      "epoch": 0.8688824914943732,
+      "grad_norm": 25.448649440851888,
+      "learning_rate": 3.0393896324452226e-08,
+      "logits/chosen": -0.8548834919929504,
+      "logits/rejected": -0.8898690938949585,
+      "logps/chosen": -1.6892175674438477,
+      "logps/rejected": -2.1383655071258545,
+      "loss": 1.0282,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": -3.3784351348876953,
+      "rewards/margins": 0.8982963562011719,
+      "rewards/rejected": -4.276731014251709,
+      "step": 415
+    },
+    {
+      "epoch": 0.8793509552473174,
+      "grad_norm": 22.81456603203954,
+      "learning_rate": 2.5757943310825026e-08,
+      "logits/chosen": -0.8120086789131165,
+      "logits/rejected": -0.8377026319503784,
+      "logps/chosen": -1.5306228399276733,
+      "logps/rejected": -2.244910478591919,
+      "loss": 0.9802,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -3.0612456798553467,
+      "rewards/margins": 1.428574800491333,
+      "rewards/rejected": -4.489820957183838,
+      "step": 420
+    },
+    {
+      "epoch": 0.8898194190002617,
+      "grad_norm": 37.81119467654555,
+      "learning_rate": 2.148962009517823e-08,
+      "logits/chosen": -0.8621734380722046,
+      "logits/rejected": -0.9295539855957031,
+      "logps/chosen": -1.594923973083496,
+      "logps/rejected": -2.202113389968872,
+      "loss": 0.9772,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -3.189847946166992,
+      "rewards/margins": 1.2143787145614624,
+      "rewards/rejected": -4.404226779937744,
+      "step": 425
+    },
+    {
+      "epoch": 0.9002878827532059,
+      "grad_norm": 23.35609170503276,
+      "learning_rate": 1.759464849429082e-08,
+      "logits/chosen": -0.8409427404403687,
+      "logits/rejected": -0.8790140151977539,
+      "logps/chosen": -1.6252171993255615,
+      "logps/rejected": -2.1690993309020996,
+      "loss": 0.9766,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -3.250434398651123,
+      "rewards/margins": 1.087764024734497,
+      "rewards/rejected": -4.338198661804199,
+      "step": 430
+    },
+    {
+      "epoch": 0.9107563465061502,
+      "grad_norm": 42.92976213914578,
+      "learning_rate": 1.4078249835774169e-08,
+      "logits/chosen": -0.8287452459335327,
+      "logits/rejected": -0.8296720385551453,
+      "logps/chosen": -1.493123173713684,
+      "logps/rejected": -2.055771827697754,
+      "loss": 1.0029,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -2.986246347427368,
+      "rewards/margins": 1.1252974271774292,
+      "rewards/rejected": -4.111543655395508,
+      "step": 435
+    },
+    {
+      "epoch": 0.9212248102590945,
+      "grad_norm": 32.7360124305529,
+      "learning_rate": 1.0945137958723705e-08,
+      "logits/chosen": -0.8666203618049622,
+      "logits/rejected": -0.9023343920707703,
+      "logps/chosen": -1.6795040369033813,
+      "logps/rejected": -2.055238962173462,
+      "loss": 1.0619,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -3.3590080738067627,
+      "rewards/margins": 0.7514694929122925,
+      "rewards/rejected": -4.110477924346924,
+      "step": 440
+    },
+    {
+      "epoch": 0.9316932740120387,
+      "grad_norm": 25.809975837885126,
+      "learning_rate": 8.19951289467482e-09,
+      "logits/chosen": -0.8226273655891418,
+      "logits/rejected": -0.8915680646896362,
+      "logps/chosen": -1.6063209772109985,
+      "logps/rejected": -2.2188549041748047,
+      "loss": 1.0036,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -3.212641954421997,
+      "rewards/margins": 1.2250680923461914,
+      "rewards/rejected": -4.437709808349609,
+      "step": 445
+    },
+    {
+      "epoch": 0.942161737764983,
+      "grad_norm": 27.907394126837357,
+      "learning_rate": 5.84505523733293e-09,
+      "logits/chosen": -0.8590003848075867,
+      "logits/rejected": -0.9254142642021179,
+      "logps/chosen": -1.5489723682403564,
+      "logps/rejected": -2.138707160949707,
+      "loss": 1.0026,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -3.097944736480713,
+      "rewards/margins": 1.1794699430465698,
+      "rewards/rejected": -4.277414321899414,
+      "step": 450
+    },
+    {
+      "epoch": 0.9526302015179272,
+      "grad_norm": 26.194546776590737,
+      "learning_rate": 3.8849212086261466e-09,
+      "logits/chosen": -0.8426074981689453,
+      "logits/rejected": -0.8449162244796753,
+      "logps/chosen": -1.5749680995941162,
+      "logps/rejected": -2.065624475479126,
+      "loss": 1.0628,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": -3.1499361991882324,
+      "rewards/margins": 0.9813130497932434,
+      "rewards/rejected": -4.131248950958252,
+      "step": 455
+    },
+    {
+      "epoch": 0.9630986652708715,
+      "grad_norm": 28.647656191366522,
+      "learning_rate": 2.3217384276938756e-09,
+      "logits/chosen": -0.7687999606132507,
+      "logits/rejected": -0.8947674036026001,
+      "logps/chosen": -1.4748101234436035,
+      "logps/rejected": -2.2467246055603027,
+      "loss": 1.0081,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -2.949620246887207,
+      "rewards/margins": 1.5438289642333984,
+      "rewards/rejected": -4.4934492111206055,
+      "step": 460
+    },
+    {
+      "epoch": 0.9735671290238157,
+      "grad_norm": 25.297804062883948,
+      "learning_rate": 1.1576023884836472e-09,
+      "logits/chosen": -0.8351796269416809,
+      "logits/rejected": -0.8887630701065063,
+      "logps/chosen": -1.5146936178207397,
+      "logps/rejected": -2.2188751697540283,
+      "loss": 0.9987,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -3.0293872356414795,
+      "rewards/margins": 1.4083633422851562,
+      "rewards/rejected": -4.437750339508057,
+      "step": 465
+    },
+    {
+      "epoch": 0.98403559277676,
+      "grad_norm": 19.986270660762962,
+      "learning_rate": 3.940736506780395e-10,
+      "logits/chosen": -0.7743644118309021,
+      "logits/rejected": -0.788620114326477,
+      "logps/chosen": -1.4425890445709229,
+      "logps/rejected": -2.27103853225708,
+      "loss": 1.0166,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -2.8851780891418457,
+      "rewards/margins": 1.6568992137908936,
+      "rewards/rejected": -4.54207706451416,
+      "step": 470
+    },
+    {
+      "epoch": 0.9945040565297043,
+      "grad_norm": 26.273630707088135,
+      "learning_rate": 3.2175747716822744e-11,
+      "logits/chosen": -0.8468500971794128,
+      "logits/rejected": -0.9172460436820984,
+      "logps/chosen": -1.5344510078430176,
+      "logps/rejected": -2.111969470977783,
+      "loss": 0.9858,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -3.068902015686035,
+      "rewards/margins": 1.1550369262695312,
+      "rewards/rejected": -4.223938941955566,
+      "step": 475
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 477,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 225,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a607a246bbc593a5988f23dce619729a68899735b48845a1171f042ca7b690e0
+size 7288

zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+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 tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        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_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)