Upload model with optimizer states

.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

README.md

@@ -0,0 +1,12 @@
+# Llama-3.1-8B Math Reasoning Model
+
+This is a fine-tuned Llama-3.1-8B model specialized for mathematical reasoning tasks.
+
+## Model Details
+- Base model: Llama-3.1-8B
+- Training dataset: tulu3_mixture_math_reasoning
+- Learning rate: 5e-06
+- Effective batch size: 128
+
+## Optimizer States
+This repository includes optimizer state files that can be used to continue training.

config.json

@@ -0,0 +1,35 @@
+{
+  "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": 131072,
+  "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": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.1"
+}

latest

@@ -0,0 +1 @@
+global_step2611

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd5acd6e64a858c03f4f6ea113648840e460f46d5490bf86658c2c0d270d04d
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed0a9fe97913ee2b744383007af15b2fccc3621fbcdd6df7d6abe5dd4a2cf5a
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71833cfaa3c89f5f666ed45590ad4deb7adcf7eaeca0697dae091f16e8261c8a
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a413f4ba2f4d6e40445ca4f5645426a4ea8563bbe0314788abc22cb1b530ea38
+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"
+  }
+}

optimizer_states/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a78efc0f0c86390162f96d75c96b8b52b99caa192991a70c3364a444d60180
+size 48181576422

optimizer_states/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c1050afebe62b89eb89a77726d937696d26ca1b40aebc303f014014274c4f21
+size 48181576422

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4
+size 14512

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6
+size 14512

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16f961c3f197fbf3216e525b1ca804e744dad807f640db5df9896d40ce12ae0
+size 1064

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "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": "<|end_of_text|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2066 @@
+{
+  "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": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "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": "<|eom_id|>",
+      "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": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}

trainer_state.json

@@ -0,0 +1,1861 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998683627921449,
+  "eval_steps": 500,
+  "global_step": 2611,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0038294460466953076,
+      "grad_norm": 5.426074325401742,
+      "learning_rate": 5.69620253164557e-07,
+      "loss": 0.596,
+      "step": 10
+    },
+    {
+      "epoch": 0.007658892093390615,
+      "grad_norm": 1.7300049140411797,
+      "learning_rate": 1.2025316455696204e-06,
+      "loss": 0.4935,
+      "step": 20
+    },
+    {
+      "epoch": 0.011488338140085923,
+      "grad_norm": 1.0566614384820672,
+      "learning_rate": 1.8354430379746838e-06,
+      "loss": 0.4179,
+      "step": 30
+    },
+    {
+      "epoch": 0.01531778418678123,
+      "grad_norm": 1.1239284474445808,
+      "learning_rate": 2.4683544303797473e-06,
+      "loss": 0.3786,
+      "step": 40
+    },
+    {
+      "epoch": 0.019147230233476538,
+      "grad_norm": 0.8236458977275282,
+      "learning_rate": 3.10126582278481e-06,
+      "loss": 0.3645,
+      "step": 50
+    },
+    {
+      "epoch": 0.022976676280171845,
+      "grad_norm": 0.939010895376297,
+      "learning_rate": 3.7341772151898737e-06,
+      "loss": 0.3472,
+      "step": 60
+    },
+    {
+      "epoch": 0.026806122326867153,
+      "grad_norm": 0.7558771041067948,
+      "learning_rate": 4.367088607594937e-06,
+      "loss": 0.3234,
+      "step": 70
+    },
+    {
+      "epoch": 0.03063556837356246,
+      "grad_norm": 0.8507599742006083,
+      "learning_rate": 5e-06,
+      "loss": 0.3273,
+      "step": 80
+    },
+    {
+      "epoch": 0.03446501442025777,
+      "grad_norm": 0.9322867483149297,
+      "learning_rate": 4.999807568225742e-06,
+      "loss": 0.3269,
+      "step": 90
+    },
+    {
+      "epoch": 0.038294460466953076,
+      "grad_norm": 0.8060180679646447,
+      "learning_rate": 4.999230302526956e-06,
+      "loss": 0.338,
+      "step": 100
+    },
+    {
+      "epoch": 0.04212390651364838,
+      "grad_norm": 0.8178741447804784,
+      "learning_rate": 4.998268291771053e-06,
+      "loss": 0.3232,
+      "step": 110
+    },
+    {
+      "epoch": 0.04595335256034369,
+      "grad_norm": 0.8264908445738317,
+      "learning_rate": 4.9969216840551815e-06,
+      "loss": 0.3239,
+      "step": 120
+    },
+    {
+      "epoch": 0.049782798607039,
+      "grad_norm": 0.8185737508740193,
+      "learning_rate": 4.995190686683432e-06,
+      "loss": 0.3164,
+      "step": 130
+    },
+    {
+      "epoch": 0.053612244653734306,
+      "grad_norm": 0.8016123974519153,
+      "learning_rate": 4.9930755661349215e-06,
+      "loss": 0.3227,
+      "step": 140
+    },
+    {
+      "epoch": 0.057441690700429614,
+      "grad_norm": 0.8304543418674754,
+      "learning_rate": 4.990576648022768e-06,
+      "loss": 0.3136,
+      "step": 150
+    },
+    {
+      "epoch": 0.06127113674712492,
+      "grad_norm": 0.7555621229293721,
+      "learning_rate": 4.98769431704397e-06,
+      "loss": 0.3033,
+      "step": 160
+    },
+    {
+      "epoch": 0.06510058279382024,
+      "grad_norm": 0.8637646507692361,
+      "learning_rate": 4.984429016920178e-06,
+      "loss": 0.3231,
+      "step": 170
+    },
+    {
+      "epoch": 0.06893002884051554,
+      "grad_norm": 0.7476252312804286,
+      "learning_rate": 4.980781250329389e-06,
+      "loss": 0.309,
+      "step": 180
+    },
+    {
+      "epoch": 0.07275947488721085,
+      "grad_norm": 0.8589580099130042,
+      "learning_rate": 4.976751578828562e-06,
+      "loss": 0.3122,
+      "step": 190
+    },
+    {
+      "epoch": 0.07658892093390615,
+      "grad_norm": 0.8355945240964501,
+      "learning_rate": 4.9723406227671645e-06,
+      "loss": 0.3109,
+      "step": 200
+    },
+    {
+      "epoch": 0.08041836698060147,
+      "grad_norm": 0.7902874463038752,
+      "learning_rate": 4.967549061191679e-06,
+      "loss": 0.3118,
+      "step": 210
+    },
+    {
+      "epoch": 0.08424781302729677,
+      "grad_norm": 0.8876153745394134,
+      "learning_rate": 4.962377631741061e-06,
+      "loss": 0.306,
+      "step": 220
+    },
+    {
+      "epoch": 0.08807725907399208,
+      "grad_norm": 0.866679126237035,
+      "learning_rate": 4.956827130533185e-06,
+      "loss": 0.3135,
+      "step": 230
+    },
+    {
+      "epoch": 0.09190670512068738,
+      "grad_norm": 0.8629644307536233,
+      "learning_rate": 4.95089841204229e-06,
+      "loss": 0.302,
+      "step": 240
+    },
+    {
+      "epoch": 0.0957361511673827,
+      "grad_norm": 0.7338565663547403,
+      "learning_rate": 4.9445923889674285e-06,
+      "loss": 0.303,
+      "step": 250
+    },
+    {
+      "epoch": 0.099565597214078,
+      "grad_norm": 0.7305791719581167,
+      "learning_rate": 4.937910032091968e-06,
+      "loss": 0.3009,
+      "step": 260
+    },
+    {
+      "epoch": 0.10339504326077331,
+      "grad_norm": 0.6695669065750437,
+      "learning_rate": 4.9308523701341415e-06,
+      "loss": 0.305,
+      "step": 270
+    },
+    {
+      "epoch": 0.10722448930746861,
+      "grad_norm": 0.7251397159069465,
+      "learning_rate": 4.923420489588677e-06,
+      "loss": 0.3005,
+      "step": 280
+    },
+    {
+      "epoch": 0.11105393535416393,
+      "grad_norm": 0.7899848638296046,
+      "learning_rate": 4.915615534559545e-06,
+      "loss": 0.3036,
+      "step": 290
+    },
+    {
+      "epoch": 0.11488338140085923,
+      "grad_norm": 0.8159662777762657,
+      "learning_rate": 4.907438706583818e-06,
+      "loss": 0.2997,
+      "step": 300
+    },
+    {
+      "epoch": 0.11871282744755454,
+      "grad_norm": 0.7496451104541622,
+      "learning_rate": 4.898891264446709e-06,
+      "loss": 0.2984,
+      "step": 310
+    },
+    {
+      "epoch": 0.12254227349424984,
+      "grad_norm": 0.7090938182919049,
+      "learning_rate": 4.889974523987784e-06,
+      "loss": 0.3037,
+      "step": 320
+    },
+    {
+      "epoch": 0.12637171954094514,
+      "grad_norm": 0.7534479964128541,
+      "learning_rate": 4.880689857898392e-06,
+      "loss": 0.2907,
+      "step": 330
+    },
+    {
+      "epoch": 0.13020116558764047,
+      "grad_norm": 0.7967215720335111,
+      "learning_rate": 4.871038695510347e-06,
+      "loss": 0.3035,
+      "step": 340
+    },
+    {
+      "epoch": 0.13403061163433577,
+      "grad_norm": 0.8589787634591548,
+      "learning_rate": 4.861022522575892e-06,
+      "loss": 0.2917,
+      "step": 350
+    },
+    {
+      "epoch": 0.13786005768103107,
+      "grad_norm": 0.77962150007173,
+      "learning_rate": 4.850642881038969e-06,
+      "loss": 0.3019,
+      "step": 360
+    },
+    {
+      "epoch": 0.14168950372772637,
+      "grad_norm": 0.6913568705438217,
+      "learning_rate": 4.839901368797849e-06,
+      "loss": 0.2987,
+      "step": 370
+    },
+    {
+      "epoch": 0.1455189497744217,
+      "grad_norm": 0.7245824514430528,
+      "learning_rate": 4.828799639459139e-06,
+      "loss": 0.2996,
+      "step": 380
+    },
+    {
+      "epoch": 0.149348395821117,
+      "grad_norm": 0.7331355223021702,
+      "learning_rate": 4.817339402083217e-06,
+      "loss": 0.2958,
+      "step": 390
+    },
+    {
+      "epoch": 0.1531778418678123,
+      "grad_norm": 0.684066179750134,
+      "learning_rate": 4.805522420921132e-06,
+      "loss": 0.2923,
+      "step": 400
+    },
+    {
+      "epoch": 0.1570072879145076,
+      "grad_norm": 0.7273451737034062,
+      "learning_rate": 4.793350515143007e-06,
+      "loss": 0.2955,
+      "step": 410
+    },
+    {
+      "epoch": 0.16083673396120293,
+      "grad_norm": 0.6922184014896344,
+      "learning_rate": 4.780825558557981e-06,
+      "loss": 0.3021,
+      "step": 420
+    },
+    {
+      "epoch": 0.16466618000789823,
+      "grad_norm": 0.7901617539245519,
+      "learning_rate": 4.767949479325749e-06,
+      "loss": 0.3004,
+      "step": 430
+    },
+    {
+      "epoch": 0.16849562605459353,
+      "grad_norm": 0.7269661753924206,
+      "learning_rate": 4.754724259659727e-06,
+      "loss": 0.2966,
+      "step": 440
+    },
+    {
+      "epoch": 0.17232507210128883,
+      "grad_norm": 0.7893201123959417,
+      "learning_rate": 4.741151935521906e-06,
+      "loss": 0.2985,
+      "step": 450
+    },
+    {
+      "epoch": 0.17615451814798416,
+      "grad_norm": 0.6946007030633581,
+      "learning_rate": 4.727234596309417e-06,
+      "loss": 0.3036,
+      "step": 460
+    },
+    {
+      "epoch": 0.17998396419467946,
+      "grad_norm": 0.7322226198234377,
+      "learning_rate": 4.71297438453288e-06,
+      "loss": 0.3001,
+      "step": 470
+    },
+    {
+      "epoch": 0.18381341024137476,
+      "grad_norm": 0.6823377208042828,
+      "learning_rate": 4.69837349548658e-06,
+      "loss": 0.2925,
+      "step": 480
+    },
+    {
+      "epoch": 0.1876428562880701,
+      "grad_norm": 0.7135771256714908,
+      "learning_rate": 4.683434176910503e-06,
+      "loss": 0.2939,
+      "step": 490
+    },
+    {
+      "epoch": 0.1914723023347654,
+      "grad_norm": 0.691020843307318,
+      "learning_rate": 4.668158728644315e-06,
+      "loss": 0.2804,
+      "step": 500
+    },
+    {
+      "epoch": 0.1953017483814607,
+      "grad_norm": 0.6612550303473294,
+      "learning_rate": 4.652549502273305e-06,
+      "loss": 0.2922,
+      "step": 510
+    },
+    {
+      "epoch": 0.199131194428156,
+      "grad_norm": 0.7364276724142655,
+      "learning_rate": 4.636608900766372e-06,
+      "loss": 0.2891,
+      "step": 520
+    },
+    {
+      "epoch": 0.20296064047485132,
+      "grad_norm": 0.6721354413833053,
+      "learning_rate": 4.620339378106103e-06,
+      "loss": 0.2809,
+      "step": 530
+    },
+    {
+      "epoch": 0.20679008652154662,
+      "grad_norm": 0.6653652380595567,
+      "learning_rate": 4.6037434389109855e-06,
+      "loss": 0.2983,
+      "step": 540
+    },
+    {
+      "epoch": 0.21061953256824192,
+      "grad_norm": 0.7449501156668481,
+      "learning_rate": 4.586823638049841e-06,
+      "loss": 0.2903,
+      "step": 550
+    },
+    {
+      "epoch": 0.21444897861493722,
+      "grad_norm": 0.715508013931221,
+      "learning_rate": 4.569582580248509e-06,
+      "loss": 0.2923,
+      "step": 560
+    },
+    {
+      "epoch": 0.21827842466163255,
+      "grad_norm": 0.6641963861933619,
+      "learning_rate": 4.552022919688861e-06,
+      "loss": 0.2924,
+      "step": 570
+    },
+    {
+      "epoch": 0.22210787070832785,
+      "grad_norm": 0.7113518461330477,
+      "learning_rate": 4.534147359600211e-06,
+      "loss": 0.2819,
+      "step": 580
+    },
+    {
+      "epoch": 0.22593731675502315,
+      "grad_norm": 0.7089839605701392,
+      "learning_rate": 4.515958651843151e-06,
+      "loss": 0.2939,
+      "step": 590
+    },
+    {
+      "epoch": 0.22976676280171845,
+      "grad_norm": 0.677078858734863,
+      "learning_rate": 4.497459596485924e-06,
+      "loss": 0.2835,
+      "step": 600
+    },
+    {
+      "epoch": 0.23359620884841378,
+      "grad_norm": 0.7703623199956556,
+      "learning_rate": 4.478653041373371e-06,
+      "loss": 0.2854,
+      "step": 610
+    },
+    {
+      "epoch": 0.23742565489510908,
+      "grad_norm": 0.6407221872558565,
+      "learning_rate": 4.459541881688501e-06,
+      "loss": 0.2872,
+      "step": 620
+    },
+    {
+      "epoch": 0.24125510094180438,
+      "grad_norm": 0.7625245912179776,
+      "learning_rate": 4.440129059506808e-06,
+      "loss": 0.2852,
+      "step": 630
+    },
+    {
+      "epoch": 0.24508454698849969,
+      "grad_norm": 0.6533872161632752,
+      "learning_rate": 4.420417563343347e-06,
+      "loss": 0.2883,
+      "step": 640
+    },
+    {
+      "epoch": 0.248913993035195,
+      "grad_norm": 0.6347508565680315,
+      "learning_rate": 4.40041042769266e-06,
+      "loss": 0.2818,
+      "step": 650
+    },
+    {
+      "epoch": 0.2527434390818903,
+      "grad_norm": 0.6956608959261769,
+      "learning_rate": 4.380110732561636e-06,
+      "loss": 0.2858,
+      "step": 660
+    },
+    {
+      "epoch": 0.2565728851285856,
+      "grad_norm": 0.7174236888577228,
+      "learning_rate": 4.3595216029953575e-06,
+      "loss": 0.2948,
+      "step": 670
+    },
+    {
+      "epoch": 0.26040233117528094,
+      "grad_norm": 0.6538209955447881,
+      "learning_rate": 4.338646208596009e-06,
+      "loss": 0.2901,
+      "step": 680
+    },
+    {
+      "epoch": 0.2642317772219762,
+      "grad_norm": 0.6777945072272051,
+      "learning_rate": 4.317487763034936e-06,
+      "loss": 0.2848,
+      "step": 690
+    },
+    {
+      "epoch": 0.26806122326867154,
+      "grad_norm": 0.6915180680337352,
+      "learning_rate": 4.296049523557917e-06,
+      "loss": 0.294,
+      "step": 700
+    },
+    {
+      "epoch": 0.2718906693153669,
+      "grad_norm": 0.6811198761407046,
+      "learning_rate": 4.274334790483718e-06,
+      "loss": 0.2925,
+      "step": 710
+    },
+    {
+      "epoch": 0.27572011536206215,
+      "grad_norm": 0.6682149146681646,
+      "learning_rate": 4.2523469066960295e-06,
+      "loss": 0.2832,
+      "step": 720
+    },
+    {
+      "epoch": 0.2795495614087575,
+      "grad_norm": 0.6343382096231662,
+      "learning_rate": 4.230089257128842e-06,
+      "loss": 0.2865,
+      "step": 730
+    },
+    {
+      "epoch": 0.28337900745545275,
+      "grad_norm": 0.7142478024296977,
+      "learning_rate": 4.207565268245356e-06,
+      "loss": 0.2852,
+      "step": 740
+    },
+    {
+      "epoch": 0.2872084535021481,
+      "grad_norm": 0.6678411720839094,
+      "learning_rate": 4.184778407510484e-06,
+      "loss": 0.2924,
+      "step": 750
+    },
+    {
+      "epoch": 0.2910378995488434,
+      "grad_norm": 0.7689563352484293,
+      "learning_rate": 4.16173218285706e-06,
+      "loss": 0.2901,
+      "step": 760
+    },
+    {
+      "epoch": 0.2948673455955387,
+      "grad_norm": 0.749864633773232,
+      "learning_rate": 4.138430142145805e-06,
+      "loss": 0.2839,
+      "step": 770
+    },
+    {
+      "epoch": 0.298696791642234,
+      "grad_norm": 0.6699595192464245,
+      "learning_rate": 4.114875872619147e-06,
+      "loss": 0.2951,
+      "step": 780
+    },
+    {
+      "epoch": 0.30252623768892933,
+      "grad_norm": 0.691214596956005,
+      "learning_rate": 4.091073000348989e-06,
+      "loss": 0.2874,
+      "step": 790
+    },
+    {
+      "epoch": 0.3063556837356246,
+      "grad_norm": 0.6554956219244137,
+      "learning_rate": 4.067025189678485e-06,
+      "loss": 0.286,
+      "step": 800
+    },
+    {
+      "epoch": 0.31018512978231993,
+      "grad_norm": 0.6954151666813602,
+      "learning_rate": 4.042736142657936e-06,
+      "loss": 0.2834,
+      "step": 810
+    },
+    {
+      "epoch": 0.3140145758290152,
+      "grad_norm": 0.7196715435903528,
+      "learning_rate": 4.018209598474869e-06,
+      "loss": 0.284,
+      "step": 820
+    },
+    {
+      "epoch": 0.31784402187571054,
+      "grad_norm": 0.7723328668264622,
+      "learning_rate": 3.9934493328784185e-06,
+      "loss": 0.2777,
+      "step": 830
+    },
+    {
+      "epoch": 0.32167346792240586,
+      "grad_norm": 0.6919247319317805,
+      "learning_rate": 3.9684591575980546e-06,
+      "loss": 0.2893,
+      "step": 840
+    },
+    {
+      "epoch": 0.32550291396910114,
+      "grad_norm": 0.612288507127871,
+      "learning_rate": 3.943242919756792e-06,
+      "loss": 0.2891,
+      "step": 850
+    },
+    {
+      "epoch": 0.32933236001579647,
+      "grad_norm": 0.7304106009933916,
+      "learning_rate": 3.917804501278942e-06,
+      "loss": 0.2838,
+      "step": 860
+    },
+    {
+      "epoch": 0.3331618060624918,
+      "grad_norm": 0.6961425637816675,
+      "learning_rate": 3.892147818292505e-06,
+      "loss": 0.2818,
+      "step": 870
+    },
+    {
+      "epoch": 0.33699125210918707,
+      "grad_norm": 0.6415090586497654,
+      "learning_rate": 3.866276820526305e-06,
+      "loss": 0.2826,
+      "step": 880
+    },
+    {
+      "epoch": 0.3408206981558824,
+      "grad_norm": 0.7319097656364029,
+      "learning_rate": 3.840195490701943e-06,
+      "loss": 0.2797,
+      "step": 890
+    },
+    {
+      "epoch": 0.34465014420257767,
+      "grad_norm": 0.6643906637801983,
+      "learning_rate": 3.8139078439206755e-06,
+      "loss": 0.2823,
+      "step": 900
+    },
+    {
+      "epoch": 0.348479590249273,
+      "grad_norm": 0.651442028320178,
+      "learning_rate": 3.787417927045315e-06,
+      "loss": 0.2845,
+      "step": 910
+    },
+    {
+      "epoch": 0.3523090362959683,
+      "grad_norm": 0.703399820267242,
+      "learning_rate": 3.760729818077224e-06,
+      "loss": 0.2782,
+      "step": 920
+    },
+    {
+      "epoch": 0.3561384823426636,
+      "grad_norm": 0.6339374061657803,
+      "learning_rate": 3.7338476255285295e-06,
+      "loss": 0.2809,
+      "step": 930
+    },
+    {
+      "epoch": 0.3599679283893589,
+      "grad_norm": 0.6650804278367294,
+      "learning_rate": 3.7067754877896388e-06,
+      "loss": 0.288,
+      "step": 940
+    },
+    {
+      "epoch": 0.36379737443605425,
+      "grad_norm": 0.6645625939049019,
+      "learning_rate": 3.6795175724921506e-06,
+      "loss": 0.2821,
+      "step": 950
+    },
+    {
+      "epoch": 0.36762682048274953,
+      "grad_norm": 0.6819651400048093,
+      "learning_rate": 3.652078075867267e-06,
+      "loss": 0.2759,
+      "step": 960
+    },
+    {
+      "epoch": 0.37145626652944486,
+      "grad_norm": 0.6767426872168217,
+      "learning_rate": 3.624461222099804e-06,
+      "loss": 0.28,
+      "step": 970
+    },
+    {
+      "epoch": 0.3752857125761402,
+      "grad_norm": 0.7310278431962209,
+      "learning_rate": 3.596671262677898e-06,
+      "loss": 0.2883,
+      "step": 980
+    },
+    {
+      "epoch": 0.37911515862283546,
+      "grad_norm": 0.6791506792289325,
+      "learning_rate": 3.5687124757385084e-06,
+      "loss": 0.2885,
+      "step": 990
+    },
+    {
+      "epoch": 0.3829446046695308,
+      "grad_norm": 0.7086896739862765,
+      "learning_rate": 3.5405891654088154e-06,
+      "loss": 0.2815,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38677405071622606,
+      "grad_norm": 0.6280354477468107,
+      "learning_rate": 3.5123056611436224e-06,
+      "loss": 0.2807,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3906034967629214,
+      "grad_norm": 0.6538192887744636,
+      "learning_rate": 3.4838663170588573e-06,
+      "loss": 0.2723,
+      "step": 1020
+    },
+    {
+      "epoch": 0.3944329428096167,
+      "grad_norm": 0.6999366929435851,
+      "learning_rate": 3.455275511261272e-06,
+      "loss": 0.2804,
+      "step": 1030
+    },
+    {
+      "epoch": 0.398262388856312,
+      "grad_norm": 0.6406720215436563,
+      "learning_rate": 3.4265376451744564e-06,
+      "loss": 0.2776,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4020918349030073,
+      "grad_norm": 0.6809060571142534,
+      "learning_rate": 3.3976571428612583e-06,
+      "loss": 0.2823,
+      "step": 1050
+    },
+    {
+      "epoch": 0.40592128094970265,
+      "grad_norm": 0.6506142391402524,
+      "learning_rate": 3.3686384503427177e-06,
+      "loss": 0.2785,
+      "step": 1060
+    },
+    {
+      "epoch": 0.4097507269963979,
+      "grad_norm": 0.6623408933951855,
+      "learning_rate": 3.339486034913627e-06,
+      "loss": 0.2781,
+      "step": 1070
+    },
+    {
+      "epoch": 0.41358017304309325,
+      "grad_norm": 0.675859964827601,
+      "learning_rate": 3.310204384454805e-06,
+      "loss": 0.2776,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4174096190897885,
+      "grad_norm": 0.7354171342985883,
+      "learning_rate": 3.280798006742213e-06,
+      "loss": 0.2929,
+      "step": 1090
+    },
+    {
+      "epoch": 0.42123906513648385,
+      "grad_norm": 0.6457062459707484,
+      "learning_rate": 3.2512714287530007e-06,
+      "loss": 0.2743,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4250685111831792,
+      "grad_norm": 0.641329871481826,
+      "learning_rate": 3.2216291959686007e-06,
+      "loss": 0.2737,
+      "step": 1110
+    },
+    {
+      "epoch": 0.42889795722987445,
+      "grad_norm": 0.6566421664911357,
+      "learning_rate": 3.191875871674971e-06,
+      "loss": 0.2838,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4327274032765698,
+      "grad_norm": 0.6027701960697498,
+      "learning_rate": 3.162016036260098e-06,
+      "loss": 0.2752,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4365568493232651,
+      "grad_norm": 0.648907215118306,
+      "learning_rate": 3.1320542865088695e-06,
+      "loss": 0.2667,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4403862953699604,
+      "grad_norm": 0.6077801768682932,
+      "learning_rate": 3.1019952348954163e-06,
+      "loss": 0.2747,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4442157414166557,
+      "grad_norm": 0.6576708995713357,
+      "learning_rate": 3.071843508873046e-06,
+      "loss": 0.2836,
+      "step": 1160
+    },
+    {
+      "epoch": 0.448045187463351,
+      "grad_norm": 0.695646974082748,
+      "learning_rate": 3.0416037501618676e-06,
+      "loss": 0.2732,
+      "step": 1170
+    },
+    {
+      "epoch": 0.4518746335100463,
+      "grad_norm": 0.616879255204133,
+      "learning_rate": 3.0112806140342176e-06,
+      "loss": 0.2759,
+      "step": 1180
+    },
+    {
+      "epoch": 0.45570407955674164,
+      "grad_norm": 0.6008817125153927,
+      "learning_rate": 2.9808787685980054e-06,
+      "loss": 0.2769,
+      "step": 1190
+    },
+    {
+      "epoch": 0.4595335256034369,
+      "grad_norm": 0.5972779982979275,
+      "learning_rate": 2.9504028940780777e-06,
+      "loss": 0.2836,
+      "step": 1200
+    },
+    {
+      "epoch": 0.46336297165013224,
+      "grad_norm": 0.6541064777899037,
+      "learning_rate": 2.9198576820957188e-06,
+      "loss": 0.2678,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46719241769682757,
+      "grad_norm": 0.7461980100750918,
+      "learning_rate": 2.8892478349463987e-06,
+      "loss": 0.279,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47102186374352284,
+      "grad_norm": 0.697749095404112,
+      "learning_rate": 2.8585780648758745e-06,
+      "loss": 0.2774,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47485130979021817,
+      "grad_norm": 0.6901917627087478,
+      "learning_rate": 2.827853093354763e-06,
+      "loss": 0.2731,
+      "step": 1240
+    },
+    {
+      "epoch": 0.47868075583691344,
+      "grad_norm": 0.6167921413072504,
+      "learning_rate": 2.79707765035169e-06,
+      "loss": 0.2781,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48251020188360877,
+      "grad_norm": 0.6877679962661163,
+      "learning_rate": 2.7662564736051378e-06,
+      "loss": 0.2779,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4863396479303041,
+      "grad_norm": 0.6529732798686552,
+      "learning_rate": 2.7353943078940876e-06,
+      "loss": 0.2755,
+      "step": 1270
+    },
+    {
+      "epoch": 0.49016909397699937,
+      "grad_norm": 0.573925656257561,
+      "learning_rate": 2.7044959043075815e-06,
+      "loss": 0.2781,
+      "step": 1280
+    },
+    {
+      "epoch": 0.4939985400236947,
+      "grad_norm": 0.7060010201146872,
+      "learning_rate": 2.67356601951332e-06,
+      "loss": 0.2885,
+      "step": 1290
+    },
+    {
+      "epoch": 0.49782798607039,
+      "grad_norm": 0.6706570115076154,
+      "learning_rate": 2.64260941502539e-06,
+      "loss": 0.2823,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5016574321170854,
+      "grad_norm": 0.6816750561081921,
+      "learning_rate": 2.611630856471252e-06,
+      "loss": 0.2734,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5054868781637806,
+      "grad_norm": 0.6503962781113031,
+      "learning_rate": 2.5806351128580963e-06,
+      "loss": 0.2775,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5093163242104759,
+      "grad_norm": 0.6770280496930409,
+      "learning_rate": 2.549626955838673e-06,
+      "loss": 0.2805,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5131457702571712,
+      "grad_norm": 0.6025144898257462,
+      "learning_rate": 2.5186111589767187e-06,
+      "loss": 0.2715,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5169752163038666,
+      "grad_norm": 0.6707574673231309,
+      "learning_rate": 2.487592497012089e-06,
+      "loss": 0.2763,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5208046623505619,
+      "grad_norm": 0.6063466305966893,
+      "learning_rate": 2.456575745125713e-06,
+      "loss": 0.2845,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5246341083972571,
+      "grad_norm": 0.6060316435488056,
+      "learning_rate": 2.4255656782044644e-06,
+      "loss": 0.2772,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5284635544439524,
+      "grad_norm": 0.6023582378786108,
+      "learning_rate": 2.3945670701061033e-06,
+      "loss": 0.267,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5322930004906478,
+      "grad_norm": 0.672852399998615,
+      "learning_rate": 2.3635846929243536e-06,
+      "loss": 0.2757,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5361224465373431,
+      "grad_norm": 0.671673917828738,
+      "learning_rate": 2.3326233162542655e-06,
+      "loss": 0.2772,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5399518925840384,
+      "grad_norm": 0.6908191182674716,
+      "learning_rate": 2.3016877064579564e-06,
+      "loss": 0.2752,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5437813386307337,
+      "grad_norm": 0.6483112345732687,
+      "learning_rate": 2.2707826259308493e-06,
+      "loss": 0.2773,
+      "step": 1420
+    },
+    {
+      "epoch": 0.547610784677429,
+      "grad_norm": 0.6527686650275873,
+      "learning_rate": 2.2399128323685287e-06,
+      "loss": 0.2711,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5514402307241243,
+      "grad_norm": 0.6402708780992856,
+      "learning_rate": 2.2090830780343116e-06,
+      "loss": 0.2774,
+      "step": 1440
+    },
+    {
+      "epoch": 0.5552696767708196,
+      "grad_norm": 0.7121133583105477,
+      "learning_rate": 2.178298109027659e-06,
+      "loss": 0.2789,
+      "step": 1450
+    },
+    {
+      "epoch": 0.559099122817515,
+      "grad_norm": 0.6936411537357103,
+      "learning_rate": 2.147562664553537e-06,
+      "loss": 0.2744,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5629285688642103,
+      "grad_norm": 0.6126488504445933,
+      "learning_rate": 2.116881476192834e-06,
+      "loss": 0.2698,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5667580149109055,
+      "grad_norm": 0.6045796996159061,
+      "learning_rate": 2.086259267173961e-06,
+      "loss": 0.2756,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5705874609576008,
+      "grad_norm": 0.6331045988234285,
+      "learning_rate": 2.0557007516457287e-06,
+      "loss": 0.2813,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5744169070042962,
+      "grad_norm": 0.6250063298087053,
+      "learning_rate": 2.025210633951627e-06,
+      "loss": 0.2659,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5782463530509915,
+      "grad_norm": 0.6244702166810576,
+      "learning_rate": 1.9947936079056118e-06,
+      "loss": 0.2691,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5820757990976868,
+      "grad_norm": 0.6645304037867747,
+      "learning_rate": 1.964454356069514e-06,
+      "loss": 0.2653,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5859052451443821,
+      "grad_norm": 0.6422648719414517,
+      "learning_rate": 1.934197549032183e-06,
+      "loss": 0.2753,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5897346911910774,
+      "grad_norm": 0.6796801504650317,
+      "learning_rate": 1.904027844690468e-06,
+      "loss": 0.2756,
+      "step": 1540
+    },
+    {
+      "epoch": 0.5935641372377727,
+      "grad_norm": 0.612092392514174,
+      "learning_rate": 1.8739498875321563e-06,
+      "loss": 0.2781,
+      "step": 1550
+    },
+    {
+      "epoch": 0.597393583284468,
+      "grad_norm": 0.6072776324810985,
+      "learning_rate": 1.8439683079209789e-06,
+      "loss": 0.2762,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6012230293311633,
+      "grad_norm": 0.6756861517531914,
+      "learning_rate": 1.8140877213837823e-06,
+      "loss": 0.2671,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6050524753778587,
+      "grad_norm": 0.6297494292950692,
+      "learning_rate": 1.7843127278999944e-06,
+      "loss": 0.2656,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6088819214245539,
+      "grad_norm": 0.6384980188983074,
+      "learning_rate": 1.7546479111934733e-06,
+      "loss": 0.2742,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6127113674712492,
+      "grad_norm": 0.6354445299662702,
+      "learning_rate": 1.7250978380268696e-06,
+      "loss": 0.2703,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6165408135179445,
+      "grad_norm": 0.6499360638842633,
+      "learning_rate": 1.6956670574985909e-06,
+      "loss": 0.2778,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6203702595646399,
+      "grad_norm": 0.6611350047172592,
+      "learning_rate": 1.6663601003424884e-06,
+      "loss": 0.2751,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6241997056113352,
+      "grad_norm": 0.6676095929381155,
+      "learning_rate": 1.6371814782303723e-06,
+      "loss": 0.2697,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6280291516580304,
+      "grad_norm": 0.6627616428191541,
+      "learning_rate": 1.6081356830774625e-06,
+      "loss": 0.2728,
+      "step": 1640
+    },
+    {
+      "epoch": 0.6318585977047257,
+      "grad_norm": 0.6297343768461555,
+      "learning_rate": 1.5792271863508751e-06,
+      "loss": 0.2725,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6356880437514211,
+      "grad_norm": 0.6164109978910287,
+      "learning_rate": 1.5504604383812646e-06,
+      "loss": 0.2665,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6395174897981164,
+      "grad_norm": 0.6163778395985405,
+      "learning_rate": 1.5218398676777103e-06,
+      "loss": 0.2676,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6433469358448117,
+      "grad_norm": 0.7111914438547673,
+      "learning_rate": 1.493369880245973e-06,
+      "loss": 0.2682,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6471763818915071,
+      "grad_norm": 0.5951988021270335,
+      "learning_rate": 1.4650548589102092e-06,
+      "loss": 0.2725,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6510058279382023,
+      "grad_norm": 0.615884409391351,
+      "learning_rate": 1.436899162638255e-06,
+      "loss": 0.2693,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6548352739848976,
+      "grad_norm": 0.5615244588845161,
+      "learning_rate": 1.4089071258705782e-06,
+      "loss": 0.2717,
+      "step": 1710
+    },
+    {
+      "epoch": 0.6586647200315929,
+      "grad_norm": 0.613522242640938,
+      "learning_rate": 1.3810830578530226e-06,
+      "loss": 0.2645,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6624941660782883,
+      "grad_norm": 0.6255188764708021,
+      "learning_rate": 1.3534312419734066e-06,
+      "loss": 0.2619,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6663236121249836,
+      "grad_norm": 0.6219089714484455,
+      "learning_rate": 1.3259559351021249e-06,
+      "loss": 0.2706,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6701530581716788,
+      "grad_norm": 0.7068243904113033,
+      "learning_rate": 1.2986613669368159e-06,
+      "loss": 0.2724,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6739825042183741,
+      "grad_norm": 0.6239904301630281,
+      "learning_rate": 1.2715517393512239e-06,
+      "loss": 0.2699,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6778119502650695,
+      "grad_norm": 0.636573560785032,
+      "learning_rate": 1.2446312257483358e-06,
+      "loss": 0.2606,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6816413963117648,
+      "grad_norm": 0.5822319215351535,
+      "learning_rate": 1.2179039704179119e-06,
+      "loss": 0.2671,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6854708423584601,
+      "grad_norm": 0.6414100583030806,
+      "learning_rate": 1.1913740878984818e-06,
+      "loss": 0.2728,
+      "step": 1790
+    },
+    {
+      "epoch": 0.6893002884051553,
+      "grad_norm": 0.6019132802768392,
+      "learning_rate": 1.1650456623439368e-06,
+      "loss": 0.2684,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6931297344518507,
+      "grad_norm": 0.6936171991583808,
+      "learning_rate": 1.1389227468947905e-06,
+      "loss": 0.271,
+      "step": 1810
+    },
+    {
+      "epoch": 0.696959180498546,
+      "grad_norm": 0.621045757650744,
+      "learning_rate": 1.11300936305422e-06,
+      "loss": 0.2657,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7007886265452413,
+      "grad_norm": 0.6554333537644303,
+      "learning_rate": 1.0873095000689676e-06,
+      "loss": 0.2666,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7046180725919367,
+      "grad_norm": 0.6286228416556564,
+      "learning_rate": 1.0618271143152185e-06,
+      "loss": 0.2714,
+      "step": 1840
+    },
+    {
+      "epoch": 0.708447518638632,
+      "grad_norm": 0.6221920366356362,
+      "learning_rate": 1.0365661286895364e-06,
+      "loss": 0.2672,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7122769646853272,
+      "grad_norm": 0.6038564143991549,
+      "learning_rate": 1.011530432004948e-06,
+      "loss": 0.2639,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7161064107320225,
+      "grad_norm": 0.6754360798564671,
+      "learning_rate": 9.86723878392279e-07,
+      "loss": 0.2675,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7199358567787179,
+      "grad_norm": 0.5875424854805807,
+      "learning_rate": 9.621502867068286e-07,
+      "loss": 0.2592,
+      "step": 1880
+    },
+    {
+      "epoch": 0.7237653028254132,
+      "grad_norm": 0.6032756771398841,
+      "learning_rate": 9.378134399404768e-07,
+      "loss": 0.2676,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7275947488721085,
+      "grad_norm": 0.597275111662435,
+      "learning_rate": 9.137170846393054e-07,
+      "loss": 0.268,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7314241949188037,
+      "grad_norm": 0.610745344226226,
+      "learning_rate": 8.898649303268373e-07,
+      "loss": 0.2752,
+      "step": 1910
+    },
+    {
+      "epoch": 0.7352536409654991,
+      "grad_norm": 0.7020431210410311,
+      "learning_rate": 8.662606489329712e-07,
+      "loss": 0.2793,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7390830870121944,
+      "grad_norm": 0.6300673226887155,
+      "learning_rate": 8.429078742287072e-07,
+      "loss": 0.2673,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7429125330588897,
+      "grad_norm": 0.6440907203937188,
+      "learning_rate": 8.198102012667409e-07,
+      "loss": 0.2662,
+      "step": 1940
+    },
+    {
+      "epoch": 0.746741979105585,
+      "grad_norm": 0.6258159414377766,
+      "learning_rate": 7.969711858280251e-07,
+      "loss": 0.2712,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7505714251522804,
+      "grad_norm": 0.5989574886855157,
+      "learning_rate": 7.743943438743676e-07,
+      "loss": 0.2634,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7544008711989756,
+      "grad_norm": 0.7834580590666472,
+      "learning_rate": 7.520831510071744e-07,
+      "loss": 0.2632,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7582303172456709,
+      "grad_norm": 0.6728771166977499,
+      "learning_rate": 7.30041041932387e-07,
+      "loss": 0.2756,
+      "step": 1980
+    },
+    {
+      "epoch": 0.7620597632923662,
+      "grad_norm": 0.5993928197071544,
+      "learning_rate": 7.082714099317334e-07,
+      "loss": 0.2664,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7658892093390616,
+      "grad_norm": 0.5848853677834179,
+      "learning_rate": 6.867776063403411e-07,
+      "loss": 0.2628,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7697186553857569,
+      "grad_norm": 0.629330394414076,
+      "learning_rate": 6.655629400308191e-07,
+      "loss": 0.2658,
+      "step": 2010
+    },
+    {
+      "epoch": 0.7735481014324521,
+      "grad_norm": 0.5924525230054234,
+      "learning_rate": 6.44630676903869e-07,
+      "loss": 0.2669,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7773775474791474,
+      "grad_norm": 0.6760063055600575,
+      "learning_rate": 6.239840393855185e-07,
+      "loss": 0.2692,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7812069935258428,
+      "grad_norm": 0.6602651610212074,
+      "learning_rate": 6.036262059310383e-07,
+      "loss": 0.2629,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7850364395725381,
+      "grad_norm": 0.6327130212823728,
+      "learning_rate": 5.835603105356396e-07,
+      "loss": 0.2678,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7888658856192334,
+      "grad_norm": 0.68617187633267,
+      "learning_rate": 5.637894422520027e-07,
+      "loss": 0.268,
+      "step": 2060
+    },
+    {
+      "epoch": 0.7926953316659286,
+      "grad_norm": 0.6854582170736043,
+      "learning_rate": 5.443166447147392e-07,
+      "loss": 0.2652,
+      "step": 2070
+    },
+    {
+      "epoch": 0.796524777712624,
+      "grad_norm": 0.6454661983770266,
+      "learning_rate": 5.251449156718313e-07,
+      "loss": 0.2616,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8003542237593193,
+      "grad_norm": 0.6204018065147047,
+      "learning_rate": 5.062772065231492e-07,
+      "loss": 0.2664,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8041836698060146,
+      "grad_norm": 0.6500266139560574,
+      "learning_rate": 4.877164218660901e-07,
+      "loss": 0.2656,
+      "step": 2100
+    },
+    {
+      "epoch": 0.80801311585271,
+      "grad_norm": 0.6419744527723766,
+      "learning_rate": 4.694654190484327e-07,
+      "loss": 0.2612,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8118425618994053,
+      "grad_norm": 0.6238307107139875,
+      "learning_rate": 4.5152700772845947e-07,
+      "loss": 0.2676,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8156720079461005,
+      "grad_norm": 0.6514460031994411,
+      "learning_rate": 4.339039494424263e-07,
+      "loss": 0.2755,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8195014539927958,
+      "grad_norm": 0.5974777353730542,
+      "learning_rate": 4.16598957179431e-07,
+      "loss": 0.2597,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8233309000394912,
+      "grad_norm": 0.6009135110985171,
+      "learning_rate": 3.9961469496376584e-07,
+      "loss": 0.2592,
+      "step": 2150
+    },
+    {
+      "epoch": 0.8271603460861865,
+      "grad_norm": 0.6454195389454723,
+      "learning_rate": 3.829537774448e-07,
+      "loss": 0.2714,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8309897921328818,
+      "grad_norm": 0.5913764986372555,
+      "learning_rate": 3.6661876949447006e-07,
+      "loss": 0.2637,
+      "step": 2170
+    },
+    {
+      "epoch": 0.834819238179577,
+      "grad_norm": 0.6714610867965414,
+      "learning_rate": 3.506121858124253e-07,
+      "loss": 0.2652,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8386486842262724,
+      "grad_norm": 0.6260094170090917,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 0.2642,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8424781302729677,
+      "grad_norm": 0.5797985857131752,
+      "learning_rate": 3.1959409687538854e-07,
+      "loss": 0.2632,
+      "step": 2200
+    },
+    {
+      "epoch": 0.846307576319663,
+      "grad_norm": 0.6189077791942977,
+      "learning_rate": 3.04587366713108e-07,
+      "loss": 0.2648,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8501370223663584,
+      "grad_norm": 0.6122894183484023,
+      "learning_rate": 2.8991861026943015e-07,
+      "loss": 0.2741,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8539664684130536,
+      "grad_norm": 0.6661899719747609,
+      "learning_rate": 2.755900857322172e-07,
+      "loss": 0.2645,
+      "step": 2230
+    },
+    {
+      "epoch": 0.8577959144597489,
+      "grad_norm": 0.5568358628059588,
+      "learning_rate": 2.616039989121899e-07,
+      "loss": 0.2546,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8616253605064442,
+      "grad_norm": 0.6975565699445695,
+      "learning_rate": 2.479625029033489e-07,
+      "loss": 0.2774,
+      "step": 2250
+    },
+    {
+      "epoch": 0.8654548065531396,
+      "grad_norm": 0.6137153739809891,
+      "learning_rate": 2.3466769775151887e-07,
+      "loss": 0.266,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8692842525998349,
+      "grad_norm": 0.6065270965865103,
+      "learning_rate": 2.21721630131054e-07,
+      "loss": 0.2717,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8731136986465302,
+      "grad_norm": 0.6194228612620867,
+      "learning_rate": 2.0912629302976494e-07,
+      "loss": 0.2656,
+      "step": 2280
+    },
+    {
+      "epoch": 0.8769431446932254,
+      "grad_norm": 0.6721041148274991,
+      "learning_rate": 1.968836254421036e-07,
+      "loss": 0.2653,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8807725907399208,
+      "grad_norm": 0.664610505857682,
+      "learning_rate": 1.849955120706673e-07,
+      "loss": 0.2677,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8846020367866161,
+      "grad_norm": 0.6321996875856193,
+      "learning_rate": 1.734637830360536e-07,
+      "loss": 0.2645,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8884314828333114,
+      "grad_norm": 0.6365093137379149,
+      "learning_rate": 1.6229021359512626e-07,
+      "loss": 0.2658,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8922609288800067,
+      "grad_norm": 0.6539770975459238,
+      "learning_rate": 1.514765238677185e-07,
+      "loss": 0.259,
+      "step": 2330
+    },
+    {
+      "epoch": 0.896090374926702,
+      "grad_norm": 0.5990361778489132,
+      "learning_rate": 1.4102437857183155e-07,
+      "loss": 0.265,
+      "step": 2340
+    },
+    {
+      "epoch": 0.8999198209733973,
+      "grad_norm": 0.6484099138497742,
+      "learning_rate": 1.30935386767356e-07,
+      "loss": 0.2667,
+      "step": 2350
+    },
+    {
+      "epoch": 0.9037492670200926,
+      "grad_norm": 0.5867117908179056,
+      "learning_rate": 1.2121110160836697e-07,
+      "loss": 0.2634,
+      "step": 2360
+    },
+    {
+      "epoch": 0.907578713066788,
+      "grad_norm": 0.5796597988618597,
+      "learning_rate": 1.1185302010402105e-07,
+      "loss": 0.2719,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9114081591134833,
+      "grad_norm": 0.6237999983224305,
+      "learning_rate": 1.0286258288810108e-07,
+      "loss": 0.2627,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9152376051601786,
+      "grad_norm": 0.603524669140342,
+      "learning_rate": 9.424117399723432e-08,
+      "loss": 0.262,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9190670512068738,
+      "grad_norm": 0.620014776939978,
+      "learning_rate": 8.599012065782924e-08,
+      "loss": 0.271,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9228964972535691,
+      "grad_norm": 0.6276616849770017,
+      "learning_rate": 7.811069308175156e-08,
+      "loss": 0.2692,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9267259433002645,
+      "grad_norm": 0.6160811115395115,
+      "learning_rate": 7.060410427078473e-08,
+      "loss": 0.2674,
+      "step": 2420
+    },
+    {
+      "epoch": 0.9305553893469598,
+      "grad_norm": 0.5848887503471439,
+      "learning_rate": 6.347150982989159e-08,
+      "loss": 0.2625,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9343848353936551,
+      "grad_norm": 0.5883046146508241,
+      "learning_rate": 5.6714007789314686e-08,
+      "loss": 0.2621,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9382142814403504,
+      "grad_norm": 0.6940261485803617,
+      "learning_rate": 5.033263843554015e-08,
+      "loss": 0.2646,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9420437274870457,
+      "grad_norm": 0.6682532368250712,
+      "learning_rate": 4.4328384151149094e-08,
+      "loss": 0.2667,
+      "step": 2460
+    },
+    {
+      "epoch": 0.945873173533741,
+      "grad_norm": 0.6267836020326658,
+      "learning_rate": 3.870216926358555e-08,
+      "loss": 0.2643,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9497026195804363,
+      "grad_norm": 0.5575161118815479,
+      "learning_rate": 3.3454859902860295e-08,
+      "loss": 0.2641,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9535320656271317,
+      "grad_norm": 0.5714423960482532,
+      "learning_rate": 2.858726386821359e-08,
+      "loss": 0.2707,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9573615116738269,
+      "grad_norm": 0.6111083062299648,
+      "learning_rate": 2.410013050375859e-08,
+      "loss": 0.2709,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9611909577205222,
+      "grad_norm": 0.642938384488523,
+      "learning_rate": 1.999415058312276e-08,
+      "loss": 0.271,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9650204037672175,
+      "grad_norm": 0.6112837503032897,
+      "learning_rate": 1.6269956203107117e-08,
+      "loss": 0.2512,
+      "step": 2520
+    },
+    {
+      "epoch": 0.9688498498139129,
+      "grad_norm": 0.5889833725999716,
+      "learning_rate": 1.2928120686377388e-08,
+      "loss": 0.2661,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9726792958606082,
+      "grad_norm": 0.5773801445867635,
+      "learning_rate": 9.969158493204067e-09,
+      "loss": 0.2653,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9765087419073035,
+      "grad_norm": 0.6062759480472552,
+      "learning_rate": 7.393525142262992e-09,
+      "loss": 0.2691,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9803381879539987,
+      "grad_norm": 0.5770795227743729,
+      "learning_rate": 5.201617140510318e-09,
+      "loss": 0.2694,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9841676340006941,
+      "grad_norm": 0.6054174692665726,
+      "learning_rate": 3.3937719221427413e-09,
+      "loss": 0.2592,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9879970800473894,
+      "grad_norm": 0.5960623948954498,
+      "learning_rate": 1.9702677966507157e-09,
+      "loss": 0.2641,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9918265260940847,
+      "grad_norm": 0.6702560926553222,
+      "learning_rate": 9.31323905974113e-10,
+      "loss": 0.2621,
+      "step": 2590
+    },
+    {
+      "epoch": 0.99565597214078,
+      "grad_norm": 0.623171089038422,
+      "learning_rate": 2.7710019076532257e-10,
+      "loss": 0.2672,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9994854181874753,
+      "grad_norm": 0.6269492106617217,
+      "learning_rate": 7.697365768943865e-12,
+      "loss": 0.2736,
+      "step": 2610
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2611,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 600,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 624569162006528.0,
+  "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 sha256:66b412e370644b56185d16fd7d7d951b6564410c682558ce3ffb394f09f059b3
+size 7736

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/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 gc
+import json
+import numpy as np
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+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,
+                                                          lazy_mode=True)
+
+    # 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")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_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 by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # 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)