Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/test/test/finetune/LLM/qwen3B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

latest

@@ -0,0 +1 @@
+global_step500

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92310f580fc5f9534fa0db88ebc8681837f14adcee254dde32c8b563ae049e8
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b5f9db3780bb2858b58b6e1183bb7bdd90b2da56be4bbaa28daa4775289426
+size 1214366696

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 6171877376
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cc13315f24c28015d695b6cde08bb1cd6fea4cbc435998485ed6fbe4c91285
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b023e05bc2d12b91dc436d4922b990d50ec8dc56d40dc3e36b3bb34fc81341
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e87d47519e32af310d5ce258e0454d331221391a1b9ee9143859120658f7a9a
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% 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: ' + system_message + '<|endoftext|>' + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|endoftext|>' + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1361 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.999000999000999,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005994005994005994,
+      "grad_norm": 6.410329800814756,
+      "learning_rate": 4.999555880952023e-05,
+      "loss": 3.0698,
+      "num_input_tokens_seen": 3145728,
+      "step": 3
+    },
+    {
+      "epoch": 0.011988011988011988,
+      "grad_norm": 3.598763931440751,
+      "learning_rate": 4.998223681601473e-05,
+      "loss": 3.1178,
+      "num_input_tokens_seen": 6291456,
+      "step": 6
+    },
+    {
+      "epoch": 0.017982017982017984,
+      "grad_norm": 1.2982339138868861,
+      "learning_rate": 4.996003875272438e-05,
+      "loss": 2.9832,
+      "num_input_tokens_seen": 9437184,
+      "step": 9
+    },
+    {
+      "epoch": 0.023976023976023976,
+      "grad_norm": 1.2074968206304935,
+      "learning_rate": 4.992897250651535e-05,
+      "loss": 2.9347,
+      "num_input_tokens_seen": 12582912,
+      "step": 12
+    },
+    {
+      "epoch": 0.029970029970029972,
+      "grad_norm": 0.9212304945073692,
+      "learning_rate": 4.9889049115077005e-05,
+      "loss": 2.8797,
+      "num_input_tokens_seen": 15728640,
+      "step": 15
+    },
+    {
+      "epoch": 0.03596403596403597,
+      "grad_norm": 0.9296039295580661,
+      "learning_rate": 4.984028276300021e-05,
+      "loss": 2.8764,
+      "num_input_tokens_seen": 18874368,
+      "step": 18
+    },
+    {
+      "epoch": 0.04195804195804196,
+      "grad_norm": 0.6566188771172786,
+      "learning_rate": 4.978269077673767e-05,
+      "loss": 2.8618,
+      "num_input_tokens_seen": 22020096,
+      "step": 21
+    },
+    {
+      "epoch": 0.04795204795204795,
+      "grad_norm": 0.5643043759778712,
+      "learning_rate": 4.971629361844785e-05,
+      "loss": 2.8084,
+      "num_input_tokens_seen": 25165824,
+      "step": 24
+    },
+    {
+      "epoch": 0.053946053946053944,
+      "grad_norm": 0.8404097218145734,
+      "learning_rate": 4.9641114878724956e-05,
+      "loss": 2.8394,
+      "num_input_tokens_seen": 28311552,
+      "step": 27
+    },
+    {
+      "epoch": 0.059940059940059943,
+      "grad_norm": 0.45930658576738653,
+      "learning_rate": 4.9557181268217227e-05,
+      "loss": 2.8177,
+      "num_input_tokens_seen": 31457280,
+      "step": 30
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.4837304897474338,
+      "learning_rate": 4.9464522608136805e-05,
+      "loss": 2.8204,
+      "num_input_tokens_seen": 34603008,
+      "step": 33
+    },
+    {
+      "epoch": 0.07192807192807193,
+      "grad_norm": 0.6048874863801816,
+      "learning_rate": 4.9363171819664434e-05,
+      "loss": 2.7799,
+      "num_input_tokens_seen": 37748736,
+      "step": 36
+    },
+    {
+      "epoch": 0.07792207792207792,
+      "grad_norm": 3.2597244464789257,
+      "learning_rate": 4.925316491225265e-05,
+      "loss": 2.7659,
+      "num_input_tokens_seen": 40894464,
+      "step": 39
+    },
+    {
+      "epoch": 0.08391608391608392,
+      "grad_norm": 0.570038657590452,
+      "learning_rate": 4.913454097083185e-05,
+      "loss": 2.7619,
+      "num_input_tokens_seen": 44040192,
+      "step": 42
+    },
+    {
+      "epoch": 0.0899100899100899,
+      "grad_norm": 0.47359587676949844,
+      "learning_rate": 4.900734214192358e-05,
+      "loss": 2.7279,
+      "num_input_tokens_seen": 47185920,
+      "step": 45
+    },
+    {
+      "epoch": 0.0959040959040959,
+      "grad_norm": 0.5778423173821229,
+      "learning_rate": 4.887161361866608e-05,
+      "loss": 2.765,
+      "num_input_tokens_seen": 50331648,
+      "step": 48
+    },
+    {
+      "epoch": 0.1018981018981019,
+      "grad_norm": 0.7237100366728827,
+      "learning_rate": 4.8727403624757365e-05,
+      "loss": 2.781,
+      "num_input_tokens_seen": 53477376,
+      "step": 51
+    },
+    {
+      "epoch": 0.10789210789210789,
+      "grad_norm": 0.8137665820619678,
+      "learning_rate": 4.8574763397321614e-05,
+      "loss": 2.7898,
+      "num_input_tokens_seen": 56623104,
+      "step": 54
+    },
+    {
+      "epoch": 0.11388611388611389,
+      "grad_norm": 0.5050391851364759,
+      "learning_rate": 4.841374716870481e-05,
+      "loss": 2.7846,
+      "num_input_tokens_seen": 59768832,
+      "step": 57
+    },
+    {
+      "epoch": 0.11988011988011989,
+      "grad_norm": 5.093048507367434,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 2.7805,
+      "num_input_tokens_seen": 62914560,
+      "step": 60
+    },
+    {
+      "epoch": 0.1258741258741259,
+      "grad_norm": 1.117581806245609,
+      "learning_rate": 4.8066818496752875e-05,
+      "loss": 2.7444,
+      "num_input_tokens_seen": 66060288,
+      "step": 63
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.7662489528910221,
+      "learning_rate": 4.788102931552294e-05,
+      "loss": 2.7508,
+      "num_input_tokens_seen": 69206016,
+      "step": 66
+    },
+    {
+      "epoch": 0.13786213786213786,
+      "grad_norm": 0.9444570453906338,
+      "learning_rate": 4.7687110613527926e-05,
+      "loss": 2.7952,
+      "num_input_tokens_seen": 72351744,
+      "step": 69
+    },
+    {
+      "epoch": 0.14385614385614387,
+      "grad_norm": 0.823124734745159,
+      "learning_rate": 4.7485131289159276e-05,
+      "loss": 2.7001,
+      "num_input_tokens_seen": 75497472,
+      "step": 72
+    },
+    {
+      "epoch": 0.14985014985014986,
+      "grad_norm": 5.498054654828591,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 2.7672,
+      "num_input_tokens_seen": 78643200,
+      "step": 75
+    },
+    {
+      "epoch": 0.15584415584415584,
+      "grad_norm": 0.48847343418746697,
+      "learning_rate": 4.7057280660873835e-05,
+      "loss": 2.7364,
+      "num_input_tokens_seen": 81788928,
+      "step": 78
+    },
+    {
+      "epoch": 0.16183816183816183,
+      "grad_norm": 0.5685862429908973,
+      "learning_rate": 4.683156137024801e-05,
+      "loss": 2.7621,
+      "num_input_tokens_seen": 84934656,
+      "step": 81
+    },
+    {
+      "epoch": 0.16783216783216784,
+      "grad_norm": 0.7915394918817883,
+      "learning_rate": 4.659808542982088e-05,
+      "loss": 2.7108,
+      "num_input_tokens_seen": 88080384,
+      "step": 84
+    },
+    {
+      "epoch": 0.17382617382617382,
+      "grad_norm": 0.6715267193991125,
+      "learning_rate": 4.635693579248238e-05,
+      "loss": 2.7189,
+      "num_input_tokens_seen": 91226112,
+      "step": 87
+    },
+    {
+      "epoch": 0.1798201798201798,
+      "grad_norm": 0.45902906356531303,
+      "learning_rate": 4.610819813755038e-05,
+      "loss": 2.731,
+      "num_input_tokens_seen": 94371840,
+      "step": 90
+    },
+    {
+      "epoch": 0.18581418581418582,
+      "grad_norm": 0.4650647215113369,
+      "learning_rate": 4.585196084032928e-05,
+      "loss": 2.7258,
+      "num_input_tokens_seen": 97517568,
+      "step": 93
+    },
+    {
+      "epoch": 0.1918081918081918,
+      "grad_norm": 0.42926302957638696,
+      "learning_rate": 4.558831494071069e-05,
+      "loss": 2.6823,
+      "num_input_tokens_seen": 100663296,
+      "step": 96
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 1.3413279663961608,
+      "learning_rate": 4.531735411082735e-05,
+      "loss": 2.6612,
+      "num_input_tokens_seen": 103809024,
+      "step": 99
+    },
+    {
+      "epoch": 0.2037962037962038,
+      "grad_norm": 0.3943880139612496,
+      "learning_rate": 4.503917462177192e-05,
+      "loss": 2.6618,
+      "num_input_tokens_seen": 106954752,
+      "step": 102
+    },
+    {
+      "epoch": 0.2097902097902098,
+      "grad_norm": 0.40171152659214054,
+      "learning_rate": 4.4753875309392266e-05,
+      "loss": 2.6962,
+      "num_input_tokens_seen": 110100480,
+      "step": 105
+    },
+    {
+      "epoch": 0.21578421578421578,
+      "grad_norm": 0.378919832453279,
+      "learning_rate": 4.4461557539175594e-05,
+      "loss": 2.688,
+      "num_input_tokens_seen": 113246208,
+      "step": 108
+    },
+    {
+      "epoch": 0.2217782217782218,
+      "grad_norm": 1.003688893990752,
+      "learning_rate": 4.4162325170233745e-05,
+      "loss": 2.6481,
+      "num_input_tokens_seen": 116391936,
+      "step": 111
+    },
+    {
+      "epoch": 0.22777222777222778,
+      "grad_norm": 0.6441319104368781,
+      "learning_rate": 4.3856284518402594e-05,
+      "loss": 2.7027,
+      "num_input_tokens_seen": 119537664,
+      "step": 114
+    },
+    {
+      "epoch": 0.23376623376623376,
+      "grad_norm": 1.324580117820949,
+      "learning_rate": 4.3543544318468485e-05,
+      "loss": 2.6872,
+      "num_input_tokens_seen": 122683392,
+      "step": 117
+    },
+    {
+      "epoch": 0.23976023976023977,
+      "grad_norm": 0.435587920648407,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 2.6966,
+      "num_input_tokens_seen": 125829120,
+      "step": 120
+    },
+    {
+      "epoch": 0.24575424575424576,
+      "grad_norm": 5.442108344419999,
+      "learning_rate": 4.289841207554578e-05,
+      "loss": 2.6806,
+      "num_input_tokens_seen": 128974848,
+      "step": 123
+    },
+    {
+      "epoch": 0.2517482517482518,
+      "grad_norm": 0.5725734386470224,
+      "learning_rate": 4.256624924497123e-05,
+      "loss": 2.6519,
+      "num_input_tokens_seen": 132120576,
+      "step": 126
+    },
+    {
+      "epoch": 0.25774225774225773,
+      "grad_norm": 0.42583304978163344,
+      "learning_rate": 4.2227845209683716e-05,
+      "loss": 2.6763,
+      "num_input_tokens_seen": 135266304,
+      "step": 129
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 1.8519209519904896,
+      "learning_rate": 4.188332020302561e-05,
+      "loss": 2.6558,
+      "num_input_tokens_seen": 138412032,
+      "step": 132
+    },
+    {
+      "epoch": 0.26973026973026976,
+      "grad_norm": 0.38683420786657774,
+      "learning_rate": 4.1532796633091296e-05,
+      "loss": 2.6959,
+      "num_input_tokens_seen": 141557760,
+      "step": 135
+    },
+    {
+      "epoch": 0.2757242757242757,
+      "grad_norm": 0.41808748224631315,
+      "learning_rate": 4.1176399039236116e-05,
+      "loss": 2.6277,
+      "num_input_tokens_seen": 144703488,
+      "step": 138
+    },
+    {
+      "epoch": 0.2817182817182817,
+      "grad_norm": 0.3840574344519147,
+      "learning_rate": 4.0814254047828116e-05,
+      "loss": 2.6848,
+      "num_input_tokens_seen": 147849216,
+      "step": 141
+    },
+    {
+      "epoch": 0.28771228771228774,
+      "grad_norm": 0.45772925021690175,
+      "learning_rate": 4.044649032725836e-05,
+      "loss": 2.6818,
+      "num_input_tokens_seen": 150994944,
+      "step": 144
+    },
+    {
+      "epoch": 0.2937062937062937,
+      "grad_norm": 1.5595692690525471,
+      "learning_rate": 4.007323854222562e-05,
+      "loss": 2.6153,
+      "num_input_tokens_seen": 154140672,
+      "step": 147
+    },
+    {
+      "epoch": 0.2997002997002997,
+      "grad_norm": 0.5279946597014384,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 2.6256,
+      "num_input_tokens_seen": 157286400,
+      "step": 150
+    },
+    {
+      "epoch": 0.30569430569430567,
+      "grad_norm": 0.5747864588714933,
+      "learning_rate": 3.9310803139864775e-05,
+      "loss": 2.6344,
+      "num_input_tokens_seen": 160432128,
+      "step": 153
+    },
+    {
+      "epoch": 0.3116883116883117,
+      "grad_norm": 0.5509394817659662,
+      "learning_rate": 3.8921890412204705e-05,
+      "loss": 2.6541,
+      "num_input_tokens_seen": 163577856,
+      "step": 156
+    },
+    {
+      "epoch": 0.3176823176823177,
+      "grad_norm": 0.42045192588755487,
+      "learning_rate": 3.8528031303171895e-05,
+      "loss": 2.6473,
+      "num_input_tokens_seen": 166723584,
+      "step": 159
+    },
+    {
+      "epoch": 0.32367632367632365,
+      "grad_norm": 0.4804827265537982,
+      "learning_rate": 3.81293657490324e-05,
+      "loss": 2.6726,
+      "num_input_tokens_seen": 169869312,
+      "step": 162
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 3.0279756731001686,
+      "learning_rate": 3.7726035393759285e-05,
+      "loss": 2.6003,
+      "num_input_tokens_seen": 173015040,
+      "step": 165
+    },
+    {
+      "epoch": 0.3356643356643357,
+      "grad_norm": 5.031908217711359,
+      "learning_rate": 3.731818353870729e-05,
+      "loss": 2.6188,
+      "num_input_tokens_seen": 176160768,
+      "step": 168
+    },
+    {
+      "epoch": 0.34165834165834164,
+      "grad_norm": 0.5767115815961583,
+      "learning_rate": 3.690595509169848e-05,
+      "loss": 2.6718,
+      "num_input_tokens_seen": 179306496,
+      "step": 171
+    },
+    {
+      "epoch": 0.34765234765234765,
+      "grad_norm": 0.6895432293898848,
+      "learning_rate": 3.6489496515537204e-05,
+      "loss": 2.6444,
+      "num_input_tokens_seen": 182452224,
+      "step": 174
+    },
+    {
+      "epoch": 0.35364635364635366,
+      "grad_norm": 0.7159781803307739,
+      "learning_rate": 3.606895577597255e-05,
+      "loss": 2.6021,
+      "num_input_tokens_seen": 185597952,
+      "step": 177
+    },
+    {
+      "epoch": 0.3596403596403596,
+      "grad_norm": 0.5272365769844538,
+      "learning_rate": 3.564448228912682e-05,
+      "loss": 2.6342,
+      "num_input_tokens_seen": 188743680,
+      "step": 180
+    },
+    {
+      "epoch": 0.36563436563436563,
+      "grad_norm": 0.8359901567041759,
+      "learning_rate": 3.521622686840873e-05,
+      "loss": 2.628,
+      "num_input_tokens_seen": 191889408,
+      "step": 183
+    },
+    {
+      "epoch": 0.37162837162837165,
+      "grad_norm": 0.572337686322507,
+      "learning_rate": 3.4784341670930065e-05,
+      "loss": 2.6353,
+      "num_input_tokens_seen": 195035136,
+      "step": 186
+    },
+    {
+      "epoch": 0.3776223776223776,
+      "grad_norm": 1.0869108038577857,
+      "learning_rate": 3.434898014344501e-05,
+      "loss": 2.6465,
+      "num_input_tokens_seen": 198180864,
+      "step": 189
+    },
+    {
+      "epoch": 0.3836163836163836,
+      "grad_norm": 0.48504927834187145,
+      "learning_rate": 3.3910296967831266e-05,
+      "loss": 2.6725,
+      "num_input_tokens_seen": 201326592,
+      "step": 192
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "grad_norm": 0.3913503309250976,
+      "learning_rate": 3.346844800613229e-05,
+      "loss": 2.712,
+      "num_input_tokens_seen": 204472320,
+      "step": 195
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.42816571600763464,
+      "learning_rate": 3.302359024518024e-05,
+      "loss": 2.6112,
+      "num_input_tokens_seen": 207618048,
+      "step": 198
+    },
+    {
+      "epoch": 0.4015984015984016,
+      "grad_norm": 0.4237132906151592,
+      "learning_rate": 3.2575881740819355e-05,
+      "loss": 2.6606,
+      "num_input_tokens_seen": 210763776,
+      "step": 201
+    },
+    {
+      "epoch": 0.4075924075924076,
+      "grad_norm": 0.4280894296899793,
+      "learning_rate": 3.21254815617494e-05,
+      "loss": 2.5857,
+      "num_input_tokens_seen": 213909504,
+      "step": 204
+    },
+    {
+      "epoch": 0.41358641358641357,
+      "grad_norm": 0.5608557700949965,
+      "learning_rate": 3.1672549733009396e-05,
+      "loss": 2.6267,
+      "num_input_tokens_seen": 217055232,
+      "step": 207
+    },
+    {
+      "epoch": 0.4195804195804196,
+      "grad_norm": 0.4223057040158911,
+      "learning_rate": 3.121724717912138e-05,
+      "loss": 2.6066,
+      "num_input_tokens_seen": 220200960,
+      "step": 210
+    },
+    {
+      "epoch": 0.4255744255744256,
+      "grad_norm": 0.6679767031345181,
+      "learning_rate": 3.075973566691477e-05,
+      "loss": 2.5588,
+      "num_input_tokens_seen": 223346688,
+      "step": 213
+    },
+    {
+      "epoch": 0.43156843156843155,
+      "grad_norm": 0.3393943953900005,
+      "learning_rate": 3.0300177748051373e-05,
+      "loss": 2.6338,
+      "num_input_tokens_seen": 226492416,
+      "step": 216
+    },
+    {
+      "epoch": 0.43756243756243757,
+      "grad_norm": 0.7044630182235262,
+      "learning_rate": 2.9838736701271514e-05,
+      "loss": 2.5779,
+      "num_input_tokens_seen": 229638144,
+      "step": 219
+    },
+    {
+      "epoch": 0.4435564435564436,
+      "grad_norm": 0.3665454695394432,
+      "learning_rate": 2.9375576474381905e-05,
+      "loss": 2.5865,
+      "num_input_tokens_seen": 232783872,
+      "step": 222
+    },
+    {
+      "epoch": 0.44955044955044954,
+      "grad_norm": 0.6891559913443284,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 2.6204,
+      "num_input_tokens_seen": 235929600,
+      "step": 225
+    },
+    {
+      "epoch": 0.45554445554445555,
+      "grad_norm": 0.3575626844517306,
+      "learning_rate": 2.844475726711595e-05,
+      "loss": 2.6311,
+      "num_input_tokens_seen": 239075328,
+      "step": 228
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.33724800358932033,
+      "learning_rate": 2.7977429002371747e-05,
+      "loss": 2.5877,
+      "num_input_tokens_seen": 242221056,
+      "step": 231
+    },
+    {
+      "epoch": 0.4675324675324675,
+      "grad_norm": 2.4861319375569275,
+      "learning_rate": 2.7509042871280372e-05,
+      "loss": 2.6024,
+      "num_input_tokens_seen": 245366784,
+      "step": 234
+    },
+    {
+      "epoch": 0.47352647352647353,
+      "grad_norm": 0.3301940185405345,
+      "learning_rate": 2.7039765289203946e-05,
+      "loss": 2.5922,
+      "num_input_tokens_seen": 248512512,
+      "step": 237
+    },
+    {
+      "epoch": 0.47952047952047955,
+      "grad_norm": 0.3196889954067017,
+      "learning_rate": 2.656976298823284e-05,
+      "loss": 2.6193,
+      "num_input_tokens_seen": 251658240,
+      "step": 240
+    },
+    {
+      "epoch": 0.4855144855144855,
+      "grad_norm": 2.2778017903527696,
+      "learning_rate": 2.6099202957946624e-05,
+      "loss": 2.6123,
+      "num_input_tokens_seen": 254803968,
+      "step": 243
+    },
+    {
+      "epoch": 0.4915084915084915,
+      "grad_norm": 2.4283058658668,
+      "learning_rate": 2.562825238608344e-05,
+      "loss": 2.6,
+      "num_input_tokens_seen": 257949696,
+      "step": 246
+    },
+    {
+      "epoch": 0.4975024975024975,
+      "grad_norm": 0.410230124930567,
+      "learning_rate": 2.5157078599138977e-05,
+      "loss": 2.6283,
+      "num_input_tokens_seen": 261095424,
+      "step": 249
+    },
+    {
+      "epoch": 0.5034965034965035,
+      "grad_norm": 0.3466943753224513,
+      "learning_rate": 2.4685849002916183e-05,
+      "loss": 2.5913,
+      "num_input_tokens_seen": 264241152,
+      "step": 252
+    },
+    {
+      "epoch": 0.5094905094905094,
+      "grad_norm": 0.3914365498954126,
+      "learning_rate": 2.4214731023046793e-05,
+      "loss": 2.6009,
+      "num_input_tokens_seen": 267386880,
+      "step": 255
+    },
+    {
+      "epoch": 0.5154845154845155,
+      "grad_norm": 0.3529131177018493,
+      "learning_rate": 2.3743892045505764e-05,
+      "loss": 2.5738,
+      "num_input_tokens_seen": 270532608,
+      "step": 258
+    },
+    {
+      "epoch": 0.5214785214785215,
+      "grad_norm": 1.875060771577452,
+      "learning_rate": 2.3273499357139855e-05,
+      "loss": 2.644,
+      "num_input_tokens_seen": 273678336,
+      "step": 261
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 3.305515863520439,
+      "learning_rate": 2.280372008623142e-05,
+      "loss": 2.5421,
+      "num_input_tokens_seen": 276824064,
+      "step": 264
+    },
+    {
+      "epoch": 0.5334665334665335,
+      "grad_norm": 0.7927173933972061,
+      "learning_rate": 2.2334721143118504e-05,
+      "loss": 2.5931,
+      "num_input_tokens_seen": 279969792,
+      "step": 267
+    },
+    {
+      "epoch": 0.5394605394605395,
+      "grad_norm": 0.32799543549185534,
+      "learning_rate": 2.186666916089239e-05,
+      "loss": 2.5424,
+      "num_input_tokens_seen": 283115520,
+      "step": 270
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.3408914601518253,
+      "learning_rate": 2.1399730436193697e-05,
+      "loss": 2.5363,
+      "num_input_tokens_seen": 286261248,
+      "step": 273
+    },
+    {
+      "epoch": 0.5514485514485514,
+      "grad_norm": 0.30890933048854724,
+      "learning_rate": 2.0934070870127912e-05,
+      "loss": 2.5816,
+      "num_input_tokens_seen": 289406976,
+      "step": 276
+    },
+    {
+      "epoch": 0.5574425574425574,
+      "grad_norm": 0.32106541083220086,
+      "learning_rate": 2.0469855909321564e-05,
+      "loss": 2.5363,
+      "num_input_tokens_seen": 292552704,
+      "step": 279
+    },
+    {
+      "epoch": 0.5634365634365635,
+      "grad_norm": 0.3408403179073976,
+      "learning_rate": 2.000725048713983e-05,
+      "loss": 2.575,
+      "num_input_tokens_seen": 295698432,
+      "step": 282
+    },
+    {
+      "epoch": 0.5694305694305695,
+      "grad_norm": 0.32723808150500727,
+      "learning_rate": 1.9546418965086442e-05,
+      "loss": 2.6032,
+      "num_input_tokens_seen": 298844160,
+      "step": 285
+    },
+    {
+      "epoch": 0.5754245754245755,
+      "grad_norm": 0.3163627653419453,
+      "learning_rate": 1.908752507440689e-05,
+      "loss": 2.5505,
+      "num_input_tokens_seen": 301989888,
+      "step": 288
+    },
+    {
+      "epoch": 0.5814185814185814,
+      "grad_norm": 1.4371183687556357,
+      "learning_rate": 1.863073185791545e-05,
+      "loss": 2.5556,
+      "num_input_tokens_seen": 305135616,
+      "step": 291
+    },
+    {
+      "epoch": 0.5874125874125874,
+      "grad_norm": 0.332426093746843,
+      "learning_rate": 1.817620161206687e-05,
+      "loss": 2.6209,
+      "num_input_tokens_seen": 308281344,
+      "step": 294
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.331930425442621,
+      "learning_rate": 1.772409582929321e-05,
+      "loss": 2.5937,
+      "num_input_tokens_seen": 311427072,
+      "step": 297
+    },
+    {
+      "epoch": 0.5994005994005994,
+      "grad_norm": 0.30015137569291384,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 2.5816,
+      "num_input_tokens_seen": 314572800,
+      "step": 300
+    },
+    {
+      "epoch": 0.6053946053946054,
+      "grad_norm": 0.29669010639441357,
+      "learning_rate": 1.6827799258626442e-05,
+      "loss": 2.5316,
+      "num_input_tokens_seen": 317718528,
+      "step": 303
+    },
+    {
+      "epoch": 0.6113886113886113,
+      "grad_norm": 0.31486652654283287,
+      "learning_rate": 1.6383926920637077e-05,
+      "loss": 2.5585,
+      "num_input_tokens_seen": 320864256,
+      "step": 306
+    },
+    {
+      "epoch": 0.6173826173826173,
+      "grad_norm": 0.311566282991231,
+      "learning_rate": 1.594311583238636e-05,
+      "loss": 2.5819,
+      "num_input_tokens_seen": 324009984,
+      "step": 309
+    },
+    {
+      "epoch": 0.6233766233766234,
+      "grad_norm": 0.29493362351781716,
+      "learning_rate": 1.5505522611954975e-05,
+      "loss": 2.5687,
+      "num_input_tokens_seen": 327155712,
+      "step": 312
+    },
+    {
+      "epoch": 0.6293706293706294,
+      "grad_norm": 0.4267576139130684,
+      "learning_rate": 1.5071302734130489e-05,
+      "loss": 2.5385,
+      "num_input_tokens_seen": 330301440,
+      "step": 315
+    },
+    {
+      "epoch": 0.6353646353646354,
+      "grad_norm": 0.3117397676497984,
+      "learning_rate": 1.4640610475167898e-05,
+      "loss": 2.5981,
+      "num_input_tokens_seen": 333447168,
+      "step": 318
+    },
+    {
+      "epoch": 0.6413586413586414,
+      "grad_norm": 0.7334176455472916,
+      "learning_rate": 1.4213598857976024e-05,
+      "loss": 2.518,
+      "num_input_tokens_seen": 336592896,
+      "step": 321
+    },
+    {
+      "epoch": 0.6473526473526473,
+      "grad_norm": 0.3079124682955966,
+      "learning_rate": 1.3790419597749199e-05,
+      "loss": 2.5933,
+      "num_input_tokens_seen": 339738624,
+      "step": 324
+    },
+    {
+      "epoch": 0.6533466533466533,
+      "grad_norm": 0.2901912083689425,
+      "learning_rate": 1.337122304806354e-05,
+      "loss": 2.5672,
+      "num_input_tokens_seen": 342884352,
+      "step": 327
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.2946920948153314,
+      "learning_rate": 1.2956158147457115e-05,
+      "loss": 2.5227,
+      "num_input_tokens_seen": 346030080,
+      "step": 330
+    },
+    {
+      "epoch": 0.6653346653346653,
+      "grad_norm": 0.3162716396365553,
+      "learning_rate": 1.254537236651273e-05,
+      "loss": 2.5623,
+      "num_input_tokens_seen": 349175808,
+      "step": 333
+    },
+    {
+      "epoch": 0.6713286713286714,
+      "grad_norm": 4.806386237704954,
+      "learning_rate": 1.2139011655462337e-05,
+      "loss": 2.5421,
+      "num_input_tokens_seen": 352321536,
+      "step": 336
+    },
+    {
+      "epoch": 0.6773226773226774,
+      "grad_norm": 0.282164042198725,
+      "learning_rate": 1.1737220392331644e-05,
+      "loss": 2.5315,
+      "num_input_tokens_seen": 355467264,
+      "step": 339
+    },
+    {
+      "epoch": 0.6833166833166833,
+      "grad_norm": 0.3072085362383577,
+      "learning_rate": 1.1340141331643276e-05,
+      "loss": 2.6113,
+      "num_input_tokens_seen": 358612992,
+      "step": 342
+    },
+    {
+      "epoch": 0.6893106893106893,
+      "grad_norm": 0.29874261150456116,
+      "learning_rate": 1.0947915553696742e-05,
+      "loss": 2.5667,
+      "num_input_tokens_seen": 361758720,
+      "step": 345
+    },
+    {
+      "epoch": 0.6953046953046953,
+      "grad_norm": 0.2977342807999766,
+      "learning_rate": 1.0560682414443315e-05,
+      "loss": 2.603,
+      "num_input_tokens_seen": 364904448,
+      "step": 348
+    },
+    {
+      "epoch": 0.7012987012987013,
+      "grad_norm": 0.28995253177965913,
+      "learning_rate": 1.017857949597352e-05,
+      "loss": 2.5654,
+      "num_input_tokens_seen": 368050176,
+      "step": 351
+    },
+    {
+      "epoch": 0.7072927072927073,
+      "grad_norm": 2.966417147796917,
+      "learning_rate": 9.801742557634872e-06,
+      "loss": 2.6343,
+      "num_input_tokens_seen": 371195904,
+      "step": 354
+    },
+    {
+      "epoch": 0.7132867132867133,
+      "grad_norm": 0.2704023797234269,
+      "learning_rate": 9.430305487797191e-06,
+      "loss": 2.5459,
+      "num_input_tokens_seen": 374341632,
+      "step": 357
+    },
+    {
+      "epoch": 0.7192807192807192,
+      "grad_norm": 0.28193281789243946,
+      "learning_rate": 9.064400256282757e-06,
+      "loss": 2.587,
+      "num_input_tokens_seen": 377487360,
+      "step": 360
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.28464876847685067,
+      "learning_rate": 8.704156867478036e-06,
+      "loss": 2.5161,
+      "num_input_tokens_seen": 380633088,
+      "step": 363
+    },
+    {
+      "epoch": 0.7312687312687313,
+      "grad_norm": 0.33462334499933316,
+      "learning_rate": 8.34970331414371e-06,
+      "loss": 2.5634,
+      "num_input_tokens_seen": 383778816,
+      "step": 366
+    },
+    {
+      "epoch": 0.7372627372627373,
+      "grad_norm": 0.2842439527764432,
+      "learning_rate": 8.00116553193952e-06,
+      "loss": 2.5562,
+      "num_input_tokens_seen": 386924544,
+      "step": 369
+    },
+    {
+      "epoch": 0.7432567432567433,
+      "grad_norm": 0.2750827928733446,
+      "learning_rate": 7.65866735467988e-06,
+      "loss": 2.5506,
+      "num_input_tokens_seen": 390070272,
+      "step": 372
+    },
+    {
+      "epoch": 0.7492507492507493,
+      "grad_norm": 0.276463968484142,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 2.5283,
+      "num_input_tokens_seen": 393216000,
+      "step": 375
+    },
+    {
+      "epoch": 0.7552447552447552,
+      "grad_norm": 0.2648943408545215,
+      "learning_rate": 6.992274377802327e-06,
+      "loss": 2.5712,
+      "num_input_tokens_seen": 396361728,
+      "step": 378
+    },
+    {
+      "epoch": 0.7612387612387612,
+      "grad_norm": 0.27061098664633787,
+      "learning_rate": 6.668616344436004e-06,
+      "loss": 2.6022,
+      "num_input_tokens_seen": 399507456,
+      "step": 381
+    },
+    {
+      "epoch": 0.7672327672327672,
+      "grad_norm": 0.2987157750517344,
+      "learning_rate": 6.3514713643954475e-06,
+      "loss": 2.5678,
+      "num_input_tokens_seen": 402653184,
+      "step": 384
+    },
+    {
+      "epoch": 0.7732267732267732,
+      "grad_norm": 0.2532344636930413,
+      "learning_rate": 6.040952117781953e-06,
+      "loss": 2.526,
+      "num_input_tokens_seen": 405798912,
+      "step": 387
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "grad_norm": 0.27643389064802143,
+      "learning_rate": 5.737168930605272e-06,
+      "loss": 2.6256,
+      "num_input_tokens_seen": 408944640,
+      "step": 390
+    },
+    {
+      "epoch": 0.7852147852147852,
+      "grad_norm": 0.2918689625031621,
+      "learning_rate": 5.440229735585298e-06,
+      "loss": 2.5908,
+      "num_input_tokens_seen": 412090368,
+      "step": 393
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.2622871999527977,
+      "learning_rate": 5.150240033804116e-06,
+      "loss": 2.5589,
+      "num_input_tokens_seen": 415236096,
+      "step": 396
+    },
+    {
+      "epoch": 0.7972027972027972,
+      "grad_norm": 2.3433807056887455,
+      "learning_rate": 4.867302857221953e-06,
+      "loss": 2.5774,
+      "num_input_tokens_seen": 418381824,
+      "step": 399
+    },
+    {
+      "epoch": 0.8031968031968032,
+      "grad_norm": 0.26971987397900704,
+      "learning_rate": 4.591518732070402e-06,
+      "loss": 2.5442,
+      "num_input_tokens_seen": 421527552,
+      "step": 402
+    },
+    {
+      "epoch": 0.8091908091908092,
+      "grad_norm": 0.26247835358132054,
+      "learning_rate": 4.322985643135952e-06,
+      "loss": 2.5993,
+      "num_input_tokens_seen": 424673280,
+      "step": 405
+    },
+    {
+      "epoch": 0.8151848151848152,
+      "grad_norm": 0.2588171884420971,
+      "learning_rate": 4.061798998946459e-06,
+      "loss": 2.566,
+      "num_input_tokens_seen": 427819008,
+      "step": 408
+    },
+    {
+      "epoch": 0.8211788211788211,
+      "grad_norm": 0.2573266101979906,
+      "learning_rate": 3.8080515978729247e-06,
+      "loss": 2.5646,
+      "num_input_tokens_seen": 430964736,
+      "step": 411
+    },
+    {
+      "epoch": 0.8271728271728271,
+      "grad_norm": 4.294728299543095,
+      "learning_rate": 3.561833595158698e-06,
+      "loss": 2.549,
+      "num_input_tokens_seen": 434110464,
+      "step": 414
+    },
+    {
+      "epoch": 0.8331668331668332,
+      "grad_norm": 0.2651887378629821,
+      "learning_rate": 3.3232324708877495e-06,
+      "loss": 2.53,
+      "num_input_tokens_seen": 437256192,
+      "step": 417
+    },
+    {
+      "epoch": 0.8391608391608392,
+      "grad_norm": 0.26912041453600144,
+      "learning_rate": 3.092332998903416e-06,
+      "loss": 2.5661,
+      "num_input_tokens_seen": 440401920,
+      "step": 420
+    },
+    {
+      "epoch": 0.8451548451548452,
+      "grad_norm": 0.27361462141760656,
+      "learning_rate": 2.8692172166886215e-06,
+      "loss": 2.5683,
+      "num_input_tokens_seen": 443547648,
+      "step": 423
+    },
+    {
+      "epoch": 0.8511488511488512,
+      "grad_norm": 1.5967179169743204,
+      "learning_rate": 2.6539643962184057e-06,
+      "loss": 2.5779,
+      "num_input_tokens_seen": 446693376,
+      "step": 426
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.28990640911461496,
+      "learning_rate": 2.446651015794932e-06,
+      "loss": 2.5747,
+      "num_input_tokens_seen": 449839104,
+      "step": 429
+    },
+    {
+      "epoch": 0.8631368631368631,
+      "grad_norm": 0.9256553851858104,
+      "learning_rate": 2.2473507328751086e-06,
+      "loss": 2.561,
+      "num_input_tokens_seen": 452984832,
+      "step": 432
+    },
+    {
+      "epoch": 0.8691308691308691,
+      "grad_norm": 0.25714088734318097,
+      "learning_rate": 2.0561343579004715e-06,
+      "loss": 2.4934,
+      "num_input_tokens_seen": 456130560,
+      "step": 435
+    },
+    {
+      "epoch": 0.8751248751248751,
+      "grad_norm": 0.2473113664400995,
+      "learning_rate": 1.8730698291385518e-06,
+      "loss": 2.5375,
+      "num_input_tokens_seen": 459276288,
+      "step": 438
+    },
+    {
+      "epoch": 0.8811188811188811,
+      "grad_norm": 0.2560070518729803,
+      "learning_rate": 1.6982221885447264e-06,
+      "loss": 2.567,
+      "num_input_tokens_seen": 462422016,
+      "step": 441
+    },
+    {
+      "epoch": 0.8871128871128872,
+      "grad_norm": 0.25411270477414355,
+      "learning_rate": 1.5316535586531483e-06,
+      "loss": 2.534,
+      "num_input_tokens_seen": 465567744,
+      "step": 444
+    },
+    {
+      "epoch": 0.8931068931068931,
+      "grad_norm": 0.245316303498655,
+      "learning_rate": 1.3734231205048825e-06,
+      "loss": 2.5633,
+      "num_input_tokens_seen": 468713472,
+      "step": 447
+    },
+    {
+      "epoch": 0.8991008991008991,
+      "grad_norm": 0.25577111442158357,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 2.5983,
+      "num_input_tokens_seen": 471859200,
+      "step": 450
+    },
+    {
+      "epoch": 0.9050949050949051,
+      "grad_norm": 0.24987715983476388,
+      "learning_rate": 1.0821987110292365e-06,
+      "loss": 2.5159,
+      "num_input_tokens_seen": 475004928,
+      "step": 453
+    },
+    {
+      "epoch": 0.9110889110889111,
+      "grad_norm": 0.2928702553444483,
+      "learning_rate": 9.493082103478517e-07,
+      "loss": 2.5494,
+      "num_input_tokens_seen": 478150656,
+      "step": 456
+    },
+    {
+      "epoch": 0.9170829170829171,
+      "grad_norm": 0.46592248874236003,
+      "learning_rate": 8.249628059391251e-07,
+      "loss": 2.5355,
+      "num_input_tokens_seen": 481296384,
+      "step": 459
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.243468566631608,
+      "learning_rate": 7.092066771331507e-07,
+      "loss": 2.5657,
+      "num_input_tokens_seen": 484442112,
+      "step": 462
+    },
+    {
+      "epoch": 0.929070929070929,
+      "grad_norm": 7.961659806542533,
+      "learning_rate": 6.020809515313142e-07,
+      "loss": 2.4972,
+      "num_input_tokens_seen": 487587840,
+      "step": 465
+    },
+    {
+      "epoch": 0.935064935064935,
+      "grad_norm": 0.25323615870286087,
+      "learning_rate": 5.036236903938285e-07,
+      "loss": 2.5829,
+      "num_input_tokens_seen": 490733568,
+      "step": 468
+    },
+    {
+      "epoch": 0.9410589410589411,
+      "grad_norm": 1.3275338218388306,
+      "learning_rate": 4.138698751167597e-07,
+      "loss": 2.5539,
+      "num_input_tokens_seen": 493879296,
+      "step": 471
+    },
+    {
+      "epoch": 0.9470529470529471,
+      "grad_norm": 0.25338130956442406,
+      "learning_rate": 3.328513948032991e-07,
+      "loss": 2.556,
+      "num_input_tokens_seen": 497025024,
+      "step": 474
+    },
+    {
+      "epoch": 0.9530469530469531,
+      "grad_norm": 0.25185572471784623,
+      "learning_rate": 2.605970349337267e-07,
+      "loss": 2.5357,
+      "num_input_tokens_seen": 500170752,
+      "step": 477
+    },
+    {
+      "epoch": 0.9590409590409591,
+      "grad_norm": 0.2503343662148193,
+      "learning_rate": 1.9713246713805588e-07,
+      "loss": 2.5642,
+      "num_input_tokens_seen": 503316480,
+      "step": 480
+    },
+    {
+      "epoch": 0.965034965034965,
+      "grad_norm": 0.24566222075733468,
+      "learning_rate": 1.424802400750269e-07,
+      "loss": 2.5242,
+      "num_input_tokens_seen": 506462208,
+      "step": 483
+    },
+    {
+      "epoch": 0.971028971028971,
+      "grad_norm": 0.6430300969637419,
+      "learning_rate": 9.665977142068738e-08,
+      "loss": 2.5258,
+      "num_input_tokens_seen": 509607936,
+      "step": 486
+    },
+    {
+      "epoch": 0.977022977022977,
+      "grad_norm": 0.2482610039337371,
+      "learning_rate": 5.968734096936935e-08,
+      "loss": 2.5688,
+      "num_input_tokens_seen": 512753664,
+      "step": 489
+    },
+    {
+      "epoch": 0.983016983016983,
+      "grad_norm": 0.2508965739247006,
+      "learning_rate": 3.157608484956332e-08,
+      "loss": 2.5615,
+      "num_input_tokens_seen": 515899392,
+      "step": 492
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.25067411907906484,
+      "learning_rate": 1.233599085671e-08,
+      "loss": 2.5384,
+      "num_input_tokens_seen": 519045120,
+      "step": 495
+    },
+    {
+      "epoch": 0.995004995004995,
+      "grad_norm": 3.0484827884937675,
+      "learning_rate": 1.973894904597207e-09,
+      "loss": 2.5299,
+      "num_input_tokens_seen": 522190848,
+      "step": 498
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 500,
+  "num_input_tokens_seen": 524288000,
+  "num_train_epochs": 1,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 760114185240576.0,
+  "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 sha256:2942d272ecd97d3e85db6e8561b55294881b65a56896a3a5df06b64784377378
+size 7480

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)