Add files using upload-large-folder tool

.gitattributes

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

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

latest

@@ -0,0 +1 @@
+global_step128

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b8e660a21b9b75d6b590f4f5c39ec8e12d9a9cbaa0235891272a543762f933
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df37157f450cebf1136915b159b10820bd48970f29922975704bf008d678dc13
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff3d8a5cbe10af91145da2f8983c1013d31ba20a4b99eeb844f6c36cdc63d67
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a451f70dd8bd44768fc6c2d66a02fd2bacbf38b226173f41e1b4a06d665e1f
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ad2cbc3c7a0fefa416ca212a3ca0c765342dd508d3b01b19c9bdea93628432
+size 14768

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c61f0d108ae90b8446a06c2dbbf771f253a6739aa2c4fd678b0fb6cdebbad0e5
+size 14768

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5599955f9c18cf845e77f327ca171b5415ea5761828d42a4a50471361c2db5b3
+size 14768

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c08382702ddd82a8d3c4634e3a5b6022d662094ef35784771681d2bc226bec4a
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "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:a4256422650d141f228fe954acee98679da412984c29a569877eefd3af69315a
+size 11422959

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1168 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8192,
+  "eval_steps": 500,
+  "global_step": 128,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.07638888888888888,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7457.0,
+      "completions/mean_length": 2484.15283203125,
+      "completions/mean_terminated_length": 2012.1199951171875,
+      "completions/min_length": 559.6666666666666,
+      "completions/min_terminated_length": 559.6666666666666,
+      "epoch": 0.0192,
+      "grad_norm": 0.11786151677370071,
+      "kl": 0.000663916269938151,
+      "learning_rate": 3.948717948717949e-06,
+      "loss": 0.0792,
+      "num_tokens": 736454.0,
+      "reward": 1.920138915379842,
+      "reward_std": 0.06854866879681747,
+      "rewards/accuracy_reward/mean": 0.9965277711550394,
+      "rewards/accuracy_reward/std": 0.03402068714300791,
+      "rewards/format_reward/mean": 0.9236111044883728,
+      "rewards/format_reward/std": 0.2288934737443924,
+      "step": 3
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.09027777777777779,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7337.333333333333,
+      "completions/mean_length": 2525.18408203125,
+      "completions/mean_terminated_length": 1964.8008219401042,
+      "completions/min_length": 538.0,
+      "completions/min_terminated_length": 538.0,
+      "epoch": 0.0384,
+      "grad_norm": 0.10443487018346786,
+      "kl": 0.001732190450032552,
+      "learning_rate": 3.8717948717948715e-06,
+      "loss": 0.0688,
+      "num_tokens": 1486231.0,
+      "reward": 1.90625003973643,
+      "reward_std": 0.11128650108973186,
+      "rewards/accuracy_reward/mean": 0.993055542310079,
+      "rewards/accuracy_reward/std": 0.0680413767695427,
+      "rewards/format_reward/mean": 0.9131944378217062,
+      "rewards/format_reward/std": 0.28209365407625836,
+      "step": 6
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.07638888888888891,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7734.0,
+      "completions/mean_length": 2304.361124674479,
+      "completions/mean_terminated_length": 1825.1893717447917,
+      "completions/min_length": 428.6666666666667,
+      "completions/min_terminated_length": 428.6666666666667,
+      "epoch": 0.0576,
+      "grad_norm": 0.11160896718502045,
+      "kl": 0.0075155893961588545,
+      "learning_rate": 3.7948717948717945e-06,
+      "loss": 0.0532,
+      "num_tokens": 2170377.0,
+      "reward": 1.9062500794728596,
+      "reward_std": 0.09471678485472997,
+      "rewards/accuracy_reward/mean": 0.9791666666666666,
+      "rewards/accuracy_reward/std": 0.11481705804665883,
+      "rewards/format_reward/mean": 0.9270833333333334,
+      "rewards/format_reward/std": 0.25792460640271503,
+      "step": 9
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.07986111111111112,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7192.333333333333,
+      "completions/mean_length": 2486.7847900390625,
+      "completions/mean_terminated_length": 2002.9917805989583,
+      "completions/min_length": 588.6666666666666,
+      "completions/min_terminated_length": 588.6666666666666,
+      "epoch": 0.0768,
+      "grad_norm": 0.07670364528894424,
+      "kl": 0.007045745849609375,
+      "learning_rate": 3.717948717948718e-06,
+      "loss": 0.0655,
+      "num_tokens": 2906641.0,
+      "reward": 1.9027778307596843,
+      "reward_std": 0.08286526799201965,
+      "rewards/accuracy_reward/mean": 0.9826388955116272,
+      "rewards/accuracy_reward/std": 0.12973794837792715,
+      "rewards/format_reward/mean": 0.9201388955116272,
+      "rewards/format_reward/std": 0.25063540538152057,
+      "step": 12
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.048611111111111084,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 5679.0,
+      "completions/mean_length": 2111.114705403646,
+      "completions/mean_terminated_length": 1806.3657633463542,
+      "completions/min_length": 638.3333333333334,
+      "completions/min_terminated_length": 638.3333333333334,
+      "epoch": 0.096,
+      "grad_norm": 0.08451474457979202,
+      "kl": 0.01056671142578125,
+      "learning_rate": 3.6410256410256406e-06,
+      "loss": 0.0438,
+      "num_tokens": 3534238.0,
+      "reward": 1.93750003973643,
+      "reward_std": 0.08955795814593633,
+      "rewards/accuracy_reward/mean": 0.9861111044883728,
+      "rewards/accuracy_reward/std": 0.11590000987052917,
+      "rewards/format_reward/mean": 0.9513888756434122,
+      "rewards/format_reward/std": 0.20225290457407633,
+      "step": 15
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.013888888888888876,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6870.666666666667,
+      "completions/mean_length": 1940.4757486979167,
+      "completions/mean_terminated_length": 1853.5159098307292,
+      "completions/min_length": 632.0,
+      "completions/min_terminated_length": 632.0,
+      "epoch": 0.1152,
+      "grad_norm": 0.10638942569494247,
+      "kl": 0.013872782389322916,
+      "learning_rate": 3.564102564102564e-06,
+      "loss": 0.0318,
+      "num_tokens": 4114947.0,
+      "reward": 1.9236111640930176,
+      "reward_std": 0.086211613068978,
+      "rewards/accuracy_reward/mean": 0.9340277711550394,
+      "rewards/accuracy_reward/std": 0.21398874868949255,
+      "rewards/format_reward/mean": 0.9895833134651184,
+      "rewards/format_reward/std": 0.10206206391255061,
+      "step": 18
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.041666666666666664,
+      "completions/max_length": 7178.333333333333,
+      "completions/max_terminated_length": 5503.666666666667,
+      "completions/mean_length": 2042.7118733723958,
+      "completions/mean_terminated_length": 1780.8347981770833,
+      "completions/min_length": 534.6666666666666,
+      "completions/min_terminated_length": 534.6666666666666,
+      "epoch": 0.1344,
+      "grad_norm": 0.06415776163339615,
+      "kl": 0.016947428385416668,
+      "learning_rate": 3.487179487179487e-06,
+      "loss": 0.0258,
+      "num_tokens": 4722190.0,
+      "reward": 1.9236111640930176,
+      "reward_std": 0.03402068962653478,
+      "rewards/accuracy_reward/mean": 0.9548611243565878,
+      "rewards/accuracy_reward/std": 0.15458878378073374,
+      "rewards/format_reward/mean": 0.96875,
+      "rewards/format_reward/std": 0.12663276741902033,
+      "step": 21
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.045138888888888916,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7599.333333333333,
+      "completions/mean_length": 2192.9861653645835,
+      "completions/mean_terminated_length": 1915.0709635416667,
+      "completions/min_length": 501.6666666666667,
+      "completions/min_terminated_length": 501.6666666666667,
+      "epoch": 0.1536,
+      "grad_norm": 0.08798938244581223,
+      "kl": 0.02048492431640625,
+      "learning_rate": 3.41025641025641e-06,
+      "loss": 0.0258,
+      "num_tokens": 5379972.0,
+      "reward": 1.8645833730697632,
+      "reward_std": 0.09762249266107877,
+      "rewards/accuracy_reward/mean": 0.9027777711550394,
+      "rewards/accuracy_reward/std": 0.286453440785408,
+      "rewards/format_reward/mean": 0.9618055621782938,
+      "rewards/format_reward/std": 0.18727133671442667,
+      "step": 24
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.020833333333333332,
+      "completions/max_length": 7410.0,
+      "completions/max_terminated_length": 6817.666666666667,
+      "completions/mean_length": 2016.982666015625,
+      "completions/mean_terminated_length": 1887.3319091796875,
+      "completions/min_length": 514.0,
+      "completions/min_terminated_length": 514.0,
+      "epoch": 0.1728,
+      "grad_norm": 0.10734036564826965,
+      "kl": 0.0256195068359375,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0323,
+      "num_tokens": 5984941.0,
+      "reward": 1.8993055820465088,
+      "reward_std": 0.10998130093018214,
+      "rewards/accuracy_reward/mean": 0.9201388955116272,
+      "rewards/accuracy_reward/std": 0.2663828631242116,
+      "rewards/format_reward/mean": 0.9791666666666666,
+      "rewards/format_reward/std": 0.10847451289494832,
+      "step": 27
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7886.666666666667,
+      "completions/mean_length": 2276.7084147135415,
+      "completions/mean_terminated_length": 2084.757283528646,
+      "completions/min_length": 573.6666666666666,
+      "completions/min_terminated_length": 573.6666666666666,
+      "epoch": 0.192,
+      "grad_norm": 0.09922217577695847,
+      "kl": 0.022427876790364582,
+      "learning_rate": 3.2564102564102564e-06,
+      "loss": 0.0182,
+      "num_tokens": 6662305.0,
+      "reward": 1.8333333730697632,
+      "reward_std": 0.1692849819858869,
+      "rewards/accuracy_reward/mean": 0.875,
+      "rewards/accuracy_reward/std": 0.31955354909102124,
+      "rewards/format_reward/mean": 0.9583333333333334,
+      "rewards/format_reward/std": 0.197714701294899,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 6856.333333333333,
+      "completions/max_terminated_length": 5939.666666666667,
+      "completions/mean_length": 2417.1563313802085,
+      "completions/mean_terminated_length": 2233.5343424479165,
+      "completions/min_length": 661.3333333333334,
+      "completions/min_terminated_length": 661.3333333333334,
+      "epoch": 0.2112,
+      "grad_norm": 0.13434383273124695,
+      "kl": 0.019597371419270832,
+      "learning_rate": 3.179487179487179e-06,
+      "loss": 0.0666,
+      "num_tokens": 7382296.0,
+      "reward": 1.87500003973643,
+      "reward_std": 0.14174887910485268,
+      "rewards/accuracy_reward/mean": 0.90625,
+      "rewards/accuracy_reward/std": 0.27019980053106946,
+      "rewards/format_reward/mean": 0.96875,
+      "rewards/format_reward/std": 0.1349801371494929,
+      "step": 33
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.010416666666666666,
+      "completions/max_length": 6942.666666666667,
+      "completions/max_terminated_length": 6595.333333333333,
+      "completions/mean_length": 1717.2361653645833,
+      "completions/mean_terminated_length": 1649.8081461588542,
+      "completions/min_length": 371.3333333333333,
+      "completions/min_terminated_length": 371.3333333333333,
+      "epoch": 0.2304,
+      "grad_norm": 0.11780474334955215,
+      "kl": 0.028951009114583332,
+      "learning_rate": 3.1025641025641025e-06,
+      "loss": 0.0318,
+      "num_tokens": 7898124.0,
+      "reward": 1.9409722884496052,
+      "reward_std": 0.08892839774489403,
+      "rewards/accuracy_reward/mean": 0.9652777910232544,
+      "rewards/accuracy_reward/std": 0.17682797213395438,
+      "rewards/format_reward/mean": 0.975694457689921,
+      "rewards/format_reward/std": 0.15401925643285116,
+      "step": 36
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.045138888888888874,
+      "completions/max_length": 7901.0,
+      "completions/max_terminated_length": 7665.0,
+      "completions/mean_length": 1984.8681233723958,
+      "completions/mean_terminated_length": 1685.4075520833333,
+      "completions/min_length": 326.3333333333333,
+      "completions/min_terminated_length": 326.3333333333333,
+      "epoch": 0.2496,
+      "grad_norm": 0.1302698850631714,
+      "kl": 0.0289154052734375,
+      "learning_rate": 3.0256410256410256e-06,
+      "loss": 0.0366,
+      "num_tokens": 8500984.0,
+      "reward": 1.8715278307596843,
+      "reward_std": 0.13606221228837967,
+      "rewards/accuracy_reward/mean": 0.9270833333333334,
+      "rewards/accuracy_reward/std": 0.25223057965437573,
+      "rewards/format_reward/mean": 0.9444444378217062,
+      "rewards/format_reward/std": 0.2128016253312429,
+      "step": 39
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.02430555555555558,
+      "completions/max_length": 6943.666666666667,
+      "completions/max_terminated_length": 6541.0,
+      "completions/mean_length": 1753.7569986979167,
+      "completions/mean_terminated_length": 1596.4458414713542,
+      "completions/min_length": 336.0,
+      "completions/min_terminated_length": 336.0,
+      "epoch": 0.2688,
+      "grad_norm": 0.12249383330345154,
+      "kl": 0.030186971028645832,
+      "learning_rate": 2.9487179487179486e-06,
+      "loss": 0.0353,
+      "num_tokens": 9033138.0,
+      "reward": 1.8680555820465088,
+      "reward_std": 0.19277991354465485,
+      "rewards/accuracy_reward/mean": 0.906250019868215,
+      "rewards/accuracy_reward/std": 0.29195430874824524,
+      "rewards/format_reward/mean": 0.961805542310079,
+      "rewards/format_reward/std": 0.18208982795476913,
+      "step": 42
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.027777777777777752,
+      "completions/max_length": 7697.333333333333,
+      "completions/max_terminated_length": 6401.666666666667,
+      "completions/mean_length": 1648.7222493489583,
+      "completions/mean_terminated_length": 1464.5533447265625,
+      "completions/min_length": 229.66666666666666,
+      "completions/min_terminated_length": 229.66666666666666,
+      "epoch": 0.288,
+      "grad_norm": 0.1356375366449356,
+      "kl": 0.034571329752604164,
+      "learning_rate": 2.8717948717948717e-06,
+      "loss": 0.0566,
+      "num_tokens": 9541138.0,
+      "reward": 1.87500003973643,
+      "reward_std": 0.14326218763987222,
+      "rewards/accuracy_reward/mean": 0.9236111044883728,
+      "rewards/accuracy_reward/std": 0.24128751705090204,
+      "rewards/format_reward/mean": 0.9513888955116272,
+      "rewards/format_reward/std": 0.17212405304114023,
+      "step": 45
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.059027777777777755,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7894.0,
+      "completions/mean_length": 2024.1111653645833,
+      "completions/mean_terminated_length": 1630.966552734375,
+      "completions/min_length": 298.3333333333333,
+      "completions/min_terminated_length": 298.3333333333333,
+      "epoch": 0.3072,
+      "grad_norm": 0.14614339172840118,
+      "kl": 0.033233642578125,
+      "learning_rate": 2.7948717948717948e-06,
+      "loss": 0.0668,
+      "num_tokens": 10152390.0,
+      "reward": 1.8819444974263508,
+      "reward_std": 0.14595978458722433,
+      "rewards/accuracy_reward/mean": 0.9479166666666666,
+      "rewards/accuracy_reward/std": 0.2198773274819056,
+      "rewards/format_reward/mean": 0.9340277711550394,
+      "rewards/format_reward/std": 0.24177277584870657,
+      "step": 48
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 8080.333333333333,
+      "completions/max_terminated_length": 6668.333333333333,
+      "completions/mean_length": 2075.5382486979165,
+      "completions/mean_terminated_length": 1875.0848795572917,
+      "completions/min_length": 313.0,
+      "completions/min_terminated_length": 313.0,
+      "epoch": 0.3264,
+      "grad_norm": 0.13130497932434082,
+      "kl": 0.029052734375,
+      "learning_rate": 2.717948717948718e-06,
+      "loss": 0.0391,
+      "num_tokens": 10781333.0,
+      "reward": 1.8715277910232544,
+      "reward_std": 0.173075832426548,
+      "rewards/accuracy_reward/mean": 0.9131944378217062,
+      "rewards/accuracy_reward/std": 0.27422525485356647,
+      "rewards/format_reward/mean": 0.9583333532015482,
+      "rewards/format_reward/std": 0.18832933902740479,
+      "step": 51
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.03472222222222221,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6894.666666666667,
+      "completions/mean_length": 1978.5972900390625,
+      "completions/mean_terminated_length": 1754.5013020833333,
+      "completions/min_length": 291.0,
+      "completions/min_terminated_length": 291.0,
+      "epoch": 0.3456,
+      "grad_norm": 0.11747946590185165,
+      "kl": 0.025873819986979168,
+      "learning_rate": 2.641025641025641e-06,
+      "loss": 0.0452,
+      "num_tokens": 11385513.0,
+      "reward": 1.8368055820465088,
+      "reward_std": 0.1378952513138453,
+      "rewards/accuracy_reward/mean": 0.8819444378217062,
+      "rewards/accuracy_reward/std": 0.3174315243959427,
+      "rewards/format_reward/mean": 0.9548611243565878,
+      "rewards/format_reward/std": 0.20342316726843515,
+      "step": 54
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.013888888888888876,
+      "completions/max_length": 7534.0,
+      "completions/max_terminated_length": 7530.666666666667,
+      "completions/mean_length": 1764.263916015625,
+      "completions/mean_terminated_length": 1680.0013834635417,
+      "completions/min_length": 283.0,
+      "completions/min_terminated_length": 283.0,
+      "epoch": 0.3648,
+      "grad_norm": 0.12080682069063187,
+      "kl": 0.032323201497395836,
+      "learning_rate": 2.5641025641025644e-06,
+      "loss": 0.0415,
+      "num_tokens": 11918815.0,
+      "reward": 1.864583412806193,
+      "reward_std": 0.17177063475052515,
+      "rewards/accuracy_reward/mean": 0.9027777711550394,
+      "rewards/accuracy_reward/std": 0.28834333022435504,
+      "rewards/format_reward/mean": 0.961805542310079,
+      "rewards/format_reward/std": 0.1363807593782743,
+      "step": 57
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.048611111111111126,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6987.666666666667,
+      "completions/mean_length": 2011.3229573567708,
+      "completions/mean_terminated_length": 1690.6886393229167,
+      "completions/min_length": 294.0,
+      "completions/min_terminated_length": 294.0,
+      "epoch": 0.384,
+      "grad_norm": 0.12239208817481995,
+      "kl": 0.030438741048177082,
+      "learning_rate": 2.487179487179487e-06,
+      "loss": 0.0768,
+      "num_tokens": 12522634.0,
+      "reward": 1.8854167064030964,
+      "reward_std": 0.15016684432824454,
+      "rewards/accuracy_reward/mean": 0.9409722089767456,
+      "rewards/accuracy_reward/std": 0.23519064486026764,
+      "rewards/format_reward/mean": 0.944444457689921,
+      "rewards/format_reward/std": 0.22536789874235788,
+      "step": 60
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.034722222222222245,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6971.333333333333,
+      "completions/mean_length": 2042.4896647135417,
+      "completions/mean_terminated_length": 1825.8701578776042,
+      "completions/min_length": 314.0,
+      "completions/min_terminated_length": 314.0,
+      "epoch": 0.4032,
+      "grad_norm": 0.10179228335618973,
+      "kl": 0.031634012858072914,
+      "learning_rate": 2.41025641025641e-06,
+      "loss": 0.0337,
+      "num_tokens": 13138633.0,
+      "reward": 1.8541667064030964,
+      "reward_std": 0.20934962232907614,
+      "rewards/accuracy_reward/mean": 0.8958333333333334,
+      "rewards/accuracy_reward/std": 0.3057904740174611,
+      "rewards/format_reward/mean": 0.9583333333333334,
+      "rewards/format_reward/std": 0.197714701294899,
+      "step": 63
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.038194444444444454,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7261.666666666667,
+      "completions/mean_length": 1903.9722493489583,
+      "completions/mean_terminated_length": 1650.5534261067708,
+      "completions/min_length": 227.66666666666666,
+      "completions/min_terminated_length": 227.66666666666666,
+      "epoch": 0.4224,
+      "grad_norm": 0.10856553167104721,
+      "kl": 0.031336466471354164,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 0.0397,
+      "num_tokens": 13714469.0,
+      "reward": 1.8819444576899211,
+      "reward_std": 0.15875921150048575,
+      "rewards/accuracy_reward/mean": 0.9270833333333334,
+      "rewards/accuracy_reward/std": 0.2572407325108846,
+      "rewards/format_reward/mean": 0.9548611044883728,
+      "rewards/format_reward/std": 0.19624211142460504,
+      "step": 66
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.038194444444444454,
+      "completions/max_length": 7431.666666666667,
+      "completions/max_terminated_length": 7204.666666666667,
+      "completions/mean_length": 1631.7222900390625,
+      "completions/mean_terminated_length": 1369.1958414713542,
+      "completions/min_length": 245.0,
+      "completions/min_terminated_length": 245.0,
+      "epoch": 0.4416,
+      "grad_norm": 0.11824989318847656,
+      "kl": 0.03619384765625,
+      "learning_rate": 2.2564102564102562e-06,
+      "loss": 0.0374,
+      "num_tokens": 14208711.0,
+      "reward": 1.81250003973643,
+      "reward_std": 0.16117709378401437,
+      "rewards/accuracy_reward/mean": 0.8611111044883728,
+      "rewards/accuracy_reward/std": 0.3456921974817912,
+      "rewards/format_reward/mean": 0.9513888955116272,
+      "rewards/format_reward/std": 0.20108659317096075,
+      "step": 69
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.041666666666666664,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6924.666666666667,
+      "completions/mean_length": 1506.6423746744792,
+      "completions/mean_terminated_length": 1216.2833251953125,
+      "completions/min_length": 246.0,
+      "completions/min_terminated_length": 246.0,
+      "epoch": 0.4608,
+      "grad_norm": 0.1255887746810913,
+      "kl": 0.053243001302083336,
+      "learning_rate": 2.1794871794871793e-06,
+      "loss": 0.0383,
+      "num_tokens": 14664410.0,
+      "reward": 1.9236111640930176,
+      "reward_std": 0.10031624138355255,
+      "rewards/accuracy_reward/mean": 0.9548611044883728,
+      "rewards/accuracy_reward/std": 0.2063711335261663,
+      "rewards/format_reward/mean": 0.968749980131785,
+      "rewards/format_reward/std": 0.16793753455082575,
+      "step": 72
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.024305555555555542,
+      "completions/max_length": 7341.0,
+      "completions/max_terminated_length": 7337.666666666667,
+      "completions/mean_length": 1445.312520345052,
+      "completions/mean_terminated_length": 1281.9166463216145,
+      "completions/min_length": 166.66666666666666,
+      "completions/min_terminated_length": 166.66666666666666,
+      "epoch": 0.48,
+      "grad_norm": 0.14921000599861145,
+      "kl": 0.042795817057291664,
+      "learning_rate": 2.1025641025641023e-06,
+      "loss": 0.036,
+      "num_tokens": 15103004.0,
+      "reward": 1.87500003973643,
+      "reward_std": 0.11799862856666248,
+      "rewards/accuracy_reward/mean": 0.9027777711550394,
+      "rewards/accuracy_reward/std": 0.28232812881469727,
+      "rewards/format_reward/mean": 0.9722222089767456,
+      "rewards/format_reward/std": 0.1211421936750412,
+      "step": 75
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.045138888888888874,
+      "completions/max_length": 7986.666666666667,
+      "completions/max_terminated_length": 7702.333333333333,
+      "completions/mean_length": 1538.5555826822917,
+      "completions/mean_terminated_length": 1232.4976399739583,
+      "completions/min_length": 201.0,
+      "completions/min_terminated_length": 201.0,
+      "epoch": 0.4992,
+      "grad_norm": 0.09636721014976501,
+      "kl": 0.04656982421875,
+      "learning_rate": 2.0256410256410254e-06,
+      "loss": 0.0377,
+      "num_tokens": 15574308.0,
+      "reward": 1.87500003973643,
+      "reward_std": 0.10612767189741135,
+      "rewards/accuracy_reward/mean": 0.9166666666666666,
+      "rewards/accuracy_reward/std": 0.26633305847644806,
+      "rewards/format_reward/mean": 0.9583333333333334,
+      "rewards/format_reward/std": 0.16222142179807028,
+      "step": 78
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.038194444444444454,
+      "completions/max_length": 8137.666666666667,
+      "completions/max_terminated_length": 7975.0,
+      "completions/mean_length": 1834.2222900390625,
+      "completions/mean_terminated_length": 1581.649169921875,
+      "completions/min_length": 203.0,
+      "completions/min_terminated_length": 203.0,
+      "epoch": 0.5184,
+      "grad_norm": 0.9437447786331177,
+      "kl": 0.051630655924479164,
+      "learning_rate": 1.9487179487179485e-06,
+      "loss": 0.0323,
+      "num_tokens": 16131508.0,
+      "reward": 1.8506944974263508,
+      "reward_std": 0.13935044904549918,
+      "rewards/accuracy_reward/mean": 0.8923611044883728,
+      "rewards/accuracy_reward/std": 0.30875815947850543,
+      "rewards/format_reward/mean": 0.9583333333333334,
+      "rewards/format_reward/std": 0.18958522379398346,
+      "step": 81
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.045138888888888916,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7797.666666666667,
+      "completions/mean_length": 1368.4097900390625,
+      "completions/mean_terminated_length": 1047.0757649739583,
+      "completions/min_length": 174.33333333333334,
+      "completions/min_terminated_length": 174.33333333333334,
+      "epoch": 0.5376,
+      "grad_norm": 0.12685449421405792,
+      "kl": 0.043909708658854164,
+      "learning_rate": 1.8717948717948718e-06,
+      "loss": 0.0486,
+      "num_tokens": 16552250.0,
+      "reward": 1.9166667064030964,
+      "reward_std": 0.08621161431074142,
+      "rewards/accuracy_reward/mean": 0.9583333333333334,
+      "rewards/accuracy_reward/std": 0.19592776894569397,
+      "rewards/format_reward/mean": 0.9583333333333334,
+      "rewards/format_reward/std": 0.18958522627751032,
+      "step": 84
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00694444444444442,
+      "completions/max_length": 8058.0,
+      "completions/max_terminated_length": 7524.0,
+      "completions/mean_length": 1276.295166015625,
+      "completions/mean_terminated_length": 1228.2986246744792,
+      "completions/min_length": 176.33333333333334,
+      "completions/min_terminated_length": 176.33333333333334,
+      "epoch": 0.5568,
+      "grad_norm": 0.10477358847856522,
+      "kl": 0.041203816731770836,
+      "learning_rate": 1.7948717948717948e-06,
+      "loss": 0.03,
+      "num_tokens": 16944123.0,
+      "reward": 1.93750003973643,
+      "reward_std": 0.0895579606294632,
+      "rewards/accuracy_reward/mean": 0.9513888955116272,
+      "rewards/accuracy_reward/std": 0.21386653184890747,
+      "rewards/format_reward/mean": 0.9861111044883728,
+      "rewards/format_reward/std": 0.11590000490347545,
+      "step": 87
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.048611111111111126,
+      "completions/max_length": 7305.0,
+      "completions/max_terminated_length": 6282.333333333333,
+      "completions/mean_length": 1492.5034993489583,
+      "completions/mean_terminated_length": 1149.2331136067708,
+      "completions/min_length": 252.0,
+      "completions/min_terminated_length": 252.0,
+      "epoch": 0.576,
+      "grad_norm": 0.13828961551189423,
+      "kl": 0.037953694661458336,
+      "learning_rate": 1.7179487179487177e-06,
+      "loss": 0.0362,
+      "num_tokens": 17398714.0,
+      "reward": 1.8854167064030964,
+      "reward_std": 0.10882141316930453,
+      "rewards/accuracy_reward/mean": 0.9375,
+      "rewards/accuracy_reward/std": 0.24268604318300882,
+      "rewards/format_reward/mean": 0.9479166666666666,
+      "rewards/format_reward/std": 0.17973358432451883,
+      "step": 90
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7929.0,
+      "completions/mean_length": 1596.2466227213542,
+      "completions/mean_terminated_length": 1390.1203206380208,
+      "completions/min_length": 207.0,
+      "completions/min_terminated_length": 207.0,
+      "epoch": 0.5952,
+      "grad_norm": 0.10115975886583328,
+      "kl": 0.037958780924479164,
+      "learning_rate": 1.641025641025641e-06,
+      "loss": 0.0531,
+      "num_tokens": 17882805.0,
+      "reward": 1.8784722487131755,
+      "reward_std": 0.08846472824613254,
+      "rewards/accuracy_reward/mean": 0.906250019868215,
+      "rewards/accuracy_reward/std": 0.28532982369263965,
+      "rewards/format_reward/mean": 0.9722222288449606,
+      "rewards/format_reward/std": 0.1563331459959348,
+      "step": 93
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.03472222222222221,
+      "completions/max_length": 6898.333333333333,
+      "completions/max_terminated_length": 6688.666666666667,
+      "completions/mean_length": 1595.3646647135417,
+      "completions/mean_terminated_length": 1364.8641357421875,
+      "completions/min_length": 208.66666666666666,
+      "completions/min_terminated_length": 208.66666666666666,
+      "epoch": 0.6144,
+      "grad_norm": 0.08329301327466965,
+      "kl": 0.038645426432291664,
+      "learning_rate": 1.564102564102564e-06,
+      "loss": 0.0404,
+      "num_tokens": 18366630.0,
+      "reward": 1.9097222884496052,
+      "reward_std": 0.1264843593041102,
+      "rewards/accuracy_reward/mean": 0.9513888756434122,
+      "rewards/accuracy_reward/std": 0.21502756575743356,
+      "rewards/format_reward/mean": 0.9583333333333334,
+      "rewards/format_reward/std": 0.18493476013342539,
+      "step": 96
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.038194444444444454,
+      "completions/max_length": 7504.666666666667,
+      "completions/max_terminated_length": 6996.0,
+      "completions/mean_length": 1620.4861246744792,
+      "completions/mean_terminated_length": 1355.0765380859375,
+      "completions/min_length": 182.66666666666666,
+      "completions/min_terminated_length": 182.66666666666666,
+      "epoch": 0.6336,
+      "grad_norm": 0.07651077955961227,
+      "kl": 0.038045247395833336,
+      "learning_rate": 1.487179487179487e-06,
+      "loss": 0.0408,
+      "num_tokens": 18857216.0,
+      "reward": 1.9131944576899211,
+      "reward_std": 0.03627380480368932,
+      "rewards/accuracy_reward/mean": 0.9479166666666666,
+      "rewards/accuracy_reward/std": 0.19905283798774084,
+      "rewards/format_reward/mean": 0.9652777711550394,
+      "rewards/format_reward/std": 0.13169091691573462,
+      "step": 99
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.038194444444444454,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7569.0,
+      "completions/mean_length": 1601.21533203125,
+      "completions/mean_terminated_length": 1339.799072265625,
+      "completions/min_length": 140.33333333333334,
+      "completions/min_terminated_length": 140.33333333333334,
+      "epoch": 0.6528,
+      "grad_norm": 0.1341271549463272,
+      "kl": 0.035313924153645836,
+      "learning_rate": 1.4102564102564104e-06,
+      "loss": 0.0451,
+      "num_tokens": 19348528.0,
+      "reward": 1.87500003973643,
+      "reward_std": 0.14174888034661612,
+      "rewards/accuracy_reward/mean": 0.9270833333333334,
+      "rewards/accuracy_reward/std": 0.26084429522355396,
+      "rewards/format_reward/mean": 0.9479166666666666,
+      "rewards/format_reward/std": 0.22252296408017477,
+      "step": 102
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.045138888888888874,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7510.666666666667,
+      "completions/mean_length": 1486.263916015625,
+      "completions/mean_terminated_length": 1165.8067626953125,
+      "completions/min_length": 135.33333333333334,
+      "completions/min_terminated_length": 135.33333333333334,
+      "epoch": 0.672,
+      "grad_norm": 0.11015435308218002,
+      "kl": 0.034245808919270836,
+      "learning_rate": 1.3333333333333332e-06,
+      "loss": 0.0214,
+      "num_tokens": 19798676.0,
+      "reward": 1.9166667064030964,
+      "reward_std": 0.0998756115635236,
+      "rewards/accuracy_reward/mean": 0.961805542310079,
+      "rewards/accuracy_reward/std": 0.19221885005633035,
+      "rewards/format_reward/mean": 0.9548611044883728,
+      "rewards/format_reward/std": 0.20372549692789713,
+      "step": 105
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 7331.0,
+      "completions/max_terminated_length": 7054.666666666667,
+      "completions/mean_length": 1494.9896647135417,
+      "completions/mean_terminated_length": 1280.5859375,
+      "completions/min_length": 221.0,
+      "completions/min_terminated_length": 221.0,
+      "epoch": 0.6912,
+      "grad_norm": 0.11232707649469376,
+      "kl": 0.0319671630859375,
+      "learning_rate": 1.2564102564102563e-06,
+      "loss": 0.0022,
+      "num_tokens": 20265089.0,
+      "reward": 1.8819444974263508,
+      "reward_std": 0.10322195539871852,
+      "rewards/accuracy_reward/mean": 0.9166666666666666,
+      "rewards/accuracy_reward/std": 0.27038883169492084,
+      "rewards/format_reward/mean": 0.9652777711550394,
+      "rewards/format_reward/std": 0.1454235017299652,
+      "step": 108
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.045138888888888874,
+      "completions/max_length": 7708.333333333333,
+      "completions/max_terminated_length": 6119.333333333333,
+      "completions/mean_length": 1444.1944580078125,
+      "completions/mean_terminated_length": 1120.3043619791667,
+      "completions/min_length": 238.33333333333334,
+      "completions/min_terminated_length": 238.33333333333334,
+      "epoch": 0.7104,
+      "grad_norm": 0.09397315979003906,
+      "kl": 0.029179890950520832,
+      "learning_rate": 1.1794871794871795e-06,
+      "loss": 0.0349,
+      "num_tokens": 20706937.0,
+      "reward": 1.9027778307596843,
+      "reward_std": 0.0833058978120486,
+      "rewards/accuracy_reward/mean": 0.937499980131785,
+      "rewards/accuracy_reward/std": 0.24120144049326578,
+      "rewards/format_reward/mean": 0.9652777711550394,
+      "rewards/format_reward/std": 0.1454235017299652,
+      "step": 111
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.09027777777777779,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7374.666666666667,
+      "completions/mean_length": 1775.2361653645833,
+      "completions/mean_terminated_length": 1136.4374389648438,
+      "completions/min_length": 140.33333333333334,
+      "completions/min_terminated_length": 140.33333333333334,
+      "epoch": 0.7296,
+      "grad_norm": 0.17233380675315857,
+      "kl": 0.0392608642578125,
+      "learning_rate": 1.1025641025641026e-06,
+      "loss": 0.0398,
+      "num_tokens": 21245775.0,
+      "reward": 1.8645833730697632,
+      "reward_std": 0.10707558691501617,
+      "rewards/accuracy_reward/mean": 0.9513888756434122,
+      "rewards/accuracy_reward/std": 0.21238192915916443,
+      "rewards/format_reward/mean": 0.913194457689921,
+      "rewards/format_reward/std": 0.27788423001766205,
+      "step": 114
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.05902777777777779,
+      "completions/max_length": 7707.333333333333,
+      "completions/max_terminated_length": 6991.333333333333,
+      "completions/mean_length": 1498.5417073567708,
+      "completions/mean_terminated_length": 1070.8243408203125,
+      "completions/min_length": 130.0,
+      "completions/min_terminated_length": 130.0,
+      "epoch": 0.7488,
+      "grad_norm": 0.10053375363349915,
+      "kl": 0.030309041341145832,
+      "learning_rate": 1.0256410256410255e-06,
+      "loss": 0.0379,
+      "num_tokens": 21700377.0,
+      "reward": 1.8506944974263508,
+      "reward_std": 0.1034339318672816,
+      "rewards/accuracy_reward/mean": 0.9097222288449606,
+      "rewards/accuracy_reward/std": 0.2692435334126155,
+      "rewards/format_reward/mean": 0.9409722288449606,
+      "rewards/format_reward/std": 0.18527215222517648,
+      "step": 117
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 8080.333333333333,
+      "completions/max_terminated_length": 8074.0,
+      "completions/mean_length": 1560.0416666666667,
+      "completions/mean_terminated_length": 1113.6520182291667,
+      "completions/min_length": 227.0,
+      "completions/min_terminated_length": 227.0,
+      "epoch": 0.768,
+      "grad_norm": 0.09212761372327805,
+      "kl": 0.033299763997395836,
+      "learning_rate": 9.487179487179486e-07,
+      "loss": 0.0356,
+      "num_tokens": 22176393.0,
+      "reward": 1.90625003973643,
+      "reward_std": 0.09762249638636906,
+      "rewards/accuracy_reward/mean": 0.9583333333333334,
+      "rewards/accuracy_reward/std": 0.197714701294899,
+      "rewards/format_reward/mean": 0.9479166666666666,
+      "rewards/format_reward/std": 0.1926976442337036,
+      "step": 120
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.052083333333333336,
+      "completions/max_length": 7240.0,
+      "completions/max_terminated_length": 6940.666666666667,
+      "completions/mean_length": 1487.6284993489583,
+      "completions/mean_terminated_length": 1119.332051595052,
+      "completions/min_length": 180.66666666666666,
+      "completions/min_terminated_length": 180.66666666666666,
+      "epoch": 0.7872,
+      "grad_norm": 0.1242799237370491,
+      "kl": 0.03277587890625,
+      "learning_rate": 8.717948717948718e-07,
+      "loss": 0.0342,
+      "num_tokens": 22636012.0,
+      "reward": 1.857638915379842,
+      "reward_std": 0.10882141441106796,
+      "rewards/accuracy_reward/mean": 0.9166666666666666,
+      "rewards/accuracy_reward/std": 0.23966746032238007,
+      "rewards/format_reward/mean": 0.9409722288449606,
+      "rewards/format_reward/std": 0.18527215222517648,
+      "step": 123
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.06597222222222221,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6789.333333333333,
+      "completions/mean_length": 1534.1597493489583,
+      "completions/mean_terminated_length": 1059.709248860677,
+      "completions/min_length": 198.0,
+      "completions/min_terminated_length": 198.0,
+      "epoch": 0.8064,
+      "grad_norm": 0.09035886079072952,
+      "kl": 0.034245808919270836,
+      "learning_rate": 7.948717948717948e-07,
+      "loss": 0.0458,
+      "num_tokens": 23103896.0,
+      "reward": 1.8854167064030964,
+      "reward_std": 0.1067802719771862,
+      "rewards/accuracy_reward/mean": 0.9583333333333334,
+      "rewards/accuracy_reward/std": 0.18493476261695227,
+      "rewards/format_reward/mean": 0.9270833134651184,
+      "rewards/format_reward/std": 0.2387408266464869,
+      "step": 126
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 156,
+  "num_input_tokens_seen": 23493835,
+  "num_train_epochs": 1,
+  "save_steps": 32,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db38230b28081e24464a87f7c4d5240f139856cb1aee7a42ebf5f6c3efc93bc2
+size 7864

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)