Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "./trained_model_rl/checkpoint-624/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0.dev0"
+}

latest

@@ -0,0 +1 @@
+global_step624

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a716a02a1a0f31c7773bb79efdd0377f2a37ed9cfec8d976caaff550c0ea34e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cd10e172f61009da7365efa1d2b34ea0be1d8a7289f17f38d682e939b021e8
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34432c000cfc6cc0d24ddf48d86b40c23531aea9b2caa12f3ae617d018e59e21
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17c869c3686a23dffcb3f51c65fa7c1192067b51f83ae69f3051e877ff3380f
+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 sha256:937c41c0701130fb22eb307ca68407018e6f872a1e1348331a87a55b7e9267e9
+size 15472

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74fc6dd4be9a3865fa0f15e4989d51cf8bb6b5b4de5ea73c4a68132e9356c2b
+size 15472

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:358212cfa5a0acfd8c0a67b81a2cf3c1a1fa834c03835be43f1daddd2731f8da
+size 15472

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aaee7d3aa960e4dfda0d4b6726c8ad2e05ea05fc2ee13db78c3862ac1289919
+size 15536

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20e1f66ebc7b28d05653a4bf3aa9099cf5edf64a18fd5a19c26040e13812b8a
+size 15472

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ebed27ec9f94e6df4a1d6a99197b07114431f19dfadeb5c941d2816622a09a1
+size 15472

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5c77309d27dc77cfdd6c8be3c8aa8c6dfe4e30af15f780b3c630a4c207fdce
+size 1064

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,212 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 131072,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,901 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9984,
+  "eval_steps": 500,
+  "global_step": 624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1090.0166961669922,
+      "epoch": 0.032,
+      "grad_norm": 1.3739021378163432,
+      "kl": 0.011310577392578125,
+      "learning_rate": 2.951923076923077e-06,
+      "loss": 0.0005,
+      "num_tokens": 1218701.0,
+      "reward": 1.3793484151363373,
+      "reward_std": 0.24156477563083173,
+      "rewards/reward_func": 1.379348385334015,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1187.3583862304688,
+      "epoch": 0.064,
+      "grad_norm": 1.2407170709125623,
+      "kl": 0.05146484375,
+      "learning_rate": 2.903846153846154e-06,
+      "loss": 0.0021,
+      "num_tokens": 2492712.0,
+      "reward": 1.4012527942657471,
+      "reward_std": 0.232261598482728,
+      "rewards/reward_func": 1.4012527465820312,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1193.7833740234375,
+      "epoch": 0.096,
+      "grad_norm": 1.6332710755623894,
+      "kl": 0.0868896484375,
+      "learning_rate": 2.8557692307692307e-06,
+      "loss": 0.0035,
+      "num_tokens": 3763792.0,
+      "reward": 1.3906624972820283,
+      "reward_std": 0.2509541690349579,
+      "rewards/reward_func": 1.3906624555587768,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1147.8333679199218,
+      "epoch": 0.128,
+      "grad_norm": 1.1957910220069445,
+      "kl": 0.11298828125,
+      "learning_rate": 2.807692307692308e-06,
+      "loss": 0.0045,
+      "num_tokens": 5019020.0,
+      "reward": 1.3979449570178986,
+      "reward_std": 0.24268287047743797,
+      "rewards/reward_func": 1.3979449152946473,
+      "step": 40
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1035.5166961669922,
+      "epoch": 0.16,
+      "grad_norm": 1.2514751954183139,
+      "kl": 0.148388671875,
+      "learning_rate": 2.7596153846153844e-06,
+      "loss": 0.0059,
+      "num_tokens": 6212869.0,
+      "reward": 1.4058575332164764,
+      "reward_std": 0.20526219047605992,
+      "rewards/reward_func": 1.4058574855327606,
+      "step": 50
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1127.416696166992,
+      "epoch": 0.192,
+      "grad_norm": 1.1179435424314572,
+      "kl": 0.16640625,
+      "learning_rate": 2.7115384615384617e-06,
+      "loss": 0.0067,
+      "num_tokens": 7461579.0,
+      "reward": 1.3581139743328094,
+      "reward_std": 0.20967118199914694,
+      "rewards/reward_func": 1.3581139326095581,
+      "step": 60
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1225.225033569336,
+      "epoch": 0.224,
+      "grad_norm": 1.0602733950469436,
+      "kl": 0.17060546875,
+      "learning_rate": 2.6634615384615385e-06,
+      "loss": 0.0068,
+      "num_tokens": 8750799.0,
+      "reward": 1.394177681207657,
+      "reward_std": 0.20445052348077297,
+      "rewards/reward_func": 1.394177633523941,
+      "step": 70
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1162.0917053222656,
+      "epoch": 0.256,
+      "grad_norm": 1.1076761293627495,
+      "kl": 0.19599609375,
+      "learning_rate": 2.6153846153846154e-06,
+      "loss": 0.0078,
+      "num_tokens": 10014725.0,
+      "reward": 1.406614112854004,
+      "reward_std": 0.17760551236569883,
+      "rewards/reward_func": 1.4066140830516816,
+      "step": 80
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1248.1833862304688,
+      "epoch": 0.288,
+      "grad_norm": 1.0403097644790908,
+      "kl": 0.204150390625,
+      "learning_rate": 2.5673076923076923e-06,
+      "loss": 0.0082,
+      "num_tokens": 11313051.0,
+      "reward": 1.3719308912754058,
+      "reward_std": 0.19940033443272115,
+      "rewards/reward_func": 1.371930855512619,
+      "step": 90
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1225.9083618164063,
+      "epoch": 0.32,
+      "grad_norm": 1.0234085541077607,
+      "kl": 0.215966796875,
+      "learning_rate": 2.5192307692307695e-06,
+      "loss": 0.0086,
+      "num_tokens": 12598432.0,
+      "reward": 1.328627246618271,
+      "reward_std": 0.17000198867172003,
+      "rewards/reward_func": 1.328627210855484,
+      "step": 100
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1155.7333679199219,
+      "epoch": 0.352,
+      "grad_norm": 0.993996272164919,
+      "kl": 0.231884765625,
+      "learning_rate": 2.471153846153846e-06,
+      "loss": 0.0093,
+      "num_tokens": 13854596.0,
+      "reward": 1.3170884191989898,
+      "reward_std": 0.16620137430727483,
+      "rewards/reward_func": 1.317088395357132,
+      "step": 110
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1179.6333618164062,
+      "epoch": 0.384,
+      "grad_norm": 1.0386008286011814,
+      "kl": 0.24189453125,
+      "learning_rate": 2.4230769230769233e-06,
+      "loss": 0.0097,
+      "num_tokens": 15122610.0,
+      "reward": 1.3696976065635682,
+      "reward_std": 0.21136937104165554,
+      "rewards/reward_func": 1.3696975648403167,
+      "step": 120
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1119.6167114257812,
+      "epoch": 0.416,
+      "grad_norm": 0.9856388260555886,
+      "kl": 0.249951171875,
+      "learning_rate": 2.375e-06,
+      "loss": 0.01,
+      "num_tokens": 16352936.0,
+      "reward": 1.3440082728862763,
+      "reward_std": 0.20238495394587516,
+      "rewards/reward_func": 1.3440082371234894,
+      "step": 130
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1080.04169921875,
+      "epoch": 0.448,
+      "grad_norm": 1.0007193412023812,
+      "kl": 0.25869140625,
+      "learning_rate": 2.326923076923077e-06,
+      "loss": 0.0103,
+      "num_tokens": 17573812.0,
+      "reward": 1.3747205495834351,
+      "reward_std": 0.19062257995828985,
+      "rewards/reward_func": 1.3747205018997193,
+      "step": 140
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1101.4416961669922,
+      "epoch": 0.48,
+      "grad_norm": 1.031523753313366,
+      "kl": 0.263427734375,
+      "learning_rate": 2.278846153846154e-06,
+      "loss": 0.0105,
+      "num_tokens": 18802458.0,
+      "reward": 1.3720044195652008,
+      "reward_std": 0.19671934731304647,
+      "rewards/reward_func": 1.3720043897628784,
+      "step": 150
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1075.5250366210937,
+      "epoch": 0.512,
+      "grad_norm": 1.0105581618764354,
+      "kl": 0.270361328125,
+      "learning_rate": 2.2307692307692307e-06,
+      "loss": 0.0108,
+      "num_tokens": 20019060.0,
+      "reward": 1.3801562547683717,
+      "reward_std": 0.1729557979851961,
+      "rewards/reward_func": 1.3801562130451202,
+      "step": 160
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1243.0083740234375,
+      "epoch": 0.544,
+      "grad_norm": 1.0536982761834348,
+      "kl": 0.26962890625,
+      "learning_rate": 2.1826923076923076e-06,
+      "loss": 0.0108,
+      "num_tokens": 21314989.0,
+      "reward": 1.3575429141521453,
+      "reward_std": 0.19225950334221126,
+      "rewards/reward_func": 1.357542872428894,
+      "step": 170
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1280.0750427246094,
+      "epoch": 0.576,
+      "grad_norm": 0.8848699702030035,
+      "kl": 0.267626953125,
+      "learning_rate": 2.134615384615385e-06,
+      "loss": 0.0107,
+      "num_tokens": 22632769.0,
+      "reward": 1.4011802554130555,
+      "reward_std": 0.2013660490512848,
+      "rewards/reward_func": 1.401180225610733,
+      "step": 180
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1198.9833740234376,
+      "epoch": 0.608,
+      "grad_norm": 0.991723778598343,
+      "kl": 0.267822265625,
+      "learning_rate": 2.0865384615384613e-06,
+      "loss": 0.0107,
+      "num_tokens": 23901665.0,
+      "reward": 1.4138015925884246,
+      "reward_std": 0.20857114791870118,
+      "rewards/reward_func": 1.413801556825638,
+      "step": 190
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1184.183367919922,
+      "epoch": 0.64,
+      "grad_norm": 0.9649670800133836,
+      "kl": 0.270166015625,
+      "learning_rate": 2.0384615384615386e-06,
+      "loss": 0.0108,
+      "num_tokens": 25164675.0,
+      "reward": 1.3996073424816131,
+      "reward_std": 0.16547524519264697,
+      "rewards/reward_func": 1.3996073186397553,
+      "step": 200
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1196.316717529297,
+      "epoch": 0.672,
+      "grad_norm": 0.918724273092122,
+      "kl": 0.2720703125,
+      "learning_rate": 1.9903846153846155e-06,
+      "loss": 0.0109,
+      "num_tokens": 26431763.0,
+      "reward": 1.3570792913436889,
+      "reward_std": 0.17546614594757556,
+      "rewards/reward_func": 1.3570792555809021,
+      "step": 210
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1102.4250427246093,
+      "epoch": 0.704,
+      "grad_norm": 1.0148202612463983,
+      "kl": 0.2970703125,
+      "learning_rate": 1.9423076923076923e-06,
+      "loss": 0.0119,
+      "num_tokens": 27658616.0,
+      "reward": 1.4585702121257782,
+      "reward_std": 0.17592256814241408,
+      "rewards/reward_func": 1.4585701644420623,
+      "step": 220
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1159.0083740234375,
+      "epoch": 0.736,
+      "grad_norm": 0.9394385447945356,
+      "kl": 0.30498046875,
+      "learning_rate": 1.8942307692307692e-06,
+      "loss": 0.0122,
+      "num_tokens": 28915389.0,
+      "reward": 1.3902163803577423,
+      "reward_std": 0.17962961010634898,
+      "rewards/reward_func": 1.3902163565158845,
+      "step": 230
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1130.2417083740233,
+      "epoch": 0.768,
+      "grad_norm": 0.9787550227844843,
+      "kl": 0.28994140625,
+      "learning_rate": 1.8461538461538462e-06,
+      "loss": 0.0116,
+      "num_tokens": 30154961.0,
+      "reward": 1.4172639489173888,
+      "reward_std": 0.19173008762300014,
+      "rewards/reward_func": 1.4172639012336732,
+      "step": 240
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1228.6833740234374,
+      "epoch": 0.8,
+      "grad_norm": 0.8878239030584107,
+      "kl": 0.27294921875,
+      "learning_rate": 1.7980769230769231e-06,
+      "loss": 0.0109,
+      "num_tokens": 31447029.0,
+      "reward": 1.344082099199295,
+      "reward_std": 0.2040238121524453,
+      "rewards/reward_func": 1.3440820574760437,
+      "step": 250
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1235.8750457763672,
+      "epoch": 0.832,
+      "grad_norm": 0.9981329657418295,
+      "kl": 0.270654296875,
+      "learning_rate": 1.7500000000000002e-06,
+      "loss": 0.0108,
+      "num_tokens": 32737296.0,
+      "reward": 1.3086235880851746,
+      "reward_std": 0.16500989422202111,
+      "rewards/reward_func": 1.3086235344409942,
+      "step": 260
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1109.133364868164,
+      "epoch": 0.864,
+      "grad_norm": 1.0372489736696113,
+      "kl": 0.276611328125,
+      "learning_rate": 1.7019230769230768e-06,
+      "loss": 0.0111,
+      "num_tokens": 33967186.0,
+      "reward": 1.32349790930748,
+      "reward_std": 0.16945721451193094,
+      "rewards/reward_func": 1.3234978675842286,
+      "step": 270
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1160.8750396728515,
+      "epoch": 0.896,
+      "grad_norm": 0.9977790529738992,
+      "kl": 0.280419921875,
+      "learning_rate": 1.653846153846154e-06,
+      "loss": 0.0112,
+      "num_tokens": 35221063.0,
+      "reward": 1.4063874542713166,
+      "reward_std": 0.19618584401905537,
+      "rewards/reward_func": 1.4063874065876008,
+      "step": 280
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1213.883352661133,
+      "epoch": 0.928,
+      "grad_norm": 0.8934722066084559,
+      "kl": 0.28408203125,
+      "learning_rate": 1.6057692307692308e-06,
+      "loss": 0.0114,
+      "num_tokens": 36502115.0,
+      "reward": 1.3294113516807555,
+      "reward_std": 0.17417304012924434,
+      "rewards/reward_func": 1.3294113099575042,
+      "step": 290
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1091.5333679199218,
+      "epoch": 0.96,
+      "grad_norm": 1.018724425828204,
+      "kl": 0.28583984375,
+      "learning_rate": 1.5576923076923078e-06,
+      "loss": 0.0114,
+      "num_tokens": 37727916.0,
+      "reward": 1.3869296073913575,
+      "reward_std": 0.16371173467487096,
+      "rewards/reward_func": 1.3869295775890351,
+      "step": 300
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1021.2416961669921,
+      "epoch": 0.992,
+      "grad_norm": 0.9294425443280302,
+      "kl": 0.2927734375,
+      "learning_rate": 1.5096153846153847e-06,
+      "loss": 0.0117,
+      "num_tokens": 38912972.0,
+      "reward": 1.4153659164905548,
+      "reward_std": 0.15135814435780048,
+      "rewards/reward_func": 1.4153658747673035,
+      "step": 310
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1182.7667175292968,
+      "epoch": 1.0256,
+      "grad_norm": 0.8869424312219367,
+      "kl": 0.27578125,
+      "learning_rate": 1.4615384615384616e-06,
+      "loss": 0.011,
+      "num_tokens": 40172304.0,
+      "reward": 1.3812768101692199,
+      "reward_std": 0.16684217527508735,
+      "rewards/reward_func": 1.3812767565250397,
+      "step": 320
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1228.6667022705078,
+      "epoch": 1.0576,
+      "grad_norm": 0.8613262556098445,
+      "kl": 0.28349609375,
+      "learning_rate": 1.4134615384615384e-06,
+      "loss": 0.0113,
+      "num_tokens": 41456270.0,
+      "reward": 1.3983363509178162,
+      "reward_std": 0.16395095624029637,
+      "rewards/reward_func": 1.3983363211154938,
+      "step": 330
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1167.2917053222657,
+      "epoch": 1.0896,
+      "grad_norm": 0.9390384699267686,
+      "kl": 0.280078125,
+      "learning_rate": 1.3653846153846153e-06,
+      "loss": 0.0112,
+      "num_tokens": 42712372.0,
+      "reward": 1.3964947879314422,
+      "reward_std": 0.1702516170218587,
+      "rewards/reward_func": 1.3964947640895844,
+      "step": 340
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1084.7917053222657,
+      "epoch": 1.1216,
+      "grad_norm": 0.9885096589277191,
+      "kl": 0.2884765625,
+      "learning_rate": 1.3173076923076924e-06,
+      "loss": 0.0115,
+      "num_tokens": 43925166.0,
+      "reward": 1.4053608894348144,
+      "reward_std": 0.1990381298586726,
+      "rewards/reward_func": 1.4053608417510985,
+      "step": 350
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1068.3333618164063,
+      "epoch": 1.1536,
+      "grad_norm": 1.0735781172914411,
+      "kl": 0.280126953125,
+      "learning_rate": 1.2692307692307692e-06,
+      "loss": 0.0112,
+      "num_tokens": 45145132.0,
+      "reward": 1.4313134729862214,
+      "reward_std": 0.16737409718334675,
+      "rewards/reward_func": 1.4313134491443633,
+      "step": 360
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1042.34169921875,
+      "epoch": 1.1856,
+      "grad_norm": 0.9580029006411359,
+      "kl": 0.27919921875,
+      "learning_rate": 1.221153846153846e-06,
+      "loss": 0.0112,
+      "num_tokens": 46348908.0,
+      "reward": 1.3674868583679198,
+      "reward_std": 0.14877260774374007,
+      "rewards/reward_func": 1.3674868285655974,
+      "step": 370
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1031.9250396728517,
+      "epoch": 1.2176,
+      "grad_norm": 0.8804020781470968,
+      "kl": 0.28212890625,
+      "learning_rate": 1.1730769230769232e-06,
+      "loss": 0.0113,
+      "num_tokens": 47539473.0,
+      "reward": 1.3569320678710937,
+      "reward_std": 0.2110467005521059,
+      "rewards/reward_func": 1.3569320380687713,
+      "step": 380
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1122.9250366210938,
+      "epoch": 1.2496,
+      "grad_norm": 0.9380366433577524,
+      "kl": 0.265771484375,
+      "learning_rate": 1.125e-06,
+      "loss": 0.0106,
+      "num_tokens": 48783723.0,
+      "reward": 1.3864129424095153,
+      "reward_std": 0.1814204862341285,
+      "rewards/reward_func": 1.3864129185676575,
+      "step": 390
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1159.4166931152345,
+      "epoch": 1.2816,
+      "grad_norm": 0.8419779230541888,
+      "kl": 0.256494140625,
+      "learning_rate": 1.0769230769230769e-06,
+      "loss": 0.0103,
+      "num_tokens": 50043956.0,
+      "reward": 1.3803913414478302,
+      "reward_std": 0.19982445538043975,
+      "rewards/reward_func": 1.38039128780365,
+      "step": 400
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1137.99169921875,
+      "epoch": 1.3136,
+      "grad_norm": 0.9984529373671053,
+      "kl": 0.2568359375,
+      "learning_rate": 1.028846153846154e-06,
+      "loss": 0.0103,
+      "num_tokens": 51299782.0,
+      "reward": 1.460522174835205,
+      "reward_std": 0.17815895490348338,
+      "rewards/reward_func": 1.4605221152305603,
+      "step": 410
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1041.4417053222655,
+      "epoch": 1.3456000000000001,
+      "grad_norm": 0.9912374462984505,
+      "kl": 0.26103515625,
+      "learning_rate": 9.807692307692308e-07,
+      "loss": 0.0104,
+      "num_tokens": 52501749.0,
+      "reward": 1.3423645079135895,
+      "reward_std": 0.14929314143955708,
+      "rewards/reward_func": 1.3423644721508026,
+      "step": 420
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1092.66669921875,
+      "epoch": 1.3776,
+      "grad_norm": 0.9523986290310165,
+      "kl": 0.250439453125,
+      "learning_rate": 9.326923076923077e-07,
+      "loss": 0.01,
+      "num_tokens": 53728457.0,
+      "reward": 1.354611724615097,
+      "reward_std": 0.13474751003086566,
+      "rewards/reward_func": 1.3546116948127747,
+      "step": 430
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1057.16669921875,
+      "epoch": 1.4096,
+      "grad_norm": 1.009051628688743,
+      "kl": 0.246142578125,
+      "learning_rate": 8.846153846153847e-07,
+      "loss": 0.0099,
+      "num_tokens": 54938749.0,
+      "reward": 1.4103461623191833,
+      "reward_std": 0.17336017228662967,
+      "rewards/reward_func": 1.4103461384773255,
+      "step": 440
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1060.3250366210937,
+      "epoch": 1.4416,
+      "grad_norm": 0.9353173548774456,
+      "kl": 0.240380859375,
+      "learning_rate": 8.365384615384616e-07,
+      "loss": 0.0096,
+      "num_tokens": 56141986.0,
+      "reward": 1.3699217855930328,
+      "reward_std": 0.1920205257833004,
+      "rewards/reward_func": 1.369921749830246,
+      "step": 450
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1070.8083740234374,
+      "epoch": 1.4736,
+      "grad_norm": 1.1879379228096696,
+      "kl": 0.243603515625,
+      "learning_rate": 7.884615384615385e-07,
+      "loss": 0.0098,
+      "num_tokens": 57349220.0,
+      "reward": 1.433353638648987,
+      "reward_std": 0.1875140480697155,
+      "rewards/reward_func": 1.4333535850048065,
+      "step": 460
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1095.0833648681642,
+      "epoch": 1.5056,
+      "grad_norm": 0.9303357023393288,
+      "kl": 0.238525390625,
+      "learning_rate": 7.403846153846155e-07,
+      "loss": 0.0095,
+      "num_tokens": 58565922.0,
+      "reward": 1.4035043895244599,
+      "reward_std": 0.1516191340982914,
+      "rewards/reward_func": 1.403504341840744,
+      "step": 470
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1135.9750427246095,
+      "epoch": 1.5375999999999999,
+      "grad_norm": 1.0458418760593815,
+      "kl": 0.2318359375,
+      "learning_rate": 6.923076923076923e-07,
+      "loss": 0.0093,
+      "num_tokens": 59811024.0,
+      "reward": 1.3473765075206756,
+      "reward_std": 0.1674899585545063,
+      "rewards/reward_func": 1.3473764777183532,
+      "step": 480
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1108.0083770751953,
+      "epoch": 1.5695999999999999,
+      "grad_norm": 0.9490082083884928,
+      "kl": 0.23408203125,
+      "learning_rate": 6.442307692307692e-07,
+      "loss": 0.0094,
+      "num_tokens": 61041091.0,
+      "reward": 1.4498742938041687,
+      "reward_std": 0.16173237282782793,
+      "rewards/reward_func": 1.4498742520809174,
+      "step": 490
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1115.508352661133,
+      "epoch": 1.6016,
+      "grad_norm": 1.0783408314068932,
+      "kl": 0.238330078125,
+      "learning_rate": 5.961538461538461e-07,
+      "loss": 0.0095,
+      "num_tokens": 62274653.0,
+      "reward": 1.4305694937705993,
+      "reward_std": 0.18373069278895854,
+      "rewards/reward_func": 1.4305694699287415,
+      "step": 500
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1106.008367919922,
+      "epoch": 1.6336,
+      "grad_norm": 1.0485879744752402,
+      "kl": 0.2328125,
+      "learning_rate": 5.48076923076923e-07,
+      "loss": 0.0093,
+      "num_tokens": 63507003.0,
+      "reward": 1.4372118294239045,
+      "reward_std": 0.16331376498565078,
+      "rewards/reward_func": 1.4372117936611175,
+      "step": 510
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1086.8583679199219,
+      "epoch": 1.6656,
+      "grad_norm": 0.969087239165111,
+      "kl": 0.22392578125,
+      "learning_rate": 5e-07,
+      "loss": 0.009,
+      "num_tokens": 64735570.0,
+      "reward": 1.4018862843513489,
+      "reward_std": 0.14240890312939883,
+      "rewards/reward_func": 1.4018862307071687,
+      "step": 520
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1181.633383178711,
+      "epoch": 1.6976,
+      "grad_norm": 0.930292561029781,
+      "kl": 0.22138671875,
+      "learning_rate": 4.519230769230769e-07,
+      "loss": 0.0089,
+      "num_tokens": 65998928.0,
+      "reward": 1.451034414768219,
+      "reward_std": 0.1665300503373146,
+      "rewards/reward_func": 1.4510343849658967,
+      "step": 530
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1129.3750427246093,
+      "epoch": 1.7296,
+      "grad_norm": 0.9485552753279838,
+      "kl": 0.219775390625,
+      "learning_rate": 4.0384615384615386e-07,
+      "loss": 0.0088,
+      "num_tokens": 67237565.0,
+      "reward": 1.4116078853607177,
+      "reward_std": 0.19281931668519975,
+      "rewards/reward_func": 1.411607849597931,
+      "step": 540
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1172.0500396728517,
+      "epoch": 1.7616,
+      "grad_norm": 0.9153424916960798,
+      "kl": 0.222265625,
+      "learning_rate": 3.557692307692308e-07,
+      "loss": 0.0089,
+      "num_tokens": 68499368.0,
+      "reward": 1.3487315595149993,
+      "reward_std": 0.16217916831374168,
+      "rewards/reward_func": 1.3487315356731415,
+      "step": 550
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1124.0000396728515,
+      "epoch": 1.7936,
+      "grad_norm": 0.9325471561683758,
+      "kl": 0.224365234375,
+      "learning_rate": 3.076923076923077e-07,
+      "loss": 0.009,
+      "num_tokens": 69738074.0,
+      "reward": 1.3620680332183839,
+      "reward_std": 0.16596744321286677,
+      "rewards/reward_func": 1.3620680034160615,
+      "step": 560
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1125.1417053222656,
+      "epoch": 1.8256000000000001,
+      "grad_norm": 0.9795359194730576,
+      "kl": 0.22099609375,
+      "learning_rate": 2.596153846153846e-07,
+      "loss": 0.0088,
+      "num_tokens": 70970701.0,
+      "reward": 1.4437049567699431,
+      "reward_std": 0.16041705552488567,
+      "rewards/reward_func": 1.4437049448490142,
+      "step": 570
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1224.0833740234375,
+      "epoch": 1.8576000000000001,
+      "grad_norm": 0.9733689502236962,
+      "kl": 0.21044921875,
+      "learning_rate": 2.1153846153846155e-07,
+      "loss": 0.0084,
+      "num_tokens": 72266813.0,
+      "reward": 1.3616447150707245,
+      "reward_std": 0.1523937964811921,
+      "rewards/reward_func": 1.3616446733474732,
+      "step": 580
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1109.3000366210938,
+      "epoch": 1.8896,
+      "grad_norm": 0.9591418934816538,
+      "kl": 0.218115234375,
+      "learning_rate": 1.6346153846153846e-07,
+      "loss": 0.0087,
+      "num_tokens": 73500374.0,
+      "reward": 1.4193914115428925,
+      "reward_std": 0.18239253303036093,
+      "rewards/reward_func": 1.4193913757801055,
+      "step": 590
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1144.5250305175782,
+      "epoch": 1.9216,
+      "grad_norm": 1.03317829301988,
+      "kl": 0.223828125,
+      "learning_rate": 1.1538461538461539e-07,
+      "loss": 0.009,
+      "num_tokens": 74746547.0,
+      "reward": 1.442783957719803,
+      "reward_std": 0.16291865180246531,
+      "rewards/reward_func": 1.4427839279174806,
+      "step": 600
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1135.000033569336,
+      "epoch": 1.9536,
+      "grad_norm": 1.0378878472369144,
+      "kl": 0.21201171875,
+      "learning_rate": 6.73076923076923e-08,
+      "loss": 0.0085,
+      "num_tokens": 75989744.0,
+      "reward": 1.4489007711410522,
+      "reward_std": 0.148934593424201,
+      "rewards/reward_func": 1.4489007532596587,
+      "step": 610
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1140.8000366210938,
+      "epoch": 1.9856,
+      "grad_norm": 1.001500512040023,
+      "kl": 0.21005859375,
+      "learning_rate": 1.923076923076923e-08,
+      "loss": 0.0084,
+      "num_tokens": 77236076.0,
+      "reward": 1.4212264478206635,
+      "reward_std": 0.18371385149657726,
+      "rewards/reward_func": 1.4212264180183412,
+      "step": 620
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 312,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cdf32aa2c26d67d1cbfb825f1d2e91a03e879c285abd5e30186cc61f0c07115
+size 8120

zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)