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 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151645,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

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": "4.50.0"
+}

latest

@@ -0,0 +1 @@
+global_step80

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1702601012dad800407aa403642cc2b2930b6671bf651b43aa71dfd728a62aa7
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f780a78677484b2dc2a7043dc00b2bbcad3e27d890eda7b6f324bbed23e581
+size 1214366696

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a2951d5edfa5cc0a2346ef872f8c77a2920274cfc3b503b04e3799104dee80
+size 11422060

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if 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": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8333333333333334,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 153.1875,
+      "epoch": 0.010416666666666666,
+      "grad_norm": 2.2964696301344203,
+      "kl": 0.0008754730224609375,
+      "learning_rate": 1e-06,
+      "loss": -0.0104,
+      "num_tokens": 44706.0,
+      "reward": 0.46666670590639114,
+      "reward_std": 0.7099685594439507,
+      "rewards/warm_up_reward/mean": 0.3888888955116272,
+      "rewards/warm_up_reward/std": 0.7168056517839432,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 147.95833587646484,
+      "epoch": 0.020833333333333332,
+      "grad_norm": 2.332332033549255,
+      "kl": 0.0011844635009765625,
+      "learning_rate": 1e-06,
+      "loss": 0.0071,
+      "num_tokens": 88904.0,
+      "reward": 0.5250000506639481,
+      "reward_std": 0.748512014746666,
+      "rewards/warm_up_reward/mean": 0.4375,
+      "rewards/warm_up_reward/std": 0.6997176110744476,
+      "step": 2
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 154.00000381469727,
+      "epoch": 0.03125,
+      "grad_norm": 2.04671487874671,
+      "kl": 0.0013523101806640625,
+      "learning_rate": 1e-06,
+      "loss": 0.0124,
+      "num_tokens": 133634.0,
+      "reward": 0.500000037252903,
+      "reward_std": 0.667382538318634,
+      "rewards/warm_up_reward/mean": 0.416666679084301,
+      "rewards/warm_up_reward/std": 0.7197580486536026,
+      "step": 3
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 151.69792556762695,
+      "epoch": 0.041666666666666664,
+      "grad_norm": 2.2153093232246226,
+      "kl": 0.00243377685546875,
+      "learning_rate": 1e-06,
+      "loss": 0.0232,
+      "num_tokens": 178089.0,
+      "reward": 0.43125002086162567,
+      "reward_std": 0.662388876080513,
+      "rewards/warm_up_reward/mean": 0.359375,
+      "rewards/warm_up_reward/std": 0.6697845309972763,
+      "step": 4
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 148.84375762939453,
+      "epoch": 0.052083333333333336,
+      "grad_norm": 2.4723944423129782,
+      "kl": 0.004669189453125,
+      "learning_rate": 1e-06,
+      "loss": 0.0002,
+      "num_tokens": 222360.0,
+      "reward": 0.6250000596046448,
+      "reward_std": 0.8341160118579865,
+      "rewards/warm_up_reward/mean": 0.5208333358168602,
+      "rewards/warm_up_reward/std": 0.7749323397874832,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 147.4791717529297,
+      "epoch": 0.0625,
+      "grad_norm": 2.452268566541841,
+      "kl": 0.00980377197265625,
+      "learning_rate": 1e-06,
+      "loss": 0.05,
+      "num_tokens": 266434.0,
+      "reward": 0.5625000298023224,
+      "reward_std": 0.8674589395523071,
+      "rewards/warm_up_reward/mean": 0.46875,
+      "rewards/warm_up_reward/std": 0.7468476742506027,
+      "step": 6
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 147.79166793823242,
+      "epoch": 0.07291666666666667,
+      "grad_norm": 55.84129867431237,
+      "kl": 0.194091796875,
+      "learning_rate": 1e-06,
+      "loss": 0.0511,
+      "num_tokens": 310532.0,
+      "reward": 0.9333333820104599,
+      "reward_std": 0.9551109671592712,
+      "rewards/warm_up_reward/mean": 0.7777777910232544,
+      "rewards/warm_up_reward/std": 0.8151216059923172,
+      "step": 7
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 157.65625381469727,
+      "epoch": 0.08333333333333333,
+      "grad_norm": 29.072228981795064,
+      "kl": 0.1204376220703125,
+      "learning_rate": 1e-06,
+      "loss": 0.0653,
+      "num_tokens": 355673.0,
+      "reward": 0.8281250894069672,
+      "reward_std": 0.9019797444343567,
+      "rewards/warm_up_reward/mean": 0.6901041716337204,
+      "rewards/warm_up_reward/std": 0.800490528345108,
+      "step": 8
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 147.62500381469727,
+      "epoch": 0.09375,
+      "grad_norm": 6.698990666563141,
+      "kl": 0.04058837890625,
+      "learning_rate": 1e-06,
+      "loss": 0.0742,
+      "num_tokens": 399929.0,
+      "reward": 0.6916667073965073,
+      "reward_std": 0.7857400476932526,
+      "rewards/warm_up_reward/mean": 0.5763888955116272,
+      "rewards/warm_up_reward/std": 0.7836765646934509,
+      "step": 9
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 150.2291717529297,
+      "epoch": 0.10416666666666667,
+      "grad_norm": 5.758187436239667,
+      "kl": 0.1109619140625,
+      "learning_rate": 1e-06,
+      "loss": 0.0303,
+      "num_tokens": 444279.0,
+      "reward": 0.9000000357627869,
+      "reward_std": 0.9381224364042282,
+      "rewards/warm_up_reward/mean": 0.75,
+      "rewards/warm_up_reward/std": 0.820982426404953,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 150.67708587646484,
+      "epoch": 0.11458333333333333,
+      "grad_norm": 24.363046434997802,
+      "kl": 0.2352294921875,
+      "learning_rate": 1e-06,
+      "loss": 0.0567,
+      "num_tokens": 488708.0,
+      "reward": 0.8645834177732468,
+      "reward_std": 0.9693308770656586,
+      "rewards/warm_up_reward/mean": 0.720486119389534,
+      "rewards/warm_up_reward/std": 0.8197668194770813,
+      "step": 11
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 155.2916717529297,
+      "epoch": 0.125,
+      "grad_norm": 3.1714199544174053,
+      "kl": 0.08984375,
+      "learning_rate": 1e-06,
+      "loss": 0.0481,
+      "num_tokens": 533526.0,
+      "reward": 1.0781250596046448,
+      "reward_std": 0.9790745824575424,
+      "rewards/warm_up_reward/mean": 0.8984375,
+      "rewards/warm_up_reward/std": 0.8148495256900787,
+      "step": 12
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.2395896911621,
+      "epoch": 0.13541666666666666,
+      "grad_norm": 5.687529927842251,
+      "kl": 0.12872314453125,
+      "learning_rate": 1e-06,
+      "loss": 0.0633,
+      "num_tokens": 576965.0,
+      "reward": 0.9635417610406876,
+      "reward_std": 0.9496043026447296,
+      "rewards/warm_up_reward/mean": 0.802951380610466,
+      "rewards/warm_up_reward/std": 0.7969174236059189,
+      "step": 13
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 137.87500762939453,
+      "epoch": 0.14583333333333334,
+      "grad_norm": 4.785248899065895,
+      "kl": 0.09088134765625,
+      "learning_rate": 1e-06,
+      "loss": 0.0956,
+      "num_tokens": 620003.0,
+      "reward": 0.8687500655651093,
+      "reward_std": 0.8496406525373459,
+      "rewards/warm_up_reward/mean": 0.7239583283662796,
+      "rewards/warm_up_reward/std": 0.7836050242185593,
+      "step": 14
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.87500381469727,
+      "epoch": 0.15625,
+      "grad_norm": 3.043938278706536,
+      "kl": 0.06243896484375,
+      "learning_rate": 1e-06,
+      "loss": 0.048,
+      "num_tokens": 663347.0,
+      "reward": 0.8843750804662704,
+      "reward_std": 0.9135490357875824,
+      "rewards/warm_up_reward/mean": 0.7369791716337204,
+      "rewards/warm_up_reward/std": 0.8226732462644577,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 145.0833396911621,
+      "epoch": 0.16666666666666666,
+      "grad_norm": 4.964409464782977,
+      "kl": 0.0794677734375,
+      "learning_rate": 1e-06,
+      "loss": 0.0574,
+      "num_tokens": 707341.0,
+      "reward": 0.9437500536441803,
+      "reward_std": 0.8649309277534485,
+      "rewards/warm_up_reward/mean": 0.7864583283662796,
+      "rewards/warm_up_reward/std": 0.795333594083786,
+      "step": 16
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 143.76041793823242,
+      "epoch": 0.17708333333333334,
+      "grad_norm": 2.5933725635254965,
+      "kl": 0.0601806640625,
+      "learning_rate": 1e-06,
+      "loss": 0.0293,
+      "num_tokens": 751028.0,
+      "reward": 0.7000000327825546,
+      "reward_std": 0.9639299660921097,
+      "rewards/warm_up_reward/mean": 0.5833333283662796,
+      "rewards/warm_up_reward/std": 0.7868598401546478,
+      "step": 17
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.90625381469727,
+      "epoch": 0.1875,
+      "grad_norm": 2.560263758795748,
+      "kl": 0.0513916015625,
+      "learning_rate": 1e-06,
+      "loss": 0.0333,
+      "num_tokens": 794597.0,
+      "reward": 0.947916716337204,
+      "reward_std": 0.9378172904253006,
+      "rewards/warm_up_reward/mean": 0.7899305373430252,
+      "rewards/warm_up_reward/std": 0.8166805952787399,
+      "step": 18
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 134.42708587646484,
+      "epoch": 0.19791666666666666,
+      "grad_norm": 2.827678010439988,
+      "kl": 0.05694580078125,
+      "learning_rate": 1e-06,
+      "loss": 0.0819,
+      "num_tokens": 837364.0,
+      "reward": 0.9250000715255737,
+      "reward_std": 0.9560818523168564,
+      "rewards/warm_up_reward/mean": 0.7708333283662796,
+      "rewards/warm_up_reward/std": 0.8091117739677429,
+      "step": 19
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 137.16666793823242,
+      "epoch": 0.20833333333333334,
+      "grad_norm": 2.92256682920272,
+      "kl": 0.05963134765625,
+      "learning_rate": 1e-06,
+      "loss": 0.0522,
+      "num_tokens": 880442.0,
+      "reward": 0.9791667610406876,
+      "reward_std": 0.9076904356479645,
+      "rewards/warm_up_reward/mean": 0.8159722089767456,
+      "rewards/warm_up_reward/std": 0.8102934062480927,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 137.84375381469727,
+      "epoch": 0.21875,
+      "grad_norm": 2.864931852177023,
+      "kl": 0.04974365234375,
+      "learning_rate": 1e-06,
+      "loss": 0.0248,
+      "num_tokens": 923615.0,
+      "reward": 0.9281250536441803,
+      "reward_std": 0.9918985664844513,
+      "rewards/warm_up_reward/mean": 0.7734375,
+      "rewards/warm_up_reward/std": 0.8185379058122635,
+      "step": 21
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 130.8750057220459,
+      "epoch": 0.22916666666666666,
+      "grad_norm": 2.8348309851740456,
+      "kl": 0.05242919921875,
+      "learning_rate": 1e-06,
+      "loss": 0.0427,
+      "num_tokens": 966107.0,
+      "reward": 1.0531250834465027,
+      "reward_std": 0.9989801347255707,
+      "rewards/warm_up_reward/mean": 0.8776041567325592,
+      "rewards/warm_up_reward/std": 0.8102044314146042,
+      "step": 22
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 144.26041793823242,
+      "epoch": 0.23958333333333334,
+      "grad_norm": 2.6071380741149004,
+      "kl": 0.06549072265625,
+      "learning_rate": 1e-06,
+      "loss": 0.0523,
+      "num_tokens": 1009998.0,
+      "reward": 0.9625000357627869,
+      "reward_std": 0.9378929734230042,
+      "rewards/warm_up_reward/mean": 0.8020833432674408,
+      "rewards/warm_up_reward/std": 0.8023640215396881,
+      "step": 23
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 139.73958587646484,
+      "epoch": 0.25,
+      "grad_norm": 2.697375275936146,
+      "kl": 0.05670166015625,
+      "learning_rate": 1e-06,
+      "loss": 0.0705,
+      "num_tokens": 1053401.0,
+      "reward": 1.031250074505806,
+      "reward_std": 0.9829376488924026,
+      "rewards/warm_up_reward/mean": 0.859375,
+      "rewards/warm_up_reward/std": 0.813440352678299,
+      "step": 24
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 138.8854217529297,
+      "epoch": 0.2604166666666667,
+      "grad_norm": 85.52835351864486,
+      "kl": 0.198486328125,
+      "learning_rate": 1e-06,
+      "loss": 0.0333,
+      "num_tokens": 1096650.0,
+      "reward": 1.089583471417427,
+      "reward_std": 0.9481612741947174,
+      "rewards/warm_up_reward/mean": 0.9079861044883728,
+      "rewards/warm_up_reward/std": 0.7854074388742447,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 130.62500381469727,
+      "epoch": 0.2708333333333333,
+      "grad_norm": 3.4064495832019297,
+      "kl": 0.07513427734375,
+      "learning_rate": 1e-06,
+      "loss": 0.0544,
+      "num_tokens": 1139058.0,
+      "reward": 0.9885417520999908,
+      "reward_std": 0.990489736199379,
+      "rewards/warm_up_reward/mean": 0.8237847238779068,
+      "rewards/warm_up_reward/std": 0.8235566318035126,
+      "step": 26
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 134.50000381469727,
+      "epoch": 0.28125,
+      "grad_norm": 118.32186343464612,
+      "kl": 0.2930908203125,
+      "learning_rate": 1e-06,
+      "loss": 0.011,
+      "num_tokens": 1181802.0,
+      "reward": 1.0552084296941757,
+      "reward_std": 0.868858814239502,
+      "rewards/warm_up_reward/mean": 0.8793402910232544,
+      "rewards/warm_up_reward/std": 0.8186527788639069,
+      "step": 27
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.8541717529297,
+      "epoch": 0.2916666666666667,
+      "grad_norm": 6.711195724360143,
+      "kl": 0.1092529296875,
+      "learning_rate": 1e-06,
+      "loss": 0.0187,
+      "num_tokens": 1225408.0,
+      "reward": 0.9666667431592941,
+      "reward_std": 0.9556048065423965,
+      "rewards/warm_up_reward/mean": 0.8055555671453476,
+      "rewards/warm_up_reward/std": 0.8192583322525024,
+      "step": 28
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 137.48958778381348,
+      "epoch": 0.3020833333333333,
+      "grad_norm": 4.712858469896548,
+      "kl": 0.13214111328125,
+      "learning_rate": 1e-06,
+      "loss": 0.0356,
+      "num_tokens": 1268481.0,
+      "reward": 0.9000000655651093,
+      "reward_std": 1.0170713812112808,
+      "rewards/warm_up_reward/mean": 0.7500000149011612,
+      "rewards/warm_up_reward/std": 0.8409183472394943,
+      "step": 29
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 142.09375381469727,
+      "epoch": 0.3125,
+      "grad_norm": 2.604660112727859,
+      "kl": 0.063720703125,
+      "learning_rate": 1e-06,
+      "loss": -0.0023,
+      "num_tokens": 1312008.0,
+      "reward": 0.9000000059604645,
+      "reward_std": 0.9869166016578674,
+      "rewards/warm_up_reward/mean": 0.75,
+      "rewards/warm_up_reward/std": 0.8337783664464951,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 145.59375381469727,
+      "epoch": 0.3229166666666667,
+      "grad_norm": 6.185404235919849,
+      "kl": 0.157470703125,
+      "learning_rate": 1e-06,
+      "loss": 0.0097,
+      "num_tokens": 1356039.0,
+      "reward": 1.0770834237337112,
+      "reward_std": 0.9777155965566635,
+      "rewards/warm_up_reward/mean": 0.8975694477558136,
+      "rewards/warm_up_reward/std": 0.7948237210512161,
+      "step": 31
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 146.37500762939453,
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.4537091049295956,
+      "kl": 0.06231689453125,
+      "learning_rate": 1e-06,
+      "loss": 0.0046,
+      "num_tokens": 1400007.0,
+      "reward": 0.9812500327825546,
+      "reward_std": 0.911426916718483,
+      "rewards/warm_up_reward/mean": 0.8177083283662796,
+      "rewards/warm_up_reward/std": 0.7836276739835739,
+      "step": 32
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 145.19792556762695,
+      "epoch": 0.34375,
+      "grad_norm": 3.0265092714690702,
+      "kl": 0.061767578125,
+      "learning_rate": 1e-06,
+      "loss": 0.0423,
+      "num_tokens": 1443874.0,
+      "reward": 1.0354167222976685,
+      "reward_std": 0.9364243745803833,
+      "rewards/warm_up_reward/mean": 0.8628472238779068,
+      "rewards/warm_up_reward/std": 0.8118415027856827,
+      "step": 33
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 143.8645896911621,
+      "epoch": 0.3541666666666667,
+      "grad_norm": 2.4770416085087477,
+      "kl": 0.05682373046875,
+      "learning_rate": 1e-06,
+      "loss": 0.0242,
+      "num_tokens": 1487601.0,
+      "reward": 0.9906250834465027,
+      "reward_std": 1.0336193144321442,
+      "rewards/warm_up_reward/mean": 0.8255208432674408,
+      "rewards/warm_up_reward/std": 0.8268236815929413,
+      "step": 34
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 137.34375762939453,
+      "epoch": 0.3645833333333333,
+      "grad_norm": 2.787024849258649,
+      "kl": 0.051513671875,
+      "learning_rate": 1e-06,
+      "loss": 0.0409,
+      "num_tokens": 1530594.0,
+      "reward": 1.0822917073965073,
+      "reward_std": 0.8545732349157333,
+      "rewards/warm_up_reward/mean": 0.9019097238779068,
+      "rewards/warm_up_reward/std": 0.7748938798904419,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 145.71875381469727,
+      "epoch": 0.375,
+      "grad_norm": 2.515335560097886,
+      "kl": 0.0687255859375,
+      "learning_rate": 1e-06,
+      "loss": 0.0284,
+      "num_tokens": 1574409.0,
+      "reward": 0.9875000715255737,
+      "reward_std": 0.9168877303600311,
+      "rewards/warm_up_reward/mean": 0.8229166567325592,
+      "rewards/warm_up_reward/std": 0.8267286717891693,
+      "step": 36
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 136.58333778381348,
+      "epoch": 0.3854166666666667,
+      "grad_norm": 11.790654099301383,
+      "kl": 0.1207275390625,
+      "learning_rate": 1e-06,
+      "loss": 0.0652,
+      "num_tokens": 1617503.0,
+      "reward": 1.031250074505806,
+      "reward_std": 0.9142753481864929,
+      "rewards/warm_up_reward/mean": 0.859375,
+      "rewards/warm_up_reward/std": 0.7878352403640747,
+      "step": 37
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 151.8645896911621,
+      "epoch": 0.3958333333333333,
+      "grad_norm": 3.4202024786499643,
+      "kl": 0.08099365234375,
+      "learning_rate": 1e-06,
+      "loss": 0.0212,
+      "num_tokens": 1661980.0,
+      "reward": 0.6229167133569717,
+      "reward_std": 0.8097958564758301,
+      "rewards/warm_up_reward/mean": 0.5190972313284874,
+      "rewards/warm_up_reward/std": 0.7617596387863159,
+      "step": 38
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 142.8854217529297,
+      "epoch": 0.40625,
+      "grad_norm": 2.4994048524913364,
+      "kl": 0.06414794921875,
+      "learning_rate": 1e-06,
+      "loss": 0.0569,
+      "num_tokens": 1705637.0,
+      "reward": 1.0656251087784767,
+      "reward_std": 0.8034301698207855,
+      "rewards/warm_up_reward/mean": 0.8880208432674408,
+      "rewards/warm_up_reward/std": 0.7390912175178528,
+      "step": 39
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 146.18750762939453,
+      "epoch": 0.4166666666666667,
+      "grad_norm": 2.4999575203414186,
+      "kl": 0.0628662109375,
+      "learning_rate": 1e-06,
+      "loss": 0.0137,
+      "num_tokens": 1749719.0,
+      "reward": 1.0104167312383652,
+      "reward_std": 0.9736887365579605,
+      "rewards/warm_up_reward/mean": 0.8420138955116272,
+      "rewards/warm_up_reward/std": 0.822531133890152,
+      "step": 40
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 143.9479217529297,
+      "epoch": 0.4270833333333333,
+      "grad_norm": 2.2639443093591205,
+      "kl": 0.0675048828125,
+      "learning_rate": 1e-06,
+      "loss": 0.0087,
+      "num_tokens": 1793436.0,
+      "reward": 0.9229167401790619,
+      "reward_std": 0.9153347015380859,
+      "rewards/warm_up_reward/mean": 0.7690972089767456,
+      "rewards/warm_up_reward/std": 0.8183709383010864,
+      "step": 41
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 147.58333587646484,
+      "epoch": 0.4375,
+      "grad_norm": 2.5193978009218965,
+      "kl": 0.07177734375,
+      "learning_rate": 1e-06,
+      "loss": 0.0392,
+      "num_tokens": 1837562.0,
+      "reward": 1.006250038743019,
+      "reward_std": 0.8919505327939987,
+      "rewards/warm_up_reward/mean": 0.8385416716337204,
+      "rewards/warm_up_reward/std": 0.8046689182519913,
+      "step": 42
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.37500381469727,
+      "epoch": 0.4479166666666667,
+      "grad_norm": 2.5496207567669034,
+      "kl": 0.06622314453125,
+      "learning_rate": 1e-06,
+      "loss": 0.0452,
+      "num_tokens": 1880972.0,
+      "reward": 1.068750038743019,
+      "reward_std": 0.9111972749233246,
+      "rewards/warm_up_reward/mean": 0.890625,
+      "rewards/warm_up_reward/std": 0.7989336252212524,
+      "step": 43
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 130.83333587646484,
+      "epoch": 0.4583333333333333,
+      "grad_norm": 5.245713134644536,
+      "kl": 0.0999755859375,
+      "learning_rate": 1e-06,
+      "loss": -0.0051,
+      "num_tokens": 1923460.0,
+      "reward": 0.929166704416275,
+      "reward_std": 0.8137651234865189,
+      "rewards/warm_up_reward/mean": 0.7743055373430252,
+      "rewards/warm_up_reward/std": 0.8136637955904007,
+      "step": 44
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 144.2604217529297,
+      "epoch": 0.46875,
+      "grad_norm": 6.317144379422631,
+      "kl": 0.10107421875,
+      "learning_rate": 1e-06,
+      "loss": -0.0175,
+      "num_tokens": 1967315.0,
+      "reward": 1.1012500673532486,
+      "reward_std": 0.7948171943426132,
+      "rewards/warm_up_reward/mean": 0.9177083224058151,
+      "rewards/warm_up_reward/std": 0.7791551500558853,
+      "step": 45
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.5104217529297,
+      "epoch": 0.4791666666666667,
+      "grad_norm": 2.8932825846308172,
+      "kl": 0.0859375,
+      "learning_rate": 1e-06,
+      "loss": 0.0029,
+      "num_tokens": 2010882.0,
+      "reward": 1.0656251162290573,
+      "reward_std": 0.9644656330347061,
+      "rewards/warm_up_reward/mean": 0.8880208432674408,
+      "rewards/warm_up_reward/std": 0.8194199502468109,
+      "step": 46
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.21875762939453,
+      "epoch": 0.4895833333333333,
+      "grad_norm": 2.9093719889125174,
+      "kl": 0.1007080078125,
+      "learning_rate": 1e-06,
+      "loss": -0.0275,
+      "num_tokens": 2054307.0,
+      "reward": 0.991666704416275,
+      "reward_std": 0.9324973523616791,
+      "rewards/warm_up_reward/mean": 0.8263888955116272,
+      "rewards/warm_up_reward/std": 0.8247981667518616,
+      "step": 47
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 136.5729217529297,
+      "epoch": 0.5,
+      "grad_norm": 2.3209209113606146,
+      "kl": 0.08441162109375,
+      "learning_rate": 1e-06,
+      "loss": 0.001,
+      "num_tokens": 2097424.0,
+      "reward": 1.1010417491197586,
+      "reward_std": 0.8305719494819641,
+      "rewards/warm_up_reward/mean": 0.9175347238779068,
+      "rewards/warm_up_reward/std": 0.7910451591014862,
+      "step": 48
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 142.50000762939453,
+      "epoch": 0.5104166666666666,
+      "grad_norm": 2.470827147583925,
+      "kl": 0.08355712890625,
+      "learning_rate": 1e-06,
+      "loss": 0.0433,
+      "num_tokens": 2141092.0,
+      "reward": 1.0208334028720856,
+      "reward_std": 0.9052031934261322,
+      "rewards/warm_up_reward/mean": 0.8506944477558136,
+      "rewards/warm_up_reward/std": 0.8133653849363327,
+      "step": 49
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 138.58333587646484,
+      "epoch": 0.5208333333333334,
+      "grad_norm": 2.314915736053297,
+      "kl": 0.0765380859375,
+      "learning_rate": 1e-06,
+      "loss": 0.0188,
+      "num_tokens": 2184306.0,
+      "reward": 1.050000086426735,
+      "reward_std": 0.9242848604917526,
+      "rewards/warm_up_reward/mean": 0.8749999850988388,
+      "rewards/warm_up_reward/std": 0.7892495840787888,
+      "step": 50
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 138.92708778381348,
+      "epoch": 0.53125,
+      "grad_norm": 16.28250872141934,
+      "kl": 0.26171875,
+      "learning_rate": 1e-06,
+      "loss": 0.0328,
+      "num_tokens": 2227673.0,
+      "reward": 1.1312500685453415,
+      "reward_std": 1.0009342432022095,
+      "rewards/warm_up_reward/mean": 0.9427083432674408,
+      "rewards/warm_up_reward/std": 0.8114291131496429,
+      "step": 51
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.92708587646484,
+      "epoch": 0.5416666666666666,
+      "grad_norm": 2.4052567403889364,
+      "kl": 0.0528564453125,
+      "learning_rate": 1e-06,
+      "loss": 0.0201,
+      "num_tokens": 2271064.0,
+      "reward": 1.2375000417232513,
+      "reward_std": 0.8487301468849182,
+      "rewards/warm_up_reward/mean": 1.03125,
+      "rewards/warm_up_reward/std": 0.7739475220441818,
+      "step": 52
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 146.1458396911621,
+      "epoch": 0.5520833333333334,
+      "grad_norm": 2.4582483635661467,
+      "kl": 0.05413818359375,
+      "learning_rate": 1e-06,
+      "loss": 0.0429,
+      "num_tokens": 2315052.0,
+      "reward": 1.1104167699813843,
+      "reward_std": 0.9700468927621841,
+      "rewards/warm_up_reward/mean": 0.9253472238779068,
+      "rewards/warm_up_reward/std": 0.7955830246210098,
+      "step": 53
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 145.2083396911621,
+      "epoch": 0.5625,
+      "grad_norm": 2.4577305981193165,
+      "kl": 0.0728759765625,
+      "learning_rate": 1e-06,
+      "loss": -0.0131,
+      "num_tokens": 2358962.0,
+      "reward": 1.1750001013278961,
+      "reward_std": 0.9326367676258087,
+      "rewards/warm_up_reward/mean": 0.9791666716337204,
+      "rewards/warm_up_reward/std": 0.7897387892007828,
+      "step": 54
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 145.7916717529297,
+      "epoch": 0.5729166666666666,
+      "grad_norm": 2.302326467124225,
+      "kl": 0.0810546875,
+      "learning_rate": 1e-06,
+      "loss": 0.0291,
+      "num_tokens": 2402922.0,
+      "reward": 0.9875000566244125,
+      "reward_std": 1.0013651847839355,
+      "rewards/warm_up_reward/mean": 0.8229166716337204,
+      "rewards/warm_up_reward/std": 0.8247637003660202,
+      "step": 55
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 147.9479217529297,
+      "epoch": 0.5833333333333334,
+      "grad_norm": 2.580316913788417,
+      "kl": 0.068115234375,
+      "learning_rate": 1e-06,
+      "loss": 0.0509,
+      "num_tokens": 2447065.0,
+      "reward": 1.183750033378601,
+      "reward_std": 0.9039967954158783,
+      "rewards/warm_up_reward/mean": 0.9864583313465118,
+      "rewards/warm_up_reward/std": 0.787983849644661,
+      "step": 56
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 142.05208587646484,
+      "epoch": 0.59375,
+      "grad_norm": 2.748934001160214,
+      "kl": 0.06414794921875,
+      "learning_rate": 1e-06,
+      "loss": -0.0078,
+      "num_tokens": 2490552.0,
+      "reward": 1.07750004529953,
+      "reward_std": 0.9763932228088379,
+      "rewards/warm_up_reward/mean": 0.8979166746139526,
+      "rewards/warm_up_reward/std": 0.8105349242687225,
+      "step": 57
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 146.0729217529297,
+      "epoch": 0.6041666666666666,
+      "grad_norm": 2.279728805159882,
+      "kl": 0.05682373046875,
+      "learning_rate": 1e-06,
+      "loss": 0.0054,
+      "num_tokens": 2534503.0,
+      "reward": 1.2562500685453415,
+      "reward_std": 0.8728772848844528,
+      "rewards/warm_up_reward/mean": 1.046875,
+      "rewards/warm_up_reward/std": 0.715716764330864,
+      "step": 58
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 136.77083587646484,
+      "epoch": 0.6145833333333334,
+      "grad_norm": 2.301940905359112,
+      "kl": 0.0634765625,
+      "learning_rate": 1e-06,
+      "loss": 0.0198,
+      "num_tokens": 2577603.0,
+      "reward": 1.2200001031160355,
+      "reward_std": 0.9238942861557007,
+      "rewards/warm_up_reward/mean": 1.0166666805744171,
+      "rewards/warm_up_reward/std": 0.7837828695774078,
+      "step": 59
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 149.3645896911621,
+      "epoch": 0.625,
+      "grad_norm": 2.3088797777576535,
+      "kl": 0.0701904296875,
+      "learning_rate": 1e-06,
+      "loss": 0.0668,
+      "num_tokens": 2621852.0,
+      "reward": 1.0885417461395264,
+      "reward_std": 0.9921838045120239,
+      "rewards/warm_up_reward/mean": 0.9071180820465088,
+      "rewards/warm_up_reward/std": 0.8187949508428574,
+      "step": 60
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 144.9791717529297,
+      "epoch": 0.6354166666666666,
+      "grad_norm": 2.3531788106957063,
+      "kl": 0.0830078125,
+      "learning_rate": 1e-06,
+      "loss": 0.0715,
+      "num_tokens": 2665584.0,
+      "reward": 1.103541761636734,
+      "reward_std": 0.8904776722192764,
+      "rewards/warm_up_reward/mean": 0.9196180552244186,
+      "rewards/warm_up_reward/std": 0.7996000051498413,
+      "step": 61
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.5416717529297,
+      "epoch": 0.6458333333333334,
+      "grad_norm": 2.3780245058749894,
+      "kl": 0.0545654296875,
+      "learning_rate": 1e-06,
+      "loss": 0.0144,
+      "num_tokens": 2709058.0,
+      "reward": 1.2650001347064972,
+      "reward_std": 0.8583473563194275,
+      "rewards/warm_up_reward/mean": 1.0541666597127914,
+      "rewards/warm_up_reward/std": 0.753357321023941,
+      "step": 62
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 150.5208396911621,
+      "epoch": 0.65625,
+      "grad_norm": 2.291724896507479,
+      "kl": 0.05914306640625,
+      "learning_rate": 1e-06,
+      "loss": 0.0102,
+      "num_tokens": 2753538.0,
+      "reward": 1.2431251406669617,
+      "reward_std": 0.8321643471717834,
+      "rewards/warm_up_reward/mean": 1.0359375476837158,
+      "rewards/warm_up_reward/std": 0.74222831428051,
+      "step": 63
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 143.2395896911621,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 3.018275289311917,
+      "kl": 0.085693359375,
+      "learning_rate": 1e-06,
+      "loss": 0.0078,
+      "num_tokens": 2797253.0,
+      "reward": 1.1802085041999817,
+      "reward_std": 0.948539987206459,
+      "rewards/warm_up_reward/mean": 0.9835069626569748,
+      "rewards/warm_up_reward/std": 0.7748740911483765,
+      "step": 64
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 138.9791717529297,
+      "epoch": 0.6770833333333334,
+      "grad_norm": 2.219343433713507,
+      "kl": 0.06298828125,
+      "learning_rate": 1e-06,
+      "loss": 0.0203,
+      "num_tokens": 2840571.0,
+      "reward": 1.2229167520999908,
+      "reward_std": 0.783911868929863,
+      "rewards/warm_up_reward/mean": 1.0190972089767456,
+      "rewards/warm_up_reward/std": 0.7600821256637573,
+      "step": 65
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 152.8958396911621,
+      "epoch": 0.6875,
+      "grad_norm": 2.2126312475293877,
+      "kl": 0.0704345703125,
+      "learning_rate": 1e-06,
+      "loss": 0.0425,
+      "num_tokens": 2885201.0,
+      "reward": 1.1691668182611465,
+      "reward_std": 0.8853475451469421,
+      "rewards/warm_up_reward/mean": 0.9743055552244186,
+      "rewards/warm_up_reward/std": 0.7726792246103287,
+      "step": 66
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 147.61459350585938,
+      "epoch": 0.6979166666666666,
+      "grad_norm": 2.3729988144079748,
+      "kl": 0.05316162109375,
+      "learning_rate": 1e-06,
+      "loss": 0.0235,
+      "num_tokens": 2929396.0,
+      "reward": 1.3312501311302185,
+      "reward_std": 0.7987091541290283,
+      "rewards/warm_up_reward/mean": 1.109375,
+      "rewards/warm_up_reward/std": 0.7549550831317902,
+      "step": 67
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 144.1041717529297,
+      "epoch": 0.7083333333333334,
+      "grad_norm": 2.268946790543885,
+      "kl": 0.04766845703125,
+      "learning_rate": 1e-06,
+      "loss": -0.0027,
+      "num_tokens": 2973200.0,
+      "reward": 1.325416773557663,
+      "reward_std": 0.8379913568496704,
+      "rewards/warm_up_reward/mean": 1.1045138835906982,
+      "rewards/warm_up_reward/std": 0.7519785463809967,
+      "step": 68
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.4791717529297,
+      "epoch": 0.71875,
+      "grad_norm": 2.40410834715932,
+      "kl": 0.0625,
+      "learning_rate": 1e-06,
+      "loss": 0.0508,
+      "num_tokens": 3016728.0,
+      "reward": 1.143750011920929,
+      "reward_std": 0.8826231509447098,
+      "rewards/warm_up_reward/mean": 0.953125,
+      "rewards/warm_up_reward/std": 0.7572390139102936,
+      "step": 69
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 145.9791717529297,
+      "epoch": 0.7291666666666666,
+      "grad_norm": 2.377991017189631,
+      "kl": 0.06512451171875,
+      "learning_rate": 1e-06,
+      "loss": 0.0505,
+      "num_tokens": 3060790.0,
+      "reward": 1.2854167819023132,
+      "reward_std": 0.9141092300415039,
+      "rewards/warm_up_reward/mean": 1.0711805671453476,
+      "rewards/warm_up_reward/std": 0.7661919444799423,
+      "step": 70
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 144.7916717529297,
+      "epoch": 0.7395833333333334,
+      "grad_norm": 5.490360584080418,
+      "kl": 0.068115234375,
+      "learning_rate": 1e-06,
+      "loss": 0.0061,
+      "num_tokens": 3104672.0,
+      "reward": 1.2937501072883606,
+      "reward_std": 0.9385685622692108,
+      "rewards/warm_up_reward/mean": 1.078125,
+      "rewards/warm_up_reward/std": 0.7564428001642227,
+      "step": 71
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 132.94792366027832,
+      "epoch": 0.75,
+      "grad_norm": 2.705450393270237,
+      "kl": 0.0748291015625,
+      "learning_rate": 1e-06,
+      "loss": 0.0032,
+      "num_tokens": 3147441.0,
+      "reward": 1.2687500715255737,
+      "reward_std": 0.9319685697555542,
+      "rewards/warm_up_reward/mean": 1.0572916567325592,
+      "rewards/warm_up_reward/std": 0.7771977633237839,
+      "step": 72
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 151.91667556762695,
+      "epoch": 0.7604166666666666,
+      "grad_norm": 2.254735299608175,
+      "kl": 0.07171630859375,
+      "learning_rate": 1e-06,
+      "loss": 0.0105,
+      "num_tokens": 3192121.0,
+      "reward": 1.0045834183692932,
+      "reward_std": 0.8630332052707672,
+      "rewards/warm_up_reward/mean": 0.8371527940034866,
+      "rewards/warm_up_reward/std": 0.7969614416360855,
+      "step": 73
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.31250190734863,
+      "epoch": 0.7708333333333334,
+      "grad_norm": 2.4523220833578345,
+      "kl": 0.05816650390625,
+      "learning_rate": 1e-06,
+      "loss": 0.0158,
+      "num_tokens": 3235453.0,
+      "reward": 1.1837501227855682,
+      "reward_std": 0.9126418828964233,
+      "rewards/warm_up_reward/mean": 0.9864583015441895,
+      "rewards/warm_up_reward/std": 0.7863775044679642,
+      "step": 74
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.7395896911621,
+      "epoch": 0.78125,
+      "grad_norm": 2.2478331336635513,
+      "kl": 0.0609130859375,
+      "learning_rate": 1e-06,
+      "loss": 0.0284,
+      "num_tokens": 3278964.0,
+      "reward": 1.2054167687892914,
+      "reward_std": 0.9118891954421997,
+      "rewards/warm_up_reward/mean": 1.0045138746500015,
+      "rewards/warm_up_reward/std": 0.7829048186540604,
+      "step": 75
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 139.71875381469727,
+      "epoch": 0.7916666666666666,
+      "grad_norm": 2.6147718994418203,
+      "kl": 0.0904541015625,
+      "learning_rate": 1e-06,
+      "loss": 0.0143,
+      "num_tokens": 3322407.0,
+      "reward": 1.2660417556762695,
+      "reward_std": 0.9197860509157181,
+      "rewards/warm_up_reward/mean": 1.0550346970558167,
+      "rewards/warm_up_reward/std": 0.7622723281383514,
+      "step": 76
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.53125762939453,
+      "epoch": 0.8020833333333334,
+      "grad_norm": 2.530432648354832,
+      "kl": 0.093505859375,
+      "learning_rate": 1e-06,
+      "loss": -0.0104,
+      "num_tokens": 3366036.0,
+      "reward": 1.1020834147930145,
+      "reward_std": 0.902558371424675,
+      "rewards/warm_up_reward/mean": 0.9184028059244156,
+      "rewards/warm_up_reward/std": 0.7975014746189117,
+      "step": 77
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 146.0416717529297,
+      "epoch": 0.8125,
+      "grad_norm": 2.2386503327740015,
+      "kl": 0.0811767578125,
+      "learning_rate": 1e-06,
+      "loss": 0.0184,
+      "num_tokens": 3410026.0,
+      "reward": 1.3406251072883606,
+      "reward_std": 0.8862900286912918,
+      "rewards/warm_up_reward/mean": 1.1171874850988388,
+      "rewards/warm_up_reward/std": 0.7199237793684006,
+      "step": 78
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 133.6041717529297,
+      "epoch": 0.8229166666666666,
+      "grad_norm": 2.9736551256376744,
+      "kl": 0.0992431640625,
+      "learning_rate": 1e-06,
+      "loss": 0.0029,
+      "num_tokens": 3452750.0,
+      "reward": 1.3556251227855682,
+      "reward_std": 0.8310635536909103,
+      "rewards/warm_up_reward/mean": 1.129687488079071,
+      "rewards/warm_up_reward/std": 0.7288718819618225,
+      "step": 79
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 139.45834350585938,
+      "epoch": 0.8333333333333334,
+      "grad_norm": 4.081234898460602,
+      "kl": 0.15234375,
+      "learning_rate": 1e-06,
+      "loss": -0.0154,
+      "num_tokens": 3496018.0,
+      "reward": 1.0906250923871994,
+      "reward_std": 0.8768025040626526,
+      "rewards/warm_up_reward/mean": 0.9088541716337204,
+      "rewards/warm_up_reward/std": 0.8029628545045853,
+      "step": 80
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 96,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 16,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5a3f66a9029d3e01a90da4fac03a83335332b06dd78156b03b293abade8e29
+size 7672

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)