Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

global_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73cb83b4a66498a69f422f8246370f8a8db1130ee1a5b69cdf40e6d735a94ec
+size 11423431820

global_step200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447a60c2ddfd132eedc75a74adb312bd1ac53a36d48b0ff9f583b44daaf6287e
+size 11423433484

global_step200/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbdbcb223a2c13fba3a2d4bb6c154dea0e2d8940a3cccb933ebb724608212fd7
+size 11423433356

global_step200/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67dda9a9cadc73474f90166376eea08cd202700acd107d5efca29d2bd86d88a0
+size 11423433804

global_step200/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d5824907e2a0f8592c079f020287bf76c73e88bcd9e3bbfdcbfef3dedec6caa
+size 11423433612

global_step200/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c50cc1f5367bbe86f616f2c6fd6864af3e9687491d41888fd5d9bd4feb1eac63
+size 11423433612

global_step200/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73323131969ab33d538ec15e5d00e419e31a624e987bdfe1b78dd7be0f5b55d3
+size 11423433420

global_step200/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20fe880ab1ca06a0138f8d6df640a2f820c6c1d51ff83c96df31528cb70e20d9
+size 11423431884

global_step200/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ccb4a06cdd6865f47295fb4a751f9a22346422acc5950e2aae9923cb4b0b993
+size 15231327544

latest

@@ -0,0 +1 @@
+global_step200

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0af4e8337c4bed48d5e7e6a93d90502d8ae892d62e0ef349dd5f356c9d363f
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ff3f00e7449f324b6f30a94ebd3113b588060faee2b94e8e27e32eeaf111ad
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c7d55ae53b051376eadd2037606bcd3953f44ad353af35ffec2018578103b6
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d32d37ced2ea354457d01450de534f198663af68c66e532c41063b19d06d241
+size 1089994880

model.safetensors.index.json

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

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60a1b40608e34bc801c8231f97b81c53b5290dfaed1b9cd0ccbeca29574a991
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad6a142a403eb9aafc4a3a9a856bca648fe31fd22d796867baca31fb13656aa
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bc23a138cc800b22881742c0f3f9a71731a9a7111c6058a0077e6274d21773
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3150b9f5095a0f370c8369dbd176c82bc2827860a93e379c65ea84bb670a9f68
+size 1064

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1711360312042907,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005850804485616773,
+      "grad_norm": 4.189145565032959,
+      "learning_rate": 1.9607843137254904e-07,
+      "loss": 0.6022,
+      "step": 1
+    },
+    {
+      "epoch": 0.011701608971233545,
+      "grad_norm": 4.088385105133057,
+      "learning_rate": 3.921568627450981e-07,
+      "loss": 0.6105,
+      "step": 2
+    },
+    {
+      "epoch": 0.017552413456850317,
+      "grad_norm": 4.105137348175049,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 0.6234,
+      "step": 3
+    },
+    {
+      "epoch": 0.02340321794246709,
+      "grad_norm": 4.010756015777588,
+      "learning_rate": 7.843137254901962e-07,
+      "loss": 0.5629,
+      "step": 4
+    },
+    {
+      "epoch": 0.02925402242808386,
+      "grad_norm": 4.201730728149414,
+      "learning_rate": 9.80392156862745e-07,
+      "loss": 0.6236,
+      "step": 5
+    },
+    {
+      "epoch": 0.035104826913700635,
+      "grad_norm": 4.13097620010376,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 0.6058,
+      "step": 6
+    },
+    {
+      "epoch": 0.040955631399317405,
+      "grad_norm": 3.753781318664551,
+      "learning_rate": 1.3725490196078434e-06,
+      "loss": 0.5798,
+      "step": 7
+    },
+    {
+      "epoch": 0.04680643588493418,
+      "grad_norm": 3.1203114986419678,
+      "learning_rate": 1.5686274509803923e-06,
+      "loss": 0.5575,
+      "step": 8
+    },
+    {
+      "epoch": 0.05265724037055095,
+      "grad_norm": 3.1326870918273926,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 0.5794,
+      "step": 9
+    },
+    {
+      "epoch": 0.05850804485616772,
+      "grad_norm": 3.01350736618042,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 0.5721,
+      "step": 10
+    },
+    {
+      "epoch": 0.0643588493417845,
+      "grad_norm": 2.0586817264556885,
+      "learning_rate": 2.1568627450980393e-06,
+      "loss": 0.5389,
+      "step": 11
+    },
+    {
+      "epoch": 0.07020965382740127,
+      "grad_norm": 2.056138753890991,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 0.5578,
+      "step": 12
+    },
+    {
+      "epoch": 0.07606045831301804,
+      "grad_norm": 1.8458319902420044,
+      "learning_rate": 2.549019607843137e-06,
+      "loss": 0.5432,
+      "step": 13
+    },
+    {
+      "epoch": 0.08191126279863481,
+      "grad_norm": 1.3385547399520874,
+      "learning_rate": 2.7450980392156867e-06,
+      "loss": 0.5375,
+      "step": 14
+    },
+    {
+      "epoch": 0.08776206728425158,
+      "grad_norm": 2.10184383392334,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.4834,
+      "step": 15
+    },
+    {
+      "epoch": 0.09361287176986836,
+      "grad_norm": 2.354717254638672,
+      "learning_rate": 3.1372549019607846e-06,
+      "loss": 0.5087,
+      "step": 16
+    },
+    {
+      "epoch": 0.09946367625548513,
+      "grad_norm": 2.4186935424804688,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.5408,
+      "step": 17
+    },
+    {
+      "epoch": 0.1053144807411019,
+      "grad_norm": 2.02093243598938,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 0.4967,
+      "step": 18
+    },
+    {
+      "epoch": 0.11116528522671867,
+      "grad_norm": 1.9769740104675293,
+      "learning_rate": 3.7254901960784316e-06,
+      "loss": 0.5429,
+      "step": 19
+    },
+    {
+      "epoch": 0.11701608971233544,
+      "grad_norm": 1.4087600708007812,
+      "learning_rate": 3.92156862745098e-06,
+      "loss": 0.4855,
+      "step": 20
+    },
+    {
+      "epoch": 0.12286689419795221,
+      "grad_norm": 1.4071195125579834,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 0.4956,
+      "step": 21
+    },
+    {
+      "epoch": 0.128717698683569,
+      "grad_norm": 1.4400174617767334,
+      "learning_rate": 4.313725490196079e-06,
+      "loss": 0.4966,
+      "step": 22
+    },
+    {
+      "epoch": 0.13456850316918575,
+      "grad_norm": 1.2176562547683716,
+      "learning_rate": 4.509803921568628e-06,
+      "loss": 0.4892,
+      "step": 23
+    },
+    {
+      "epoch": 0.14041930765480254,
+      "grad_norm": 1.0557763576507568,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.4664,
+      "step": 24
+    },
+    {
+      "epoch": 0.1462701121404193,
+      "grad_norm": 1.0654219388961792,
+      "learning_rate": 4.901960784313726e-06,
+      "loss": 0.4427,
+      "step": 25
+    },
+    {
+      "epoch": 0.15212091662603608,
+      "grad_norm": 0.8639155626296997,
+      "learning_rate": 5.098039215686274e-06,
+      "loss": 0.4676,
+      "step": 26
+    },
+    {
+      "epoch": 0.15797172111165286,
+      "grad_norm": 0.8091264963150024,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 0.4339,
+      "step": 27
+    },
+    {
+      "epoch": 0.16382252559726962,
+      "grad_norm": 0.7697594165802002,
+      "learning_rate": 5.4901960784313735e-06,
+      "loss": 0.4164,
+      "step": 28
+    },
+    {
+      "epoch": 0.1696733300828864,
+      "grad_norm": 0.8522382378578186,
+      "learning_rate": 5.686274509803922e-06,
+      "loss": 0.4512,
+      "step": 29
+    },
+    {
+      "epoch": 0.17552413456850316,
+      "grad_norm": 0.7640376687049866,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.432,
+      "step": 30
+    },
+    {
+      "epoch": 0.18137493905411994,
+      "grad_norm": 0.6247867941856384,
+      "learning_rate": 6.07843137254902e-06,
+      "loss": 0.408,
+      "step": 31
+    },
+    {
+      "epoch": 0.18722574353973673,
+      "grad_norm": 0.6288900971412659,
+      "learning_rate": 6.274509803921569e-06,
+      "loss": 0.4611,
+      "step": 32
+    },
+    {
+      "epoch": 0.19307654802535348,
+      "grad_norm": 0.6182562708854675,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 0.4257,
+      "step": 33
+    },
+    {
+      "epoch": 0.19892735251097027,
+      "grad_norm": 0.6193389892578125,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.4063,
+      "step": 34
+    },
+    {
+      "epoch": 0.20477815699658702,
+      "grad_norm": 0.6892727017402649,
+      "learning_rate": 6.862745098039216e-06,
+      "loss": 0.3967,
+      "step": 35
+    },
+    {
+      "epoch": 0.2106289614822038,
+      "grad_norm": 0.6725057363510132,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 0.4428,
+      "step": 36
+    },
+    {
+      "epoch": 0.21647976596782056,
+      "grad_norm": 0.5203535556793213,
+      "learning_rate": 7.2549019607843145e-06,
+      "loss": 0.4151,
+      "step": 37
+    },
+    {
+      "epoch": 0.22233057045343735,
+      "grad_norm": 0.45232418179512024,
+      "learning_rate": 7.450980392156863e-06,
+      "loss": 0.3666,
+      "step": 38
+    },
+    {
+      "epoch": 0.22818137493905413,
+      "grad_norm": 0.5872768759727478,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 0.4144,
+      "step": 39
+    },
+    {
+      "epoch": 0.2340321794246709,
+      "grad_norm": 0.526172399520874,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 0.4346,
+      "step": 40
+    },
+    {
+      "epoch": 0.23988298391028767,
+      "grad_norm": 0.5474228858947754,
+      "learning_rate": 8.03921568627451e-06,
+      "loss": 0.3965,
+      "step": 41
+    },
+    {
+      "epoch": 0.24573378839590443,
+      "grad_norm": 0.46727877855300903,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 0.4417,
+      "step": 42
+    },
+    {
+      "epoch": 0.2515845928815212,
+      "grad_norm": 0.40532198548316956,
+      "learning_rate": 8.43137254901961e-06,
+      "loss": 0.3851,
+      "step": 43
+    },
+    {
+      "epoch": 0.257435397367138,
+      "grad_norm": 0.4897397458553314,
+      "learning_rate": 8.627450980392157e-06,
+      "loss": 0.4013,
+      "step": 44
+    },
+    {
+      "epoch": 0.26328620185275475,
+      "grad_norm": 0.4565890431404114,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.3745,
+      "step": 45
+    },
+    {
+      "epoch": 0.2691370063383715,
+      "grad_norm": 0.38417261838912964,
+      "learning_rate": 9.019607843137256e-06,
+      "loss": 0.3783,
+      "step": 46
+    },
+    {
+      "epoch": 0.2749878108239883,
+      "grad_norm": 0.40912356972694397,
+      "learning_rate": 9.215686274509804e-06,
+      "loss": 0.3879,
+      "step": 47
+    },
+    {
+      "epoch": 0.2808386153096051,
+      "grad_norm": 0.42792415618896484,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.3837,
+      "step": 48
+    },
+    {
+      "epoch": 0.28668941979522183,
+      "grad_norm": 0.4394405484199524,
+      "learning_rate": 9.607843137254903e-06,
+      "loss": 0.4004,
+      "step": 49
+    },
+    {
+      "epoch": 0.2925402242808386,
+      "grad_norm": 0.4622238576412201,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 0.409,
+      "step": 50
+    },
+    {
+      "epoch": 0.2983910287664554,
+      "grad_norm": 0.3894466757774353,
+      "learning_rate": 1e-05,
+      "loss": 0.3766,
+      "step": 51
+    },
+    {
+      "epoch": 0.30424183325207216,
+      "grad_norm": 0.39314836263656616,
+      "learning_rate": 9.999882884955554e-06,
+      "loss": 0.3418,
+      "step": 52
+    },
+    {
+      "epoch": 0.3100926377376889,
+      "grad_norm": 0.44764766097068787,
+      "learning_rate": 9.999531545308584e-06,
+      "loss": 0.3909,
+      "step": 53
+    },
+    {
+      "epoch": 0.3159434422233057,
+      "grad_norm": 0.403144896030426,
+      "learning_rate": 9.998945997517957e-06,
+      "loss": 0.3716,
+      "step": 54
+    },
+    {
+      "epoch": 0.3217942467089225,
+      "grad_norm": 0.4303280711174011,
+      "learning_rate": 9.998126269014255e-06,
+      "loss": 0.4026,
+      "step": 55
+    },
+    {
+      "epoch": 0.32764505119453924,
+      "grad_norm": 0.4083136022090912,
+      "learning_rate": 9.997072398198492e-06,
+      "loss": 0.3842,
+      "step": 56
+    },
+    {
+      "epoch": 0.333495855680156,
+      "grad_norm": 0.3750261664390564,
+      "learning_rate": 9.99578443444032e-06,
+      "loss": 0.3605,
+      "step": 57
+    },
+    {
+      "epoch": 0.3393466601657728,
+      "grad_norm": 0.43343302607536316,
+      "learning_rate": 9.994262438075713e-06,
+      "loss": 0.4119,
+      "step": 58
+    },
+    {
+      "epoch": 0.34519746465138956,
+      "grad_norm": 0.3778004050254822,
+      "learning_rate": 9.992506480404137e-06,
+      "loss": 0.3616,
+      "step": 59
+    },
+    {
+      "epoch": 0.3510482691370063,
+      "grad_norm": 0.36973798274993896,
+      "learning_rate": 9.990516643685222e-06,
+      "loss": 0.3793,
+      "step": 60
+    },
+    {
+      "epoch": 0.35689907362262313,
+      "grad_norm": 0.3836229145526886,
+      "learning_rate": 9.988293021134888e-06,
+      "loss": 0.3492,
+      "step": 61
+    },
+    {
+      "epoch": 0.3627498781082399,
+      "grad_norm": 0.3700697720050812,
+      "learning_rate": 9.985835716921e-06,
+      "loss": 0.3583,
+      "step": 62
+    },
+    {
+      "epoch": 0.36860068259385664,
+      "grad_norm": 0.4023352861404419,
+      "learning_rate": 9.983144846158472e-06,
+      "loss": 0.3697,
+      "step": 63
+    },
+    {
+      "epoch": 0.37445148707947346,
+      "grad_norm": 0.38035494089126587,
+      "learning_rate": 9.980220534903889e-06,
+      "loss": 0.3772,
+      "step": 64
+    },
+    {
+      "epoch": 0.3803022915650902,
+      "grad_norm": 0.3641819953918457,
+      "learning_rate": 9.977062920149583e-06,
+      "loss": 0.3562,
+      "step": 65
+    },
+    {
+      "epoch": 0.38615309605070697,
+      "grad_norm": 0.39018484950065613,
+      "learning_rate": 9.973672149817232e-06,
+      "loss": 0.3377,
+      "step": 66
+    },
+    {
+      "epoch": 0.3920039005363237,
+      "grad_norm": 0.351622998714447,
+      "learning_rate": 9.970048382750925e-06,
+      "loss": 0.351,
+      "step": 67
+    },
+    {
+      "epoch": 0.39785470502194054,
+      "grad_norm": 0.40039461851119995,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 0.3775,
+      "step": 68
+    },
+    {
+      "epoch": 0.4037055095075573,
+      "grad_norm": 0.3892274796962738,
+      "learning_rate": 9.96210254835968e-06,
+      "loss": 0.4034,
+      "step": 69
+    },
+    {
+      "epoch": 0.40955631399317405,
+      "grad_norm": 0.4052744507789612,
+      "learning_rate": 9.957780853265441e-06,
+      "loss": 0.4079,
+      "step": 70
+    },
+    {
+      "epoch": 0.41540711847879086,
+      "grad_norm": 0.3877456486225128,
+      "learning_rate": 9.953226905881208e-06,
+      "loss": 0.3342,
+      "step": 71
+    },
+    {
+      "epoch": 0.4212579229644076,
+      "grad_norm": 0.4107078015804291,
+      "learning_rate": 9.948440919541277e-06,
+      "loss": 0.358,
+      "step": 72
+    },
+    {
+      "epoch": 0.4271087274500244,
+      "grad_norm": 0.37597158551216125,
+      "learning_rate": 9.943423118450051e-06,
+      "loss": 0.3948,
+      "step": 73
+    },
+    {
+      "epoch": 0.43295953193564113,
+      "grad_norm": 0.4590906798839569,
+      "learning_rate": 9.938173737671531e-06,
+      "loss": 0.3847,
+      "step": 74
+    },
+    {
+      "epoch": 0.43881033642125794,
+      "grad_norm": 0.48799118399620056,
+      "learning_rate": 9.932693023118299e-06,
+      "loss": 0.3845,
+      "step": 75
+    },
+    {
+      "epoch": 0.4446611409068747,
+      "grad_norm": 0.39222586154937744,
+      "learning_rate": 9.926981231540007e-06,
+      "loss": 0.3872,
+      "step": 76
+    },
+    {
+      "epoch": 0.45051194539249145,
+      "grad_norm": 0.4158020615577698,
+      "learning_rate": 9.921038630511345e-06,
+      "loss": 0.388,
+      "step": 77
+    },
+    {
+      "epoch": 0.45636274987810826,
+      "grad_norm": 0.40331101417541504,
+      "learning_rate": 9.91486549841951e-06,
+      "loss": 0.3705,
+      "step": 78
+    },
+    {
+      "epoch": 0.462213554363725,
+      "grad_norm": 0.4275971055030823,
+      "learning_rate": 9.908462124451152e-06,
+      "loss": 0.3849,
+      "step": 79
+    },
+    {
+      "epoch": 0.4680643588493418,
+      "grad_norm": 0.3466413915157318,
+      "learning_rate": 9.901828808578846e-06,
+      "loss": 0.347,
+      "step": 80
+    },
+    {
+      "epoch": 0.47391516333495853,
+      "grad_norm": 0.44375771284103394,
+      "learning_rate": 9.894965861547023e-06,
+      "loss": 0.373,
+      "step": 81
+    },
+    {
+      "epoch": 0.47976596782057535,
+      "grad_norm": 0.38661712408065796,
+      "learning_rate": 9.887873604857424e-06,
+      "loss": 0.3702,
+      "step": 82
+    },
+    {
+      "epoch": 0.4856167723061921,
+      "grad_norm": 0.41488274931907654,
+      "learning_rate": 9.88055237075403e-06,
+      "loss": 0.3574,
+      "step": 83
+    },
+    {
+      "epoch": 0.49146757679180886,
+      "grad_norm": 0.41137149930000305,
+      "learning_rate": 9.873002502207502e-06,
+      "loss": 0.3901,
+      "step": 84
+    },
+    {
+      "epoch": 0.49731838127742567,
+      "grad_norm": 0.39136987924575806,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.38,
+      "step": 85
+    },
+    {
+      "epoch": 0.5031691857630424,
+      "grad_norm": 0.37086671590805054,
+      "learning_rate": 9.857218287204204e-06,
+      "loss": 0.3541,
+      "step": 86
+    },
+    {
+      "epoch": 0.5090199902486592,
+      "grad_norm": 0.43105342984199524,
+      "learning_rate": 9.848984680175049e-06,
+      "loss": 0.4087,
+      "step": 87
+    },
+    {
+      "epoch": 0.514870794734276,
+      "grad_norm": 0.36811238527297974,
+      "learning_rate": 9.840523917523354e-06,
+      "loss": 0.3639,
+      "step": 88
+    },
+    {
+      "epoch": 0.5207215992198927,
+      "grad_norm": 0.378967821598053,
+      "learning_rate": 9.831836395602164e-06,
+      "loss": 0.3251,
+      "step": 89
+    },
+    {
+      "epoch": 0.5265724037055095,
+      "grad_norm": 0.36341214179992676,
+      "learning_rate": 9.822922521387277e-06,
+      "loss": 0.3705,
+      "step": 90
+    },
+    {
+      "epoch": 0.5324232081911263,
+      "grad_norm": 0.37682002782821655,
+      "learning_rate": 9.813782712458206e-06,
+      "loss": 0.3513,
+      "step": 91
+    },
+    {
+      "epoch": 0.538274012676743,
+      "grad_norm": 0.4142582416534424,
+      "learning_rate": 9.804417396978605e-06,
+      "loss": 0.3716,
+      "step": 92
+    },
+    {
+      "epoch": 0.5441248171623598,
+      "grad_norm": 0.4432157278060913,
+      "learning_rate": 9.794827013676206e-06,
+      "loss": 0.4126,
+      "step": 93
+    },
+    {
+      "epoch": 0.5499756216479766,
+      "grad_norm": 0.47457224130630493,
+      "learning_rate": 9.78501201182228e-06,
+      "loss": 0.3941,
+      "step": 94
+    },
+    {
+      "epoch": 0.5558264261335933,
+      "grad_norm": 0.35374128818511963,
+      "learning_rate": 9.774972851210572e-06,
+      "loss": 0.3893,
+      "step": 95
+    },
+    {
+      "epoch": 0.5616772306192102,
+      "grad_norm": 0.37110310792922974,
+      "learning_rate": 9.764710002135784e-06,
+      "loss": 0.3453,
+      "step": 96
+    },
+    {
+      "epoch": 0.567528035104827,
+      "grad_norm": 0.4286816716194153,
+      "learning_rate": 9.754223945371524e-06,
+      "loss": 0.3674,
+      "step": 97
+    },
+    {
+      "epoch": 0.5733788395904437,
+      "grad_norm": 0.3735758662223816,
+      "learning_rate": 9.743515172147793e-06,
+      "loss": 0.3572,
+      "step": 98
+    },
+    {
+      "epoch": 0.5792296440760605,
+      "grad_norm": 0.3784080445766449,
+      "learning_rate": 9.732584184127973e-06,
+      "loss": 0.3864,
+      "step": 99
+    },
+    {
+      "epoch": 0.5850804485616772,
+      "grad_norm": 0.40882179141044617,
+      "learning_rate": 9.721431493385322e-06,
+      "loss": 0.3458,
+      "step": 100
+    },
+    {
+      "epoch": 0.590931253047294,
+      "grad_norm": 0.3924429416656494,
+      "learning_rate": 9.710057622378992e-06,
+      "loss": 0.3497,
+      "step": 101
+    },
+    {
+      "epoch": 0.5967820575329108,
+      "grad_norm": 0.41799789667129517,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.3915,
+      "step": 102
+    },
+    {
+      "epoch": 0.6026328620185275,
+      "grad_norm": 0.4201458990573883,
+      "learning_rate": 9.686648481193994e-06,
+      "loss": 0.3797,
+      "step": 103
+    },
+    {
+      "epoch": 0.6084836665041443,
+      "grad_norm": 0.3876160979270935,
+      "learning_rate": 9.674614307640368e-06,
+      "loss": 0.3667,
+      "step": 104
+    },
+    {
+      "epoch": 0.6143344709897611,
+      "grad_norm": 0.39733994007110596,
+      "learning_rate": 9.66236114702178e-06,
+      "loss": 0.3746,
+      "step": 105
+    },
+    {
+      "epoch": 0.6201852754753778,
+      "grad_norm": 0.4422380030155182,
+      "learning_rate": 9.649889573350006e-06,
+      "loss": 0.3657,
+      "step": 106
+    },
+    {
+      "epoch": 0.6260360799609946,
+      "grad_norm": 0.34534451365470886,
+      "learning_rate": 9.637200170868607e-06,
+      "loss": 0.3173,
+      "step": 107
+    },
+    {
+      "epoch": 0.6318868844466115,
+      "grad_norm": 0.49448907375335693,
+      "learning_rate": 9.62429353402556e-06,
+      "loss": 0.3528,
+      "step": 108
+    },
+    {
+      "epoch": 0.6377376889322282,
+      "grad_norm": 0.4157074987888336,
+      "learning_rate": 9.611170267445401e-06,
+      "loss": 0.3647,
+      "step": 109
+    },
+    {
+      "epoch": 0.643588493417845,
+      "grad_norm": 0.3649308383464813,
+      "learning_rate": 9.597830985900913e-06,
+      "loss": 0.3592,
+      "step": 110
+    },
+    {
+      "epoch": 0.6494392979034618,
+      "grad_norm": 0.38802069425582886,
+      "learning_rate": 9.584276314284316e-06,
+      "loss": 0.3749,
+      "step": 111
+    },
+    {
+      "epoch": 0.6552901023890785,
+      "grad_norm": 0.41905415058135986,
+      "learning_rate": 9.570506887577994e-06,
+      "loss": 0.3761,
+      "step": 112
+    },
+    {
+      "epoch": 0.6611409068746953,
+      "grad_norm": 0.34973040223121643,
+      "learning_rate": 9.556523350824759e-06,
+      "loss": 0.3377,
+      "step": 113
+    },
+    {
+      "epoch": 0.666991711360312,
+      "grad_norm": 0.42152735590934753,
+      "learning_rate": 9.542326359097619e-06,
+      "loss": 0.3758,
+      "step": 114
+    },
+    {
+      "epoch": 0.6728425158459288,
+      "grad_norm": 0.34654316306114197,
+      "learning_rate": 9.527916577469104e-06,
+      "loss": 0.3612,
+      "step": 115
+    },
+    {
+      "epoch": 0.6786933203315456,
+      "grad_norm": 0.3440297842025757,
+      "learning_rate": 9.5132946809801e-06,
+      "loss": 0.37,
+      "step": 116
+    },
+    {
+      "epoch": 0.6845441248171623,
+      "grad_norm": 0.36565279960632324,
+      "learning_rate": 9.498461354608228e-06,
+      "loss": 0.352,
+      "step": 117
+    },
+    {
+      "epoch": 0.6903949293027791,
+      "grad_norm": 0.3970431983470917,
+      "learning_rate": 9.483417293235759e-06,
+      "loss": 0.3694,
+      "step": 118
+    },
+    {
+      "epoch": 0.6962457337883959,
+      "grad_norm": 0.3433384895324707,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 0.3657,
+      "step": 119
+    },
+    {
+      "epoch": 0.7020965382740126,
+      "grad_norm": 0.39245930314064026,
+      "learning_rate": 9.452699794345583e-06,
+      "loss": 0.362,
+      "step": 120
+    },
+    {
+      "epoch": 0.7079473427596294,
+      "grad_norm": 0.38453614711761475,
+      "learning_rate": 9.437027795820373e-06,
+      "loss": 0.3675,
+      "step": 121
+    },
+    {
+      "epoch": 0.7137981472452463,
+      "grad_norm": 0.369517058134079,
+      "learning_rate": 9.421147940212152e-06,
+      "loss": 0.3634,
+      "step": 122
+    },
+    {
+      "epoch": 0.719648951730863,
+      "grad_norm": 0.38849949836730957,
+      "learning_rate": 9.405060971428924e-06,
+      "loss": 0.3387,
+      "step": 123
+    },
+    {
+      "epoch": 0.7254997562164798,
+      "grad_norm": 0.4063083231449127,
+      "learning_rate": 9.388767643081109e-06,
+      "loss": 0.3719,
+      "step": 124
+    },
+    {
+      "epoch": 0.7313505607020966,
+      "grad_norm": 0.40234676003456116,
+      "learning_rate": 9.372268718446259e-06,
+      "loss": 0.3939,
+      "step": 125
+    },
+    {
+      "epoch": 0.7372013651877133,
+      "grad_norm": 0.3845783770084381,
+      "learning_rate": 9.355564970433288e-06,
+      "loss": 0.3699,
+      "step": 126
+    },
+    {
+      "epoch": 0.7430521696733301,
+      "grad_norm": 0.3887750506401062,
+      "learning_rate": 9.338657181546277e-06,
+      "loss": 0.3686,
+      "step": 127
+    },
+    {
+      "epoch": 0.7489029741589469,
+      "grad_norm": 0.3700850307941437,
+      "learning_rate": 9.321546143847802e-06,
+      "loss": 0.3431,
+      "step": 128
+    },
+    {
+      "epoch": 0.7547537786445636,
+      "grad_norm": 0.44235607981681824,
+      "learning_rate": 9.30423265892184e-06,
+      "loss": 0.3836,
+      "step": 129
+    },
+    {
+      "epoch": 0.7606045831301804,
+      "grad_norm": 0.39945074915885925,
+      "learning_rate": 9.286717537836211e-06,
+      "loss": 0.3706,
+      "step": 130
+    },
+    {
+      "epoch": 0.7664553876157971,
+      "grad_norm": 0.42615601420402527,
+      "learning_rate": 9.269001601104593e-06,
+      "loss": 0.369,
+      "step": 131
+    },
+    {
+      "epoch": 0.7723061921014139,
+      "grad_norm": 0.4713898003101349,
+      "learning_rate": 9.251085678648072e-06,
+      "loss": 0.3818,
+      "step": 132
+    },
+    {
+      "epoch": 0.7781569965870307,
+      "grad_norm": 0.3744489550590515,
+      "learning_rate": 9.232970609756267e-06,
+      "loss": 0.3542,
+      "step": 133
+    },
+    {
+      "epoch": 0.7840078010726474,
+      "grad_norm": 0.3802720308303833,
+      "learning_rate": 9.214657243048021e-06,
+      "loss": 0.3346,
+      "step": 134
+    },
+    {
+      "epoch": 0.7898586055582643,
+      "grad_norm": 0.45320552587509155,
+      "learning_rate": 9.196146436431635e-06,
+      "loss": 0.3766,
+      "step": 135
+    },
+    {
+      "epoch": 0.7957094100438811,
+      "grad_norm": 0.3729214370250702,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.3694,
+      "step": 136
+    },
+    {
+      "epoch": 0.8015602145294978,
+      "grad_norm": 0.3678078055381775,
+      "learning_rate": 9.158535981313395e-06,
+      "loss": 0.3515,
+      "step": 137
+    },
+    {
+      "epoch": 0.8074110190151146,
+      "grad_norm": 0.4144746959209442,
+      "learning_rate": 9.13943809471159e-06,
+      "loss": 0.3756,
+      "step": 138
+    },
+    {
+      "epoch": 0.8132618235007314,
+      "grad_norm": 0.3548150658607483,
+      "learning_rate": 9.120146291919206e-06,
+      "loss": 0.3494,
+      "step": 139
+    },
+    {
+      "epoch": 0.8191126279863481,
+      "grad_norm": 0.3966399133205414,
+      "learning_rate": 9.100661476680379e-06,
+      "loss": 0.3427,
+      "step": 140
+    },
+    {
+      "epoch": 0.8249634324719649,
+      "grad_norm": 0.4523519277572632,
+      "learning_rate": 9.08098456178111e-06,
+      "loss": 0.3641,
+      "step": 141
+    },
+    {
+      "epoch": 0.8308142369575817,
+      "grad_norm": 0.45737963914871216,
+      "learning_rate": 9.061116469006504e-06,
+      "loss": 0.3643,
+      "step": 142
+    },
+    {
+      "epoch": 0.8366650414431984,
+      "grad_norm": 0.34355804324150085,
+      "learning_rate": 9.041058129097586e-06,
+      "loss": 0.3227,
+      "step": 143
+    },
+    {
+      "epoch": 0.8425158459288152,
+      "grad_norm": 0.4239197373390198,
+      "learning_rate": 9.020810481707709e-06,
+      "loss": 0.3604,
+      "step": 144
+    },
+    {
+      "epoch": 0.8483666504144319,
+      "grad_norm": 0.4363431930541992,
+      "learning_rate": 9.00037447535852e-06,
+      "loss": 0.3785,
+      "step": 145
+    },
+    {
+      "epoch": 0.8542174549000487,
+      "grad_norm": 0.383635550737381,
+      "learning_rate": 8.979751067395534e-06,
+      "loss": 0.355,
+      "step": 146
+    },
+    {
+      "epoch": 0.8600682593856656,
+      "grad_norm": 0.3972126543521881,
+      "learning_rate": 8.958941223943292e-06,
+      "loss": 0.394,
+      "step": 147
+    },
+    {
+      "epoch": 0.8659190638712823,
+      "grad_norm": 0.3762996196746826,
+      "learning_rate": 8.937945919860086e-06,
+      "loss": 0.3779,
+      "step": 148
+    },
+    {
+      "epoch": 0.8717698683568991,
+      "grad_norm": 0.40220147371292114,
+      "learning_rate": 8.916766138692303e-06,
+      "loss": 0.3725,
+      "step": 149
+    },
+    {
+      "epoch": 0.8776206728425159,
+      "grad_norm": 0.35849395394325256,
+      "learning_rate": 8.895402872628352e-06,
+      "loss": 0.3533,
+      "step": 150
+    },
+    {
+      "epoch": 0.8834714773281326,
+      "grad_norm": 0.3301231861114502,
+      "learning_rate": 8.873857122452174e-06,
+      "loss": 0.3156,
+      "step": 151
+    },
+    {
+      "epoch": 0.8893222818137494,
+      "grad_norm": 0.39462047815322876,
+      "learning_rate": 8.852129897496367e-06,
+      "loss": 0.3538,
+      "step": 152
+    },
+    {
+      "epoch": 0.8951730862993662,
+      "grad_norm": 0.3844425082206726,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.3913,
+      "step": 153
+    },
+    {
+      "epoch": 0.9010238907849829,
+      "grad_norm": 0.37792298197746277,
+      "learning_rate": 8.808135103035407e-06,
+      "loss": 0.3495,
+      "step": 154
+    },
+    {
+      "epoch": 0.9068746952705997,
+      "grad_norm": 0.39290040731430054,
+      "learning_rate": 8.785869594511182e-06,
+      "loss": 0.3784,
+      "step": 155
+    },
+    {
+      "epoch": 0.9127254997562165,
+      "grad_norm": 0.3619037866592407,
+      "learning_rate": 8.763426733072624e-06,
+      "loss": 0.3614,
+      "step": 156
+    },
+    {
+      "epoch": 0.9185763042418332,
+      "grad_norm": 0.3633933663368225,
+      "learning_rate": 8.740807570078419e-06,
+      "loss": 0.3902,
+      "step": 157
+    },
+    {
+      "epoch": 0.92442710872745,
+      "grad_norm": 0.3714929223060608,
+      "learning_rate": 8.718013165146275e-06,
+      "loss": 0.3274,
+      "step": 158
+    },
+    {
+      "epoch": 0.9302779132130667,
+      "grad_norm": 0.38371893763542175,
+      "learning_rate": 8.695044586103297e-06,
+      "loss": 0.3507,
+      "step": 159
+    },
+    {
+      "epoch": 0.9361287176986836,
+      "grad_norm": 0.34635236859321594,
+      "learning_rate": 8.671902908935942e-06,
+      "loss": 0.3275,
+      "step": 160
+    },
+    {
+      "epoch": 0.9419795221843004,
+      "grad_norm": 0.34420835971832275,
+      "learning_rate": 8.648589217739635e-06,
+      "loss": 0.3461,
+      "step": 161
+    },
+    {
+      "epoch": 0.9478303266699171,
+      "grad_norm": 0.3969476819038391,
+      "learning_rate": 8.625104604667965e-06,
+      "loss": 0.3579,
+      "step": 162
+    },
+    {
+      "epoch": 0.9536811311555339,
+      "grad_norm": 0.3697619140148163,
+      "learning_rate": 8.601450169881533e-06,
+      "loss": 0.3476,
+      "step": 163
+    },
+    {
+      "epoch": 0.9595319356411507,
+      "grad_norm": 0.3809903860092163,
+      "learning_rate": 8.577627021496413e-06,
+      "loss": 0.36,
+      "step": 164
+    },
+    {
+      "epoch": 0.9653827401267674,
+      "grad_norm": 0.3934761881828308,
+      "learning_rate": 8.553636275532236e-06,
+      "loss": 0.3704,
+      "step": 165
+    },
+    {
+      "epoch": 0.9712335446123842,
+      "grad_norm": 0.3420058786869049,
+      "learning_rate": 8.529479055859918e-06,
+      "loss": 0.3335,
+      "step": 166
+    },
+    {
+      "epoch": 0.977084349098001,
+      "grad_norm": 0.3801231384277344,
+      "learning_rate": 8.505156494148997e-06,
+      "loss": 0.3723,
+      "step": 167
+    },
+    {
+      "epoch": 0.9829351535836177,
+      "grad_norm": 0.38984423875808716,
+      "learning_rate": 8.480669729814635e-06,
+      "loss": 0.3563,
+      "step": 168
+    },
+    {
+      "epoch": 0.9887859580692345,
+      "grad_norm": 0.369872123003006,
+      "learning_rate": 8.456019909964224e-06,
+      "loss": 0.3494,
+      "step": 169
+    },
+    {
+      "epoch": 0.9946367625548513,
+      "grad_norm": 0.3835128843784332,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.3672,
+      "step": 170
+    },
+    {
+      "epoch": 1.0014627011214041,
+      "grad_norm": 0.4482472538948059,
+      "learning_rate": 8.40623573028327e-06,
+      "loss": 0.4454,
+      "step": 171
+    },
+    {
+      "epoch": 1.007313505607021,
+      "grad_norm": 0.45144927501678467,
+      "learning_rate": 8.381103702643295e-06,
+      "loss": 0.3454,
+      "step": 172
+    },
+    {
+      "epoch": 1.0131643100926377,
+      "grad_norm": 0.3322243094444275,
+      "learning_rate": 8.35581328375915e-06,
+      "loss": 0.2828,
+      "step": 173
+    },
+    {
+      "epoch": 1.0190151145782544,
+      "grad_norm": 0.397659033536911,
+      "learning_rate": 8.330365658386252e-06,
+      "loss": 0.3287,
+      "step": 174
+    },
+    {
+      "epoch": 1.0248659190638714,
+      "grad_norm": 0.3485862910747528,
+      "learning_rate": 8.30476201864451e-06,
+      "loss": 0.2744,
+      "step": 175
+    },
+    {
+      "epoch": 1.030716723549488,
+      "grad_norm": 0.3832169473171234,
+      "learning_rate": 8.27900356396249e-06,
+      "loss": 0.2868,
+      "step": 176
+    },
+    {
+      "epoch": 1.0365675280351048,
+      "grad_norm": 0.4184396266937256,
+      "learning_rate": 8.25309150102121e-06,
+      "loss": 0.3291,
+      "step": 177
+    },
+    {
+      "epoch": 1.0424183325207217,
+      "grad_norm": 0.45518970489501953,
+      "learning_rate": 8.227027043697642e-06,
+      "loss": 0.3489,
+      "step": 178
+    },
+    {
+      "epoch": 1.0482691370063384,
+      "grad_norm": 0.3730817437171936,
+      "learning_rate": 8.200811413007808e-06,
+      "loss": 0.3055,
+      "step": 179
+    },
+    {
+      "epoch": 1.054119941491955,
+      "grad_norm": 0.398185133934021,
+      "learning_rate": 8.174445837049614e-06,
+      "loss": 0.326,
+      "step": 180
+    },
+    {
+      "epoch": 1.059970745977572,
+      "grad_norm": 0.4147329032421112,
+      "learning_rate": 8.147931550945301e-06,
+      "loss": 0.2961,
+      "step": 181
+    },
+    {
+      "epoch": 1.0658215504631887,
+      "grad_norm": 0.4088496267795563,
+      "learning_rate": 8.121269796783585e-06,
+      "loss": 0.3239,
+      "step": 182
+    },
+    {
+      "epoch": 1.0716723549488054,
+      "grad_norm": 0.35450735688209534,
+      "learning_rate": 8.094461823561473e-06,
+      "loss": 0.2851,
+      "step": 183
+    },
+    {
+      "epoch": 1.0775231594344223,
+      "grad_norm": 0.4081903100013733,
+      "learning_rate": 8.06750888712576e-06,
+      "loss": 0.3188,
+      "step": 184
+    },
+    {
+      "epoch": 1.083373963920039,
+      "grad_norm": 0.3934895396232605,
+      "learning_rate": 8.040412250114184e-06,
+      "loss": 0.2891,
+      "step": 185
+    },
+    {
+      "epoch": 1.0892247684056557,
+      "grad_norm": 0.35631951689720154,
+      "learning_rate": 8.013173181896283e-06,
+      "loss": 0.2667,
+      "step": 186
+    },
+    {
+      "epoch": 1.0950755728912727,
+      "grad_norm": 0.42703738808631897,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 0.312,
+      "step": 187
+    },
+    {
+      "epoch": 1.1009263773768894,
+      "grad_norm": 0.4023725986480713,
+      "learning_rate": 7.958272862621562e-06,
+      "loss": 0.3343,
+      "step": 188
+    },
+    {
+      "epoch": 1.106777181862506,
+      "grad_norm": 0.3514081537723541,
+      "learning_rate": 7.930614183426074e-06,
+      "loss": 0.2959,
+      "step": 189
+    },
+    {
+      "epoch": 1.1126279863481228,
+      "grad_norm": 0.40648946166038513,
+      "learning_rate": 7.902818216626446e-06,
+      "loss": 0.3529,
+      "step": 190
+    },
+    {
+      "epoch": 1.1184787908337397,
+      "grad_norm": 0.38296204805374146,
+      "learning_rate": 7.874886264353035e-06,
+      "loss": 0.2988,
+      "step": 191
+    },
+    {
+      "epoch": 1.1243295953193564,
+      "grad_norm": 0.4062958061695099,
+      "learning_rate": 7.846819635106569e-06,
+      "loss": 0.3344,
+      "step": 192
+    },
+    {
+      "epoch": 1.130180399804973,
+      "grad_norm": 0.3408312499523163,
+      "learning_rate": 7.818619643696863e-06,
+      "loss": 0.2857,
+      "step": 193
+    },
+    {
+      "epoch": 1.13603120429059,
+      "grad_norm": 0.3789331316947937,
+      "learning_rate": 7.790287611181217e-06,
+      "loss": 0.3077,
+      "step": 194
+    },
+    {
+      "epoch": 1.1418820087762067,
+      "grad_norm": 0.38520050048828125,
+      "learning_rate": 7.76182486480253e-06,
+      "loss": 0.3025,
+      "step": 195
+    },
+    {
+      "epoch": 1.1477328132618234,
+      "grad_norm": 0.3634053170681,
+      "learning_rate": 7.733232737927123e-06,
+      "loss": 0.3037,
+      "step": 196
+    },
+    {
+      "epoch": 1.1535836177474403,
+      "grad_norm": 0.42052581906318665,
+      "learning_rate": 7.70451256998228e-06,
+      "loss": 0.304,
+      "step": 197
+    },
+    {
+      "epoch": 1.159434422233057,
+      "grad_norm": 0.3758928179740906,
+      "learning_rate": 7.675665706393502e-06,
+      "loss": 0.2755,
+      "step": 198
+    },
+    {
+      "epoch": 1.1652852267186737,
+      "grad_norm": 0.35784485936164856,
+      "learning_rate": 7.646693498521472e-06,
+      "loss": 0.2876,
+      "step": 199
+    },
+    {
+      "epoch": 1.1711360312042907,
+      "grad_norm": 0.38650694489479065,
+      "learning_rate": 7.617597303598754e-06,
+      "loss": 0.288,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 510,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.7100142648497275e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2c8226bcc2cf11d655f392b5ea920f6bd2eea9e2a3df746ef9dcb5e58bc2df
+size 7032

zero_to_fp32.py

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