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": "/root/cproject_updated/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.47.1"
+}

global_step330/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1c926afd79594d521710eaa7aea1da900d4342c297e54f5f60b876b6af7422
+size 5742198243

global_step330/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:a49c519d84b7813744e6526364c111eabddbcee18cb7ab6052b1e02bfc751a1a
+size 5742198243

global_step330/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd30a7c0d57034150b2b8ff6774d45691cb7bce3db0358ef66f44eb46ab3635
+size 5742198243

global_step330/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785f0cfd892b0fda76104e79ff48c1dcd82b3935db30f71ee6da28ead87ac3ac
+size 5742198243

global_step330/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6fd1b8cee51efec999c49d7856a62cee5335dbb3c9bb63598167ac448b6be6
+size 5742198243

global_step330/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09fd18dc70063d1f2e6321b39cc9479bd29c82d35cb8b37971637cb8944785f5
+size 5742198243

global_step330/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:f4154dac51415a50f8ee10ae9495556b305ad3439325386d810bbc014674da7b
+size 5742198243

global_step330/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941a5685ce3f12fad2fbe9e5cf5387504f81279c6d0f2ff0cdc45e55d11b7018
+size 5742198243

global_step330/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b0ffd17fe99bb156e6896a953f977b1f3b2faae6a4b46bc9164f4e38720c733
+size 170133

global_step330/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eef76b686f83478ef44262ef78b5546c340c09968b72827ecbf3bbf4bbae8b1
+size 170133

global_step330/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5bc2f493aec601401bb59766845072edac0285f03f6fdb4eda36bd2051c587
+size 170133

global_step330/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22584a768b535d93d4f599c2f42e550e21ed63065fe99a4a7eba6be10490f29d
+size 170133

global_step330/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8794bfbda4bd70a9b9d7d94117f65138dd15b41e1f4ec9ff94200b4e6d2305
+size 170133

global_step330/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ee15d84ba7475b951f0d707163d39dea929129d874affd06492f7524fd176a
+size 170133

global_step330/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28243f0711075897fbdd70bb0529ad368026feb9cbe01929edda4aedefe595be
+size 170133

global_step330/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb122f7cac6d3b23053f601c52e2b1d54fbca5542a1cc26aa0b46bb85bac6569
+size 170133

latest

@@ -0,0 +1 @@
+global_step330

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526144b8d851bf585327c28dcc93293d8afe6b74b36e59310234ba6d112f98b1
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b02d4f8e3dcc86ad7a673e4617159cc4c36076f313d9a78d94750511a74f88c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664d903b356aa24bc62a6d70ddef0bfc4434a660fd8a08f833020e1ac90fdbcc
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52d1b3652828c54186d1e89082ec07f19a69c0e112dfa76b603a9568d8d8ad1
+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 sha256:575119a228f98110923ffa2dedcb50e3317251b26054355d015e0b2240d566f2
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0728b56dab7abb5ef8a0d4bae3519c5767c97467bdd886d26bf19cc8599d0312
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e481d4ef1546694da7337f6bb6c658b866dcb79b85deeb477da0d27ebe851e
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353c60be37ea56fc992fca446598ceca5d1fd002aa3bd6dbb9ad740e6f47ebb3
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9107fe964ba7205e354084b85210e5a5ea1c98cfd4d38adb9cd3926945dcae4
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d1bb1abee38b92e53f3f23549b642ce0f1edcdccf7b6129847ac61636e96d5
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd5516048e20f36959601574e29e40106085a7d3cdc7bf425ce5e84633490e6
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2c46927fc06939b4c976a01e4b95dec1f8b98ceaea86d31a5d756fc30ff006
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c372067c2e65a84860f907ed62c07f26ff90e78aba64c04d2d38130db00caa
+size 1064

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,2343 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9977324263038548,
+  "eval_steps": 500,
+  "global_step": 330,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0030234315948601664,
+      "grad_norm": 0.6349862119317693,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.3237,
+      "step": 1
+    },
+    {
+      "epoch": 0.006046863189720333,
+      "grad_norm": 0.6915137231647266,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.3595,
+      "step": 2
+    },
+    {
+      "epoch": 0.009070294784580499,
+      "grad_norm": 0.623700079073619,
+      "learning_rate": 1.5e-06,
+      "loss": 1.343,
+      "step": 3
+    },
+    {
+      "epoch": 0.012093726379440665,
+      "grad_norm": 0.7242880491963869,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.3527,
+      "step": 4
+    },
+    {
+      "epoch": 0.015117157974300832,
+      "grad_norm": 0.6516906859598985,
+      "learning_rate": 2.5e-06,
+      "loss": 1.3319,
+      "step": 5
+    },
+    {
+      "epoch": 0.018140589569160998,
+      "grad_norm": 0.5742747957897,
+      "learning_rate": 3e-06,
+      "loss": 1.342,
+      "step": 6
+    },
+    {
+      "epoch": 0.021164021164021163,
+      "grad_norm": 0.557815390462239,
+      "learning_rate": 3.5e-06,
+      "loss": 1.3152,
+      "step": 7
+    },
+    {
+      "epoch": 0.02418745275888133,
+      "grad_norm": 0.4620246107786041,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2963,
+      "step": 8
+    },
+    {
+      "epoch": 0.027210884353741496,
+      "grad_norm": 0.44763809541022137,
+      "learning_rate": 4.5e-06,
+      "loss": 1.2895,
+      "step": 9
+    },
+    {
+      "epoch": 0.030234315948601664,
+      "grad_norm": 0.3416187088663793,
+      "learning_rate": 5e-06,
+      "loss": 1.2531,
+      "step": 10
+    },
+    {
+      "epoch": 0.03325774754346183,
+      "grad_norm": 0.31917539621933483,
+      "learning_rate": 4.999970800043822e-06,
+      "loss": 1.2006,
+      "step": 11
+    },
+    {
+      "epoch": 0.036281179138321996,
+      "grad_norm": 0.27239571970104204,
+      "learning_rate": 4.9998832008573975e-06,
+      "loss": 1.1767,
+      "step": 12
+    },
+    {
+      "epoch": 0.039304610733182165,
+      "grad_norm": 0.32495241030295385,
+      "learning_rate": 4.999737204487039e-06,
+      "loss": 1.1951,
+      "step": 13
+    },
+    {
+      "epoch": 0.042328042328042326,
+      "grad_norm": 0.31114523478470957,
+      "learning_rate": 4.999532814343219e-06,
+      "loss": 1.1474,
+      "step": 14
+    },
+    {
+      "epoch": 0.045351473922902494,
+      "grad_norm": 0.26573282398874887,
+      "learning_rate": 4.999270035200483e-06,
+      "loss": 1.1684,
+      "step": 15
+    },
+    {
+      "epoch": 0.04837490551776266,
+      "grad_norm": 0.27675989125666167,
+      "learning_rate": 4.998948873197342e-06,
+      "loss": 1.142,
+      "step": 16
+    },
+    {
+      "epoch": 0.05139833711262283,
+      "grad_norm": 0.2341024474066861,
+      "learning_rate": 4.99856933583613e-06,
+      "loss": 1.1735,
+      "step": 17
+    },
+    {
+      "epoch": 0.05442176870748299,
+      "grad_norm": 0.20679018253539813,
+      "learning_rate": 4.998131431982826e-06,
+      "loss": 1.0896,
+      "step": 18
+    },
+    {
+      "epoch": 0.05744520030234316,
+      "grad_norm": 0.21159362728987222,
+      "learning_rate": 4.9976351718668485e-06,
+      "loss": 1.1191,
+      "step": 19
+    },
+    {
+      "epoch": 0.06046863189720333,
+      "grad_norm": 0.19379985234830382,
+      "learning_rate": 4.9970805670808174e-06,
+      "loss": 1.1162,
+      "step": 20
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.2039064731806591,
+      "learning_rate": 4.9964676305802794e-06,
+      "loss": 1.1155,
+      "step": 21
+    },
+    {
+      "epoch": 0.06651549508692366,
+      "grad_norm": 0.22133580902562022,
+      "learning_rate": 4.995796376683411e-06,
+      "loss": 1.0603,
+      "step": 22
+    },
+    {
+      "epoch": 0.06953892668178382,
+      "grad_norm": 0.24913058306438574,
+      "learning_rate": 4.9950668210706795e-06,
+      "loss": 1.0854,
+      "step": 23
+    },
+    {
+      "epoch": 0.07256235827664399,
+      "grad_norm": 0.22434864947712013,
+      "learning_rate": 4.994278980784478e-06,
+      "loss": 1.0601,
+      "step": 24
+    },
+    {
+      "epoch": 0.07558578987150416,
+      "grad_norm": 0.18349247230596857,
+      "learning_rate": 4.9934328742287285e-06,
+      "loss": 1.1042,
+      "step": 25
+    },
+    {
+      "epoch": 0.07860922146636433,
+      "grad_norm": 0.1585429266996897,
+      "learning_rate": 4.992528521168449e-06,
+      "loss": 1.0409,
+      "step": 26
+    },
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 0.16168593725598268,
+      "learning_rate": 4.991565942729298e-06,
+      "loss": 1.0341,
+      "step": 27
+    },
+    {
+      "epoch": 0.08465608465608465,
+      "grad_norm": 0.19566832668054185,
+      "learning_rate": 4.990545161397073e-06,
+      "loss": 1.0689,
+      "step": 28
+    },
+    {
+      "epoch": 0.08767951625094482,
+      "grad_norm": 0.2499930738278608,
+      "learning_rate": 4.989466201017188e-06,
+      "loss": 1.0096,
+      "step": 29
+    },
+    {
+      "epoch": 0.09070294784580499,
+      "grad_norm": 0.2779488624344162,
+      "learning_rate": 4.988329086794122e-06,
+      "loss": 1.0609,
+      "step": 30
+    },
+    {
+      "epoch": 0.09372637944066516,
+      "grad_norm": 0.2244846945907016,
+      "learning_rate": 4.987133845290823e-06,
+      "loss": 1.0366,
+      "step": 31
+    },
+    {
+      "epoch": 0.09674981103552532,
+      "grad_norm": 0.17994766023159892,
+      "learning_rate": 4.98588050442809e-06,
+      "loss": 1.0314,
+      "step": 32
+    },
+    {
+      "epoch": 0.09977324263038549,
+      "grad_norm": 0.22279237142259942,
+      "learning_rate": 4.984569093483922e-06,
+      "loss": 1.0445,
+      "step": 33
+    },
+    {
+      "epoch": 0.10279667422524566,
+      "grad_norm": 0.2494526014297992,
+      "learning_rate": 4.983199643092833e-06,
+      "loss": 1.0344,
+      "step": 34
+    },
+    {
+      "epoch": 0.10582010582010581,
+      "grad_norm": 0.21434458455232053,
+      "learning_rate": 4.981772185245135e-06,
+      "loss": 1.0421,
+      "step": 35
+    },
+    {
+      "epoch": 0.10884353741496598,
+      "grad_norm": 0.18307769428152484,
+      "learning_rate": 4.980286753286196e-06,
+      "loss": 0.9864,
+      "step": 36
+    },
+    {
+      "epoch": 0.11186696900982615,
+      "grad_norm": 0.21179293089346243,
+      "learning_rate": 4.97874338191565e-06,
+      "loss": 0.9842,
+      "step": 37
+    },
+    {
+      "epoch": 0.11489040060468632,
+      "grad_norm": 0.23379777419897857,
+      "learning_rate": 4.977142107186602e-06,
+      "loss": 0.9955,
+      "step": 38
+    },
+    {
+      "epoch": 0.11791383219954649,
+      "grad_norm": 0.20298340697744424,
+      "learning_rate": 4.975482966504772e-06,
+      "loss": 0.9957,
+      "step": 39
+    },
+    {
+      "epoch": 0.12093726379440665,
+      "grad_norm": 0.22788321802784506,
+      "learning_rate": 4.973765998627628e-06,
+      "loss": 0.9909,
+      "step": 40
+    },
+    {
+      "epoch": 0.12396069538926682,
+      "grad_norm": 0.22447377185154144,
+      "learning_rate": 4.97199124366348e-06,
+      "loss": 0.9995,
+      "step": 41
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.19695029744427425,
+      "learning_rate": 4.970158743070542e-06,
+      "loss": 0.9781,
+      "step": 42
+    },
+    {
+      "epoch": 0.13000755857898716,
+      "grad_norm": 0.178963231333608,
+      "learning_rate": 4.9682685396559625e-06,
+      "loss": 0.9779,
+      "step": 43
+    },
+    {
+      "epoch": 0.1330309901738473,
+      "grad_norm": 0.1873471219218099,
+      "learning_rate": 4.966320677574828e-06,
+      "loss": 0.9796,
+      "step": 44
+    },
+    {
+      "epoch": 0.1360544217687075,
+      "grad_norm": 0.22949932135410833,
+      "learning_rate": 4.964315202329127e-06,
+      "loss": 0.9965,
+      "step": 45
+    },
+    {
+      "epoch": 0.13907785336356765,
+      "grad_norm": 0.2274052062281532,
+      "learning_rate": 4.9622521607666936e-06,
+      "loss": 0.9625,
+      "step": 46
+    },
+    {
+      "epoch": 0.1421012849584278,
+      "grad_norm": 0.1806669455946557,
+      "learning_rate": 4.960131601080104e-06,
+      "loss": 0.9807,
+      "step": 47
+    },
+    {
+      "epoch": 0.14512471655328799,
+      "grad_norm": 0.19467061044424094,
+      "learning_rate": 4.957953572805558e-06,
+      "loss": 0.9615,
+      "step": 48
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.2731410757300855,
+      "learning_rate": 4.9557181268217225e-06,
+      "loss": 0.9819,
+      "step": 49
+    },
+    {
+      "epoch": 0.15117157974300832,
+      "grad_norm": 0.19042718807008738,
+      "learning_rate": 4.953425315348534e-06,
+      "loss": 0.9547,
+      "step": 50
+    },
+    {
+      "epoch": 0.15419501133786848,
+      "grad_norm": 0.16643927370098177,
+      "learning_rate": 4.9510751919459895e-06,
+      "loss": 0.9892,
+      "step": 51
+    },
+    {
+      "epoch": 0.15721844293272866,
+      "grad_norm": 0.2524323083468839,
+      "learning_rate": 4.94866781151289e-06,
+      "loss": 1.0181,
+      "step": 52
+    },
+    {
+      "epoch": 0.1602418745275888,
+      "grad_norm": 0.27545197371921265,
+      "learning_rate": 4.946203230285558e-06,
+      "loss": 0.9713,
+      "step": 53
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.17013540947461778,
+      "learning_rate": 4.943681505836523e-06,
+      "loss": 1.0005,
+      "step": 54
+    },
+    {
+      "epoch": 0.16628873771730915,
+      "grad_norm": 0.18283369295290966,
+      "learning_rate": 4.941102697073181e-06,
+      "loss": 0.9183,
+      "step": 55
+    },
+    {
+      "epoch": 0.1693121693121693,
+      "grad_norm": 0.2189807492467087,
+      "learning_rate": 4.938466864236413e-06,
+      "loss": 0.9683,
+      "step": 56
+    },
+    {
+      "epoch": 0.17233560090702948,
+      "grad_norm": 0.2766806847549335,
+      "learning_rate": 4.935774068899184e-06,
+      "loss": 0.958,
+      "step": 57
+    },
+    {
+      "epoch": 0.17535903250188964,
+      "grad_norm": 0.2295270706172793,
+      "learning_rate": 4.933024373965097e-06,
+      "loss": 0.9399,
+      "step": 58
+    },
+    {
+      "epoch": 0.17838246409674982,
+      "grad_norm": 0.20415845821236425,
+      "learning_rate": 4.930217843666929e-06,
+      "loss": 0.9677,
+      "step": 59
+    },
+    {
+      "epoch": 0.18140589569160998,
+      "grad_norm": 0.18705886763979152,
+      "learning_rate": 4.927354543565131e-06,
+      "loss": 0.9453,
+      "step": 60
+    },
+    {
+      "epoch": 0.18442932728647016,
+      "grad_norm": 0.25228689054978015,
+      "learning_rate": 4.924434540546291e-06,
+      "loss": 0.9639,
+      "step": 61
+    },
+    {
+      "epoch": 0.1874527588813303,
+      "grad_norm": 0.2685784416971121,
+      "learning_rate": 4.921457902821578e-06,
+      "loss": 0.9561,
+      "step": 62
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.24674154778238747,
+      "learning_rate": 4.918424699925146e-06,
+      "loss": 0.952,
+      "step": 63
+    },
+    {
+      "epoch": 0.19349962207105065,
+      "grad_norm": 0.19937803912058571,
+      "learning_rate": 4.915335002712506e-06,
+      "loss": 0.9158,
+      "step": 64
+    },
+    {
+      "epoch": 0.1965230536659108,
+      "grad_norm": 0.21943107617585558,
+      "learning_rate": 4.912188883358879e-06,
+      "loss": 0.9622,
+      "step": 65
+    },
+    {
+      "epoch": 0.19954648526077098,
+      "grad_norm": 0.20789781104002328,
+      "learning_rate": 4.9089864153575016e-06,
+      "loss": 0.9432,
+      "step": 66
+    },
+    {
+      "epoch": 0.20256991685563114,
+      "grad_norm": 0.21625333461538526,
+      "learning_rate": 4.9057276735179134e-06,
+      "loss": 0.9136,
+      "step": 67
+    },
+    {
+      "epoch": 0.20559334845049132,
+      "grad_norm": 0.20774782340550482,
+      "learning_rate": 4.902412733964212e-06,
+      "loss": 0.9205,
+      "step": 68
+    },
+    {
+      "epoch": 0.20861678004535147,
+      "grad_norm": 0.23205941698573587,
+      "learning_rate": 4.899041674133266e-06,
+      "loss": 0.9193,
+      "step": 69
+    },
+    {
+      "epoch": 0.21164021164021163,
+      "grad_norm": 0.20096610581169602,
+      "learning_rate": 4.895614572772916e-06,
+      "loss": 0.9332,
+      "step": 70
+    },
+    {
+      "epoch": 0.2146636432350718,
+      "grad_norm": 0.18733010074274722,
+      "learning_rate": 4.89213150994013e-06,
+      "loss": 0.9562,
+      "step": 71
+    },
+    {
+      "epoch": 0.21768707482993196,
+      "grad_norm": 0.2131500035254074,
+      "learning_rate": 4.888592566999134e-06,
+      "loss": 0.978,
+      "step": 72
+    },
+    {
+      "epoch": 0.22071050642479215,
+      "grad_norm": 0.25995206465303416,
+      "learning_rate": 4.884997826619512e-06,
+      "loss": 0.9615,
+      "step": 73
+    },
+    {
+      "epoch": 0.2237339380196523,
+      "grad_norm": 0.20122899473383501,
+      "learning_rate": 4.88134737277427e-06,
+      "loss": 0.9223,
+      "step": 74
+    },
+    {
+      "epoch": 0.22675736961451248,
+      "grad_norm": 0.20082627865414718,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 0.9129,
+      "step": 75
+    },
+    {
+      "epoch": 0.22978080120937264,
+      "grad_norm": 0.22559902896183986,
+      "learning_rate": 4.873879667084301e-06,
+      "loss": 0.9331,
+      "step": 76
+    },
+    {
+      "epoch": 0.2328042328042328,
+      "grad_norm": 0.24097328648057836,
+      "learning_rate": 4.870062589684917e-06,
+      "loss": 0.9302,
+      "step": 77
+    },
+    {
+      "epoch": 0.23582766439909297,
+      "grad_norm": 0.2191859905396367,
+      "learning_rate": 4.866190147706525e-06,
+      "loss": 0.906,
+      "step": 78
+    },
+    {
+      "epoch": 0.23885109599395313,
+      "grad_norm": 0.1927603541449588,
+      "learning_rate": 4.862262431609235e-06,
+      "loss": 0.9158,
+      "step": 79
+    },
+    {
+      "epoch": 0.2418745275888133,
+      "grad_norm": 0.20091846606347583,
+      "learning_rate": 4.858279533144358e-06,
+      "loss": 0.9241,
+      "step": 80
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 0.19776572498006212,
+      "learning_rate": 4.854241545352262e-06,
+      "loss": 0.908,
+      "step": 81
+    },
+    {
+      "epoch": 0.24792139077853365,
+      "grad_norm": 0.19142342325998066,
+      "learning_rate": 4.8501485625602e-06,
+      "loss": 0.9031,
+      "step": 82
+    },
+    {
+      "epoch": 0.2509448223733938,
+      "grad_norm": 0.255824517812554,
+      "learning_rate": 4.846000680380106e-06,
+      "loss": 0.896,
+      "step": 83
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.23838401037023174,
+      "learning_rate": 4.841797995706362e-06,
+      "loss": 0.9169,
+      "step": 84
+    },
+    {
+      "epoch": 0.25699168556311414,
+      "grad_norm": 0.20594758086068155,
+      "learning_rate": 4.837540606713538e-06,
+      "loss": 0.9293,
+      "step": 85
+    },
+    {
+      "epoch": 0.2600151171579743,
+      "grad_norm": 0.21813818048500913,
+      "learning_rate": 4.833228612854088e-06,
+      "loss": 0.9194,
+      "step": 86
+    },
+    {
+      "epoch": 0.26303854875283444,
+      "grad_norm": 0.23454835369326738,
+      "learning_rate": 4.828862114856038e-06,
+      "loss": 0.9214,
+      "step": 87
+    },
+    {
+      "epoch": 0.2660619803476946,
+      "grad_norm": 0.2204000662732641,
+      "learning_rate": 4.824441214720629e-06,
+      "loss": 0.907,
+      "step": 88
+    },
+    {
+      "epoch": 0.2690854119425548,
+      "grad_norm": 0.2250848297991148,
+      "learning_rate": 4.819966015719933e-06,
+      "loss": 0.9032,
+      "step": 89
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 0.2535347696118056,
+      "learning_rate": 4.815436622394442e-06,
+      "loss": 0.9149,
+      "step": 90
+    },
+    {
+      "epoch": 0.2751322751322751,
+      "grad_norm": 0.22450012032883543,
+      "learning_rate": 4.810853140550625e-06,
+      "loss": 0.9055,
+      "step": 91
+    },
+    {
+      "epoch": 0.2781557067271353,
+      "grad_norm": 0.17386208282106705,
+      "learning_rate": 4.806215677258456e-06,
+      "loss": 0.8933,
+      "step": 92
+    },
+    {
+      "epoch": 0.2811791383219955,
+      "grad_norm": 0.19053752177477154,
+      "learning_rate": 4.801524340848917e-06,
+      "loss": 0.8915,
+      "step": 93
+    },
+    {
+      "epoch": 0.2842025699168556,
+      "grad_norm": 0.2725320545499666,
+      "learning_rate": 4.796779240911461e-06,
+      "loss": 0.9251,
+      "step": 94
+    },
+    {
+      "epoch": 0.2872260015117158,
+      "grad_norm": 0.2386183196781376,
+      "learning_rate": 4.791980488291457e-06,
+      "loss": 0.8928,
+      "step": 95
+    },
+    {
+      "epoch": 0.29024943310657597,
+      "grad_norm": 0.1817710733957378,
+      "learning_rate": 4.787128195087596e-06,
+      "loss": 0.9165,
+      "step": 96
+    },
+    {
+      "epoch": 0.29327286470143615,
+      "grad_norm": 0.17308690210240787,
+      "learning_rate": 4.782222474649279e-06,
+      "loss": 0.887,
+      "step": 97
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.2404735832702819,
+      "learning_rate": 4.777263441573963e-06,
+      "loss": 0.9012,
+      "step": 98
+    },
+    {
+      "epoch": 0.29931972789115646,
+      "grad_norm": 0.28779677911496493,
+      "learning_rate": 4.772251211704487e-06,
+      "loss": 0.9016,
+      "step": 99
+    },
+    {
+      "epoch": 0.30234315948601664,
+      "grad_norm": 0.15787837522906498,
+      "learning_rate": 4.7671859021263635e-06,
+      "loss": 0.9051,
+      "step": 100
+    },
+    {
+      "epoch": 0.30536659108087677,
+      "grad_norm": 0.1575234808015298,
+      "learning_rate": 4.762067631165049e-06,
+      "loss": 0.8917,
+      "step": 101
+    },
+    {
+      "epoch": 0.30839002267573695,
+      "grad_norm": 0.17558403452861931,
+      "learning_rate": 4.756896518383173e-06,
+      "loss": 0.9174,
+      "step": 102
+    },
+    {
+      "epoch": 0.31141345427059713,
+      "grad_norm": 0.28974349430226604,
+      "learning_rate": 4.751672684577747e-06,
+      "loss": 0.8929,
+      "step": 103
+    },
+    {
+      "epoch": 0.3144368858654573,
+      "grad_norm": 0.24411092218088543,
+      "learning_rate": 4.746396251777348e-06,
+      "loss": 0.8811,
+      "step": 104
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.16801064806045637,
+      "learning_rate": 4.74106734323926e-06,
+      "loss": 0.8758,
+      "step": 105
+    },
+    {
+      "epoch": 0.3204837490551776,
+      "grad_norm": 0.19248014461061233,
+      "learning_rate": 4.7356860834466e-06,
+      "loss": 0.9103,
+      "step": 106
+    },
+    {
+      "epoch": 0.3235071806500378,
+      "grad_norm": 0.27209908752286666,
+      "learning_rate": 4.730252598105407e-06,
+      "loss": 0.8843,
+      "step": 107
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.2293714752972601,
+      "learning_rate": 4.72476701414171e-06,
+      "loss": 0.9231,
+      "step": 108
+    },
+    {
+      "epoch": 0.3295540438397581,
+      "grad_norm": 0.18392800235656956,
+      "learning_rate": 4.7192294596985564e-06,
+      "loss": 0.8552,
+      "step": 109
+    },
+    {
+      "epoch": 0.3325774754346183,
+      "grad_norm": 0.1893627518175467,
+      "learning_rate": 4.7136400641330245e-06,
+      "loss": 0.8811,
+      "step": 110
+    },
+    {
+      "epoch": 0.3356009070294785,
+      "grad_norm": 0.27532406651290064,
+      "learning_rate": 4.7079989580132005e-06,
+      "loss": 0.9032,
+      "step": 111
+    },
+    {
+      "epoch": 0.3386243386243386,
+      "grad_norm": 0.21281637805817608,
+      "learning_rate": 4.702306273115122e-06,
+      "loss": 0.8731,
+      "step": 112
+    },
+    {
+      "epoch": 0.3416477702191988,
+      "grad_norm": 0.21685692387167585,
+      "learning_rate": 4.696562142419712e-06,
+      "loss": 0.8713,
+      "step": 113
+    },
+    {
+      "epoch": 0.34467120181405897,
+      "grad_norm": 0.27021306476550466,
+      "learning_rate": 4.690766700109659e-06,
+      "loss": 0.88,
+      "step": 114
+    },
+    {
+      "epoch": 0.3476946334089191,
+      "grad_norm": 0.23439835580439225,
+      "learning_rate": 4.684920081566295e-06,
+      "loss": 0.8814,
+      "step": 115
+    },
+    {
+      "epoch": 0.3507180650037793,
+      "grad_norm": 0.21025681348048122,
+      "learning_rate": 4.679022423366424e-06,
+      "loss": 0.8535,
+      "step": 116
+    },
+    {
+      "epoch": 0.35374149659863946,
+      "grad_norm": 0.21924118290065314,
+      "learning_rate": 4.673073863279133e-06,
+      "loss": 0.8869,
+      "step": 117
+    },
+    {
+      "epoch": 0.35676492819349964,
+      "grad_norm": 0.2875708297089177,
+      "learning_rate": 4.667074540262577e-06,
+      "loss": 0.8646,
+      "step": 118
+    },
+    {
+      "epoch": 0.35978835978835977,
+      "grad_norm": 0.20014737080144987,
+      "learning_rate": 4.661024594460733e-06,
+      "loss": 0.8718,
+      "step": 119
+    },
+    {
+      "epoch": 0.36281179138321995,
+      "grad_norm": 0.19119381829230253,
+      "learning_rate": 4.654924167200124e-06,
+      "loss": 0.8683,
+      "step": 120
+    },
+    {
+      "epoch": 0.36583522297808013,
+      "grad_norm": 0.2655620248145862,
+      "learning_rate": 4.648773400986513e-06,
+      "loss": 0.8655,
+      "step": 121
+    },
+    {
+      "epoch": 0.3688586545729403,
+      "grad_norm": 0.25081787812962225,
+      "learning_rate": 4.6425724395015865e-06,
+      "loss": 0.8582,
+      "step": 122
+    },
+    {
+      "epoch": 0.37188208616780044,
+      "grad_norm": 0.2146047325963571,
+      "learning_rate": 4.636321427599586e-06,
+      "loss": 0.8893,
+      "step": 123
+    },
+    {
+      "epoch": 0.3749055177626606,
+      "grad_norm": 0.2309806267470169,
+      "learning_rate": 4.63002051130393e-06,
+      "loss": 0.8486,
+      "step": 124
+    },
+    {
+      "epoch": 0.3779289493575208,
+      "grad_norm": 0.27736367362748365,
+      "learning_rate": 4.623669837803803e-06,
+      "loss": 0.8687,
+      "step": 125
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.2224756513405458,
+      "learning_rate": 4.617269555450715e-06,
+      "loss": 0.8825,
+      "step": 126
+    },
+    {
+      "epoch": 0.3839758125472411,
+      "grad_norm": 0.17936830170379472,
+      "learning_rate": 4.610819813755038e-06,
+      "loss": 0.8546,
+      "step": 127
+    },
+    {
+      "epoch": 0.3869992441421013,
+      "grad_norm": 0.18923636586433076,
+      "learning_rate": 4.604320763382512e-06,
+      "loss": 0.87,
+      "step": 128
+    },
+    {
+      "epoch": 0.3900226757369615,
+      "grad_norm": 0.18724186374787236,
+      "learning_rate": 4.597772556150724e-06,
+      "loss": 0.8676,
+      "step": 129
+    },
+    {
+      "epoch": 0.3930461073318216,
+      "grad_norm": 0.2914426770268331,
+      "learning_rate": 4.591175345025567e-06,
+      "loss": 0.8799,
+      "step": 130
+    },
+    {
+      "epoch": 0.3960695389266818,
+      "grad_norm": 0.23506817928141502,
+      "learning_rate": 4.584529284117662e-06,
+      "loss": 0.8895,
+      "step": 131
+    },
+    {
+      "epoch": 0.39909297052154197,
+      "grad_norm": 0.19429487340998514,
+      "learning_rate": 4.5778345286787575e-06,
+      "loss": 0.8272,
+      "step": 132
+    },
+    {
+      "epoch": 0.4021164021164021,
+      "grad_norm": 0.24906142354962724,
+      "learning_rate": 4.5710912350981066e-06,
+      "loss": 0.8647,
+      "step": 133
+    },
+    {
+      "epoch": 0.4051398337112623,
+      "grad_norm": 0.25795927507557026,
+      "learning_rate": 4.56429956089881e-06,
+      "loss": 0.8653,
+      "step": 134
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.18224019982541997,
+      "learning_rate": 4.5574596647341414e-06,
+      "loss": 0.8555,
+      "step": 135
+    },
+    {
+      "epoch": 0.41118669690098264,
+      "grad_norm": 0.20473182208619398,
+      "learning_rate": 4.550571706383833e-06,
+      "loss": 0.8664,
+      "step": 136
+    },
+    {
+      "epoch": 0.41421012849584277,
+      "grad_norm": 0.22168708013084754,
+      "learning_rate": 4.543635846750351e-06,
+      "loss": 0.8515,
+      "step": 137
+    },
+    {
+      "epoch": 0.41723356009070295,
+      "grad_norm": 0.21632029243557258,
+      "learning_rate": 4.536652247855133e-06,
+      "loss": 0.8619,
+      "step": 138
+    },
+    {
+      "epoch": 0.42025699168556313,
+      "grad_norm": 0.1920055931208493,
+      "learning_rate": 4.529621072834805e-06,
+      "loss": 0.8566,
+      "step": 139
+    },
+    {
+      "epoch": 0.42328042328042326,
+      "grad_norm": 0.1880614895437287,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.8243,
+      "step": 140
+    },
+    {
+      "epoch": 0.42630385487528344,
+      "grad_norm": 0.25600769805101486,
+      "learning_rate": 4.515416652518366e-06,
+      "loss": 0.8551,
+      "step": 141
+    },
+    {
+      "epoch": 0.4293272864701436,
+      "grad_norm": 0.2034314626277561,
+      "learning_rate": 4.508243739037016e-06,
+      "loss": 0.8603,
+      "step": 142
+    },
+    {
+      "epoch": 0.4323507180650038,
+      "grad_norm": 0.23508415301120186,
+      "learning_rate": 4.501023913052326e-06,
+      "loss": 0.8826,
+      "step": 143
+    },
+    {
+      "epoch": 0.43537414965986393,
+      "grad_norm": 0.2775448226015208,
+      "learning_rate": 4.4937573432191766e-06,
+      "loss": 0.8764,
+      "step": 144
+    },
+    {
+      "epoch": 0.4383975812547241,
+      "grad_norm": 0.24618223106362153,
+      "learning_rate": 4.486444199284386e-06,
+      "loss": 0.8973,
+      "step": 145
+    },
+    {
+      "epoch": 0.4414210128495843,
+      "grad_norm": 0.23424108283949535,
+      "learning_rate": 4.47908465208274e-06,
+      "loss": 0.8736,
+      "step": 146
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.22742376996470443,
+      "learning_rate": 4.471678873533002e-06,
+      "loss": 0.8581,
+      "step": 147
+    },
+    {
+      "epoch": 0.4474678760393046,
+      "grad_norm": 0.24653243269473768,
+      "learning_rate": 4.464227036633901e-06,
+      "loss": 0.8489,
+      "step": 148
+    },
+    {
+      "epoch": 0.4504913076341648,
+      "grad_norm": 0.2408835452466121,
+      "learning_rate": 4.456729315460084e-06,
+      "loss": 0.8637,
+      "step": 149
+    },
+    {
+      "epoch": 0.45351473922902497,
+      "grad_norm": 0.20149761505503935,
+      "learning_rate": 4.449185885158056e-06,
+      "loss": 0.8671,
+      "step": 150
+    },
+    {
+      "epoch": 0.4565381708238851,
+      "grad_norm": 0.19127590785183332,
+      "learning_rate": 4.4415969219420846e-06,
+      "loss": 0.8792,
+      "step": 151
+    },
+    {
+      "epoch": 0.4595616024187453,
+      "grad_norm": 0.22390628054581238,
+      "learning_rate": 4.433962603090083e-06,
+      "loss": 0.8468,
+      "step": 152
+    },
+    {
+      "epoch": 0.46258503401360546,
+      "grad_norm": 0.2957253215613366,
+      "learning_rate": 4.426283106939474e-06,
+      "loss": 0.8268,
+      "step": 153
+    },
+    {
+      "epoch": 0.4656084656084656,
+      "grad_norm": 0.20506648122584112,
+      "learning_rate": 4.418558612883016e-06,
+      "loss": 0.8772,
+      "step": 154
+    },
+    {
+      "epoch": 0.46863189720332576,
+      "grad_norm": 0.18636265474604682,
+      "learning_rate": 4.410789301364621e-06,
+      "loss": 0.858,
+      "step": 155
+    },
+    {
+      "epoch": 0.47165532879818595,
+      "grad_norm": 0.2674232446173923,
+      "learning_rate": 4.402975353875134e-06,
+      "loss": 0.8683,
+      "step": 156
+    },
+    {
+      "epoch": 0.47467876039304613,
+      "grad_norm": 0.2747499333038218,
+      "learning_rate": 4.3951169529480934e-06,
+      "loss": 0.8439,
+      "step": 157
+    },
+    {
+      "epoch": 0.47770219198790626,
+      "grad_norm": 0.18463338955505504,
+      "learning_rate": 4.3872142821554695e-06,
+      "loss": 0.8321,
+      "step": 158
+    },
+    {
+      "epoch": 0.48072562358276644,
+      "grad_norm": 0.19683973897761153,
+      "learning_rate": 4.379267526103374e-06,
+      "loss": 0.8378,
+      "step": 159
+    },
+    {
+      "epoch": 0.4837490551776266,
+      "grad_norm": 0.23093724944543254,
+      "learning_rate": 4.3712768704277535e-06,
+      "loss": 0.8342,
+      "step": 160
+    },
+    {
+      "epoch": 0.48677248677248675,
+      "grad_norm": 0.25457828536678356,
+      "learning_rate": 4.36324250179004e-06,
+      "loss": 0.8438,
+      "step": 161
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.2341347444247441,
+      "learning_rate": 4.355164607872806e-06,
+      "loss": 0.874,
+      "step": 162
+    },
+    {
+      "epoch": 0.4928193499622071,
+      "grad_norm": 0.19832386653308293,
+      "learning_rate": 4.347043377375369e-06,
+      "loss": 0.8871,
+      "step": 163
+    },
+    {
+      "epoch": 0.4958427815570673,
+      "grad_norm": 0.23548674821464477,
+      "learning_rate": 4.338879000009389e-06,
+      "loss": 0.8571,
+      "step": 164
+    },
+    {
+      "epoch": 0.4988662131519274,
+      "grad_norm": 0.2564635876122362,
+      "learning_rate": 4.3306716664944345e-06,
+      "loss": 0.8441,
+      "step": 165
+    },
+    {
+      "epoch": 0.5018896447467877,
+      "grad_norm": 0.22937827244764553,
+      "learning_rate": 4.322421568553529e-06,
+      "loss": 0.8435,
+      "step": 166
+    },
+    {
+      "epoch": 0.5049130763416477,
+      "grad_norm": 0.20546938114609037,
+      "learning_rate": 4.314128898908672e-06,
+      "loss": 0.8427,
+      "step": 167
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 0.24461216551872245,
+      "learning_rate": 4.305793851276335e-06,
+      "loss": 0.8488,
+      "step": 168
+    },
+    {
+      "epoch": 0.5109599395313681,
+      "grad_norm": 0.2280451372713774,
+      "learning_rate": 4.297416620362939e-06,
+      "loss": 0.8493,
+      "step": 169
+    },
+    {
+      "epoch": 0.5139833711262283,
+      "grad_norm": 0.2202142714476725,
+      "learning_rate": 4.288997401860303e-06,
+      "loss": 0.8514,
+      "step": 170
+    },
+    {
+      "epoch": 0.5170068027210885,
+      "grad_norm": 0.2426775141297586,
+      "learning_rate": 4.280536392441078e-06,
+      "loss": 0.8501,
+      "step": 171
+    },
+    {
+      "epoch": 0.5200302343159486,
+      "grad_norm": 0.1998543423805206,
+      "learning_rate": 4.272033789754146e-06,
+      "loss": 0.8313,
+      "step": 172
+    },
+    {
+      "epoch": 0.5230536659108088,
+      "grad_norm": 0.1847895892138973,
+      "learning_rate": 4.263489792420008e-06,
+      "loss": 0.8195,
+      "step": 173
+    },
+    {
+      "epoch": 0.5260770975056689,
+      "grad_norm": 0.23817124539909545,
+      "learning_rate": 4.254904600026143e-06,
+      "loss": 0.8581,
+      "step": 174
+    },
+    {
+      "epoch": 0.5291005291005291,
+      "grad_norm": 0.2575742303999011,
+      "learning_rate": 4.246278413122344e-06,
+      "loss": 0.8511,
+      "step": 175
+    },
+    {
+      "epoch": 0.5321239606953893,
+      "grad_norm": 0.22609359204972732,
+      "learning_rate": 4.2376114332160325e-06,
+      "loss": 0.843,
+      "step": 176
+    },
+    {
+      "epoch": 0.5351473922902494,
+      "grad_norm": 0.22696322689045012,
+      "learning_rate": 4.2289038627675585e-06,
+      "loss": 0.833,
+      "step": 177
+    },
+    {
+      "epoch": 0.5381708238851096,
+      "grad_norm": 0.2083064134180325,
+      "learning_rate": 4.220155905185461e-06,
+      "loss": 0.8707,
+      "step": 178
+    },
+    {
+      "epoch": 0.5411942554799698,
+      "grad_norm": 0.2188998951871127,
+      "learning_rate": 4.211367764821722e-06,
+      "loss": 0.8756,
+      "step": 179
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 0.21174182945781866,
+      "learning_rate": 4.202539646966993e-06,
+      "loss": 0.8431,
+      "step": 180
+    },
+    {
+      "epoch": 0.54724111866969,
+      "grad_norm": 0.26921219919236117,
+      "learning_rate": 4.193671757845797e-06,
+      "loss": 0.8346,
+      "step": 181
+    },
+    {
+      "epoch": 0.5502645502645502,
+      "grad_norm": 0.2410488610748255,
+      "learning_rate": 4.184764304611715e-06,
+      "loss": 0.8323,
+      "step": 182
+    },
+    {
+      "epoch": 0.5532879818594104,
+      "grad_norm": 0.19188924232191892,
+      "learning_rate": 4.17581749534254e-06,
+      "loss": 0.8275,
+      "step": 183
+    },
+    {
+      "epoch": 0.5563114134542706,
+      "grad_norm": 0.24965929389660024,
+      "learning_rate": 4.166831539035423e-06,
+      "loss": 0.8558,
+      "step": 184
+    },
+    {
+      "epoch": 0.5593348450491308,
+      "grad_norm": 0.2715497253670651,
+      "learning_rate": 4.1578066456019885e-06,
+      "loss": 0.8667,
+      "step": 185
+    },
+    {
+      "epoch": 0.562358276643991,
+      "grad_norm": 0.19906288449082996,
+      "learning_rate": 4.148743025863432e-06,
+      "loss": 0.8535,
+      "step": 186
+    },
+    {
+      "epoch": 0.5653817082388511,
+      "grad_norm": 0.22076525732705374,
+      "learning_rate": 4.139640891545591e-06,
+      "loss": 0.8296,
+      "step": 187
+    },
+    {
+      "epoch": 0.5684051398337112,
+      "grad_norm": 0.25483531753570576,
+      "learning_rate": 4.130500455274005e-06,
+      "loss": 0.8355,
+      "step": 188
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.24421069561222894,
+      "learning_rate": 4.121321930568946e-06,
+      "loss": 0.8357,
+      "step": 189
+    },
+    {
+      "epoch": 0.5744520030234316,
+      "grad_norm": 0.20339394657166124,
+      "learning_rate": 4.112105531840427e-06,
+      "loss": 0.8357,
+      "step": 190
+    },
+    {
+      "epoch": 0.5774754346182918,
+      "grad_norm": 0.24233770822338466,
+      "learning_rate": 4.1028514743832e-06,
+      "loss": 0.8313,
+      "step": 191
+    },
+    {
+      "epoch": 0.5804988662131519,
+      "grad_norm": 0.2829777666494022,
+      "learning_rate": 4.093559974371725e-06,
+      "loss": 0.8378,
+      "step": 192
+    },
+    {
+      "epoch": 0.5835222978080121,
+      "grad_norm": 0.1699407087734907,
+      "learning_rate": 4.084231248855113e-06,
+      "loss": 0.8208,
+      "step": 193
+    },
+    {
+      "epoch": 0.5865457294028723,
+      "grad_norm": 0.17498689950665328,
+      "learning_rate": 4.074865515752068e-06,
+      "loss": 0.838,
+      "step": 194
+    },
+    {
+      "epoch": 0.5895691609977324,
+      "grad_norm": 0.2475691965670073,
+      "learning_rate": 4.065462993845785e-06,
+      "loss": 0.849,
+      "step": 195
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.24997313540826083,
+      "learning_rate": 4.056023902778846e-06,
+      "loss": 0.8229,
+      "step": 196
+    },
+    {
+      "epoch": 0.5956160241874527,
+      "grad_norm": 0.19976933217581305,
+      "learning_rate": 4.046548463048089e-06,
+      "loss": 0.8301,
+      "step": 197
+    },
+    {
+      "epoch": 0.5986394557823129,
+      "grad_norm": 0.24028559185538167,
+      "learning_rate": 4.037036895999453e-06,
+      "loss": 0.8462,
+      "step": 198
+    },
+    {
+      "epoch": 0.6016628873771731,
+      "grad_norm": 0.27335949880058813,
+      "learning_rate": 4.0274894238228115e-06,
+      "loss": 0.8364,
+      "step": 199
+    },
+    {
+      "epoch": 0.6046863189720333,
+      "grad_norm": 0.18909543268493909,
+      "learning_rate": 4.017906269546778e-06,
+      "loss": 0.8083,
+      "step": 200
+    },
+    {
+      "epoch": 0.6077097505668935,
+      "grad_norm": 0.20724602824279856,
+      "learning_rate": 4.0082876570335025e-06,
+      "loss": 0.8193,
+      "step": 201
+    },
+    {
+      "epoch": 0.6107331821617535,
+      "grad_norm": 0.26651899455610345,
+      "learning_rate": 3.9986338109734354e-06,
+      "loss": 0.8299,
+      "step": 202
+    },
+    {
+      "epoch": 0.6137566137566137,
+      "grad_norm": 0.20515478118259406,
+      "learning_rate": 3.988944956880082e-06,
+      "loss": 0.8323,
+      "step": 203
+    },
+    {
+      "epoch": 0.6167800453514739,
+      "grad_norm": 0.1823781343576012,
+      "learning_rate": 3.979221321084734e-06,
+      "loss": 0.8224,
+      "step": 204
+    },
+    {
+      "epoch": 0.6198034769463341,
+      "grad_norm": 0.19460227890197035,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 0.8243,
+      "step": 205
+    },
+    {
+      "epoch": 0.6228269085411943,
+      "grad_norm": 0.25256274653870814,
+      "learning_rate": 3.959670613770414e-06,
+      "loss": 0.834,
+      "step": 206
+    },
+    {
+      "epoch": 0.6258503401360545,
+      "grad_norm": 0.2099371278262912,
+      "learning_rate": 3.949843998955279e-06,
+      "loss": 0.8001,
+      "step": 207
+    },
+    {
+      "epoch": 0.6288737717309146,
+      "grad_norm": 0.18831071399800087,
+      "learning_rate": 3.939983515835157e-06,
+      "loss": 0.846,
+      "step": 208
+    },
+    {
+      "epoch": 0.6318972033257747,
+      "grad_norm": 0.20326222391630303,
+      "learning_rate": 3.9300893947505865e-06,
+      "loss": 0.813,
+      "step": 209
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.28946931059014386,
+      "learning_rate": 3.92016186682789e-06,
+      "loss": 0.8252,
+      "step": 210
+    },
+    {
+      "epoch": 0.6379440665154951,
+      "grad_norm": 0.20146394091804065,
+      "learning_rate": 3.9102011639737715e-06,
+      "loss": 0.8273,
+      "step": 211
+    },
+    {
+      "epoch": 0.6409674981103552,
+      "grad_norm": 0.16554710439809656,
+      "learning_rate": 3.900207518869901e-06,
+      "loss": 0.8294,
+      "step": 212
+    },
+    {
+      "epoch": 0.6439909297052154,
+      "grad_norm": 0.19154551239872575,
+      "learning_rate": 3.890181164967476e-06,
+      "loss": 0.8331,
+      "step": 213
+    },
+    {
+      "epoch": 0.6470143613000756,
+      "grad_norm": 0.2863695398034112,
+      "learning_rate": 3.880122336481774e-06,
+      "loss": 0.8156,
+      "step": 214
+    },
+    {
+      "epoch": 0.6500377928949358,
+      "grad_norm": 0.21052777788511692,
+      "learning_rate": 3.870031268386676e-06,
+      "loss": 0.7963,
+      "step": 215
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.1566104119157067,
+      "learning_rate": 3.859908196409177e-06,
+      "loss": 0.8247,
+      "step": 216
+    },
+    {
+      "epoch": 0.656084656084656,
+      "grad_norm": 0.17376065755010325,
+      "learning_rate": 3.849753357023885e-06,
+      "loss": 0.8412,
+      "step": 217
+    },
+    {
+      "epoch": 0.6591080876795162,
+      "grad_norm": 0.2775570184417396,
+      "learning_rate": 3.839566987447492e-06,
+      "loss": 0.8444,
+      "step": 218
+    },
+    {
+      "epoch": 0.6621315192743764,
+      "grad_norm": 0.3002446727716999,
+      "learning_rate": 3.829349325633233e-06,
+      "loss": 0.8353,
+      "step": 219
+    },
+    {
+      "epoch": 0.6651549508692366,
+      "grad_norm": 0.17501583537193782,
+      "learning_rate": 3.819100610265332e-06,
+      "loss": 0.8406,
+      "step": 220
+    },
+    {
+      "epoch": 0.6681783824640968,
+      "grad_norm": 0.16018543435725524,
+      "learning_rate": 3.8088210807534185e-06,
+      "loss": 0.8143,
+      "step": 221
+    },
+    {
+      "epoch": 0.671201814058957,
+      "grad_norm": 0.26632239617155334,
+      "learning_rate": 3.7985109772269435e-06,
+      "loss": 0.8099,
+      "step": 222
+    },
+    {
+      "epoch": 0.674225245653817,
+      "grad_norm": 0.2502372675648549,
+      "learning_rate": 3.7881705405295623e-06,
+      "loss": 0.828,
+      "step": 223
+    },
+    {
+      "epoch": 0.6772486772486772,
+      "grad_norm": 0.21825897588135384,
+      "learning_rate": 3.777800012213514e-06,
+      "loss": 0.8246,
+      "step": 224
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 0.27497686942905814,
+      "learning_rate": 3.767399634533976e-06,
+      "loss": 0.8131,
+      "step": 225
+    },
+    {
+      "epoch": 0.6832955404383976,
+      "grad_norm": 0.22856597196018685,
+      "learning_rate": 3.756969650443408e-06,
+      "loss": 0.8098,
+      "step": 226
+    },
+    {
+      "epoch": 0.6863189720332578,
+      "grad_norm": 0.21059170940590144,
+      "learning_rate": 3.7465103035858718e-06,
+      "loss": 0.8187,
+      "step": 227
+    },
+    {
+      "epoch": 0.6893424036281179,
+      "grad_norm": 0.2289160214691356,
+      "learning_rate": 3.7360218382913426e-06,
+      "loss": 0.8265,
+      "step": 228
+    },
+    {
+      "epoch": 0.6923658352229781,
+      "grad_norm": 0.22771294742249917,
+      "learning_rate": 3.7255044995700024e-06,
+      "loss": 0.8063,
+      "step": 229
+    },
+    {
+      "epoch": 0.6953892668178382,
+      "grad_norm": 0.220912987205476,
+      "learning_rate": 3.714958533106515e-06,
+      "loss": 0.8141,
+      "step": 230
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 0.2331093248404988,
+      "learning_rate": 3.7043841852542884e-06,
+      "loss": 0.7967,
+      "step": 231
+    },
+    {
+      "epoch": 0.7014361300075586,
+      "grad_norm": 0.24044315675315245,
+      "learning_rate": 3.6937817030297164e-06,
+      "loss": 0.8202,
+      "step": 232
+    },
+    {
+      "epoch": 0.7044595616024187,
+      "grad_norm": 0.17808063026487772,
+      "learning_rate": 3.6831513341064128e-06,
+      "loss": 0.824,
+      "step": 233
+    },
+    {
+      "epoch": 0.7074829931972789,
+      "grad_norm": 0.1686282272216412,
+      "learning_rate": 3.672493326809422e-06,
+      "loss": 0.8265,
+      "step": 234
+    },
+    {
+      "epoch": 0.7105064247921391,
+      "grad_norm": 0.2620354561369418,
+      "learning_rate": 3.661807930109422e-06,
+      "loss": 0.8156,
+      "step": 235
+    },
+    {
+      "epoch": 0.7135298563869993,
+      "grad_norm": 0.325482330440253,
+      "learning_rate": 3.651095393616904e-06,
+      "loss": 0.828,
+      "step": 236
+    },
+    {
+      "epoch": 0.7165532879818595,
+      "grad_norm": 0.15080114640909387,
+      "learning_rate": 3.6403559675763457e-06,
+      "loss": 0.7995,
+      "step": 237
+    },
+    {
+      "epoch": 0.7195767195767195,
+      "grad_norm": 0.14745127928311055,
+      "learning_rate": 3.629589902860363e-06,
+      "loss": 0.8087,
+      "step": 238
+    },
+    {
+      "epoch": 0.7226001511715797,
+      "grad_norm": 0.2799111726866219,
+      "learning_rate": 3.6187974509638496e-06,
+      "loss": 0.8176,
+      "step": 239
+    },
+    {
+      "epoch": 0.7256235827664399,
+      "grad_norm": 0.2502547915239206,
+      "learning_rate": 3.607978863998104e-06,
+      "loss": 0.8064,
+      "step": 240
+    },
+    {
+      "epoch": 0.7286470143613001,
+      "grad_norm": 0.13777657856560566,
+      "learning_rate": 3.5971343946849374e-06,
+      "loss": 0.8178,
+      "step": 241
+    },
+    {
+      "epoch": 0.7316704459561603,
+      "grad_norm": 0.1385328283480905,
+      "learning_rate": 3.586264296350775e-06,
+      "loss": 0.8027,
+      "step": 242
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 0.17341004642304678,
+      "learning_rate": 3.57536882292073e-06,
+      "loss": 0.8096,
+      "step": 243
+    },
+    {
+      "epoch": 0.7377173091458806,
+      "grad_norm": 0.3691916406878038,
+      "learning_rate": 3.564448228912682e-06,
+      "loss": 0.8338,
+      "step": 244
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.21689653213933718,
+      "learning_rate": 3.5535027694313233e-06,
+      "loss": 0.7977,
+      "step": 245
+    },
+    {
+      "epoch": 0.7437641723356009,
+      "grad_norm": 0.16595312089208156,
+      "learning_rate": 3.5425327001622034e-06,
+      "loss": 0.7987,
+      "step": 246
+    },
+    {
+      "epoch": 0.7467876039304611,
+      "grad_norm": 0.21979225164562236,
+      "learning_rate": 3.5315382773657563e-06,
+      "loss": 0.8181,
+      "step": 247
+    },
+    {
+      "epoch": 0.7498110355253212,
+      "grad_norm": 0.31450056661452935,
+      "learning_rate": 3.520519757871313e-06,
+      "loss": 0.8128,
+      "step": 248
+    },
+    {
+      "epoch": 0.7528344671201814,
+      "grad_norm": 0.155403218509628,
+      "learning_rate": 3.5094773990711024e-06,
+      "loss": 0.807,
+      "step": 249
+    },
+    {
+      "epoch": 0.7558578987150416,
+      "grad_norm": 0.14490425331756726,
+      "learning_rate": 3.4984114589142388e-06,
+      "loss": 0.7883,
+      "step": 250
+    },
+    {
+      "epoch": 0.7588813303099018,
+      "grad_norm": 0.21380341083079393,
+      "learning_rate": 3.4873221959006973e-06,
+      "loss": 0.8162,
+      "step": 251
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.35920542267660566,
+      "learning_rate": 3.476209869075273e-06,
+      "loss": 0.7852,
+      "step": 252
+    },
+    {
+      "epoch": 0.764928193499622,
+      "grad_norm": 0.14693329979199346,
+      "learning_rate": 3.4650747380215296e-06,
+      "loss": 0.8164,
+      "step": 253
+    },
+    {
+      "epoch": 0.7679516250944822,
+      "grad_norm": 0.2613621433404773,
+      "learning_rate": 3.4539170628557383e-06,
+      "loss": 0.8083,
+      "step": 254
+    },
+    {
+      "epoch": 0.7709750566893424,
+      "grad_norm": 0.3665112092678806,
+      "learning_rate": 3.442737104220801e-06,
+      "loss": 0.8181,
+      "step": 255
+    },
+    {
+      "epoch": 0.7739984882842026,
+      "grad_norm": 0.16067983638579006,
+      "learning_rate": 3.4315351232801597e-06,
+      "loss": 0.8162,
+      "step": 256
+    },
+    {
+      "epoch": 0.7770219198790628,
+      "grad_norm": 0.24580578582443013,
+      "learning_rate": 3.4203113817116955e-06,
+      "loss": 0.8199,
+      "step": 257
+    },
+    {
+      "epoch": 0.780045351473923,
+      "grad_norm": 0.331248956918326,
+      "learning_rate": 3.409066141701618e-06,
+      "loss": 0.7913,
+      "step": 258
+    },
+    {
+      "epoch": 0.783068783068783,
+      "grad_norm": 0.16426278470075412,
+      "learning_rate": 3.3977996659383396e-06,
+      "loss": 0.8166,
+      "step": 259
+    },
+    {
+      "epoch": 0.7860922146636432,
+      "grad_norm": 0.2057865252683302,
+      "learning_rate": 3.386512217606339e-06,
+      "loss": 0.8018,
+      "step": 260
+    },
+    {
+      "epoch": 0.7891156462585034,
+      "grad_norm": 0.3793459602253602,
+      "learning_rate": 3.3752040603800148e-06,
+      "loss": 0.8243,
+      "step": 261
+    },
+    {
+      "epoch": 0.7921390778533636,
+      "grad_norm": 0.14811638555402215,
+      "learning_rate": 3.3638754584175222e-06,
+      "loss": 0.8144,
+      "step": 262
+    },
+    {
+      "epoch": 0.7951625094482238,
+      "grad_norm": 0.3237839618432774,
+      "learning_rate": 3.352526676354606e-06,
+      "loss": 0.7933,
+      "step": 263
+    },
+    {
+      "epoch": 0.7981859410430839,
+      "grad_norm": 0.21169351866452582,
+      "learning_rate": 3.3411579792984178e-06,
+      "loss": 0.8125,
+      "step": 264
+    },
+    {
+      "epoch": 0.8012093726379441,
+      "grad_norm": 0.14502913140221696,
+      "learning_rate": 3.3297696328213215e-06,
+      "loss": 0.7919,
+      "step": 265
+    },
+    {
+      "epoch": 0.8042328042328042,
+      "grad_norm": 0.130046065883626,
+      "learning_rate": 3.318361902954692e-06,
+      "loss": 0.7925,
+      "step": 266
+    },
+    {
+      "epoch": 0.8072562358276644,
+      "grad_norm": 0.1806023890937921,
+      "learning_rate": 3.3069350561826997e-06,
+      "loss": 0.7977,
+      "step": 267
+    },
+    {
+      "epoch": 0.8102796674225246,
+      "grad_norm": 0.3661239179855748,
+      "learning_rate": 3.295489359436083e-06,
+      "loss": 0.8121,
+      "step": 268
+    },
+    {
+      "epoch": 0.8133030990173847,
+      "grad_norm": 0.15684544823299335,
+      "learning_rate": 3.2840250800859185e-06,
+      "loss": 0.8439,
+      "step": 269
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.1442117724504863,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.8205,
+      "step": 270
+    },
+    {
+      "epoch": 0.8193499622071051,
+      "grad_norm": 0.1630144971387636,
+      "learning_rate": 3.2610418452234315e-06,
+      "loss": 0.8116,
+      "step": 271
+    },
+    {
+      "epoch": 0.8223733938019653,
+      "grad_norm": 0.2272302138625313,
+      "learning_rate": 3.249523426598669e-06,
+      "loss": 0.7889,
+      "step": 272
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 0.2630488611954438,
+      "learning_rate": 3.2379874991329374e-06,
+      "loss": 0.8101,
+      "step": 273
+    },
+    {
+      "epoch": 0.8284202569916855,
+      "grad_norm": 0.1636882510390679,
+      "learning_rate": 3.2264343323050985e-06,
+      "loss": 0.8067,
+      "step": 274
+    },
+    {
+      "epoch": 0.8314436885865457,
+      "grad_norm": 0.1800718434777349,
+      "learning_rate": 3.214864195996723e-06,
+      "loss": 0.8267,
+      "step": 275
+    },
+    {
+      "epoch": 0.8344671201814059,
+      "grad_norm": 0.27772170659214646,
+      "learning_rate": 3.2032773604857915e-06,
+      "loss": 0.8021,
+      "step": 276
+    },
+    {
+      "epoch": 0.8374905517762661,
+      "grad_norm": 0.2524388193093376,
+      "learning_rate": 3.1916740964403736e-06,
+      "loss": 0.8067,
+      "step": 277
+    },
+    {
+      "epoch": 0.8405139833711263,
+      "grad_norm": 0.18970600852145528,
+      "learning_rate": 3.1800546749123108e-06,
+      "loss": 0.8073,
+      "step": 278
+    },
+    {
+      "epoch": 0.8435374149659864,
+      "grad_norm": 0.19923073362072904,
+      "learning_rate": 3.168419367330883e-06,
+      "loss": 0.799,
+      "step": 279
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "grad_norm": 0.25436094223895794,
+      "learning_rate": 3.1567684454964674e-06,
+      "loss": 0.8041,
+      "step": 280
+    },
+    {
+      "epoch": 0.8495842781557067,
+      "grad_norm": 0.21128266721448266,
+      "learning_rate": 3.14510218157419e-06,
+      "loss": 0.8113,
+      "step": 281
+    },
+    {
+      "epoch": 0.8526077097505669,
+      "grad_norm": 0.22163072880133364,
+      "learning_rate": 3.133420848087566e-06,
+      "loss": 0.7889,
+      "step": 282
+    },
+    {
+      "epoch": 0.8556311413454271,
+      "grad_norm": 0.22883591781527274,
+      "learning_rate": 3.121724717912138e-06,
+      "loss": 0.7917,
+      "step": 283
+    },
+    {
+      "epoch": 0.8586545729402872,
+      "grad_norm": 0.2032672012417271,
+      "learning_rate": 3.110014064269094e-06,
+      "loss": 0.8032,
+      "step": 284
+    },
+    {
+      "epoch": 0.8616780045351474,
+      "grad_norm": 0.1740199158625731,
+      "learning_rate": 3.0982891607188948e-06,
+      "loss": 0.7827,
+      "step": 285
+    },
+    {
+      "epoch": 0.8647014361300076,
+      "grad_norm": 0.18106353392739202,
+      "learning_rate": 3.0865502811548755e-06,
+      "loss": 0.7896,
+      "step": 286
+    },
+    {
+      "epoch": 0.8677248677248677,
+      "grad_norm": 0.2292881686201471,
+      "learning_rate": 3.0747976997968513e-06,
+      "loss": 0.8159,
+      "step": 287
+    },
+    {
+      "epoch": 0.8707482993197279,
+      "grad_norm": 0.27476966438745903,
+      "learning_rate": 3.0630316911847112e-06,
+      "loss": 0.7938,
+      "step": 288
+    },
+    {
+      "epoch": 0.873771730914588,
+      "grad_norm": 0.21250803524552264,
+      "learning_rate": 3.051252530172003e-06,
+      "loss": 0.7912,
+      "step": 289
+    },
+    {
+      "epoch": 0.8767951625094482,
+      "grad_norm": 0.20109882386036412,
+      "learning_rate": 3.039460491919516e-06,
+      "loss": 0.8005,
+      "step": 290
+    },
+    {
+      "epoch": 0.8798185941043084,
+      "grad_norm": 0.22987450725486983,
+      "learning_rate": 3.0276558518888496e-06,
+      "loss": 0.8081,
+      "step": 291
+    },
+    {
+      "epoch": 0.8828420256991686,
+      "grad_norm": 0.20495650915854588,
+      "learning_rate": 3.015838885835981e-06,
+      "loss": 0.8115,
+      "step": 292
+    },
+    {
+      "epoch": 0.8858654572940288,
+      "grad_norm": 0.17141615072214778,
+      "learning_rate": 3.0040098698048232e-06,
+      "loss": 0.7813,
+      "step": 293
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.18881546824196338,
+      "learning_rate": 2.992169080120776e-06,
+      "loss": 0.8113,
+      "step": 294
+    },
+    {
+      "epoch": 0.891912320483749,
+      "grad_norm": 0.20261508334609984,
+      "learning_rate": 2.9803167933842712e-06,
+      "loss": 0.7993,
+      "step": 295
+    },
+    {
+      "epoch": 0.8949357520786092,
+      "grad_norm": 0.2637865639683421,
+      "learning_rate": 2.9684532864643123e-06,
+      "loss": 0.8025,
+      "step": 296
+    },
+    {
+      "epoch": 0.8979591836734694,
+      "grad_norm": 0.20588016874386464,
+      "learning_rate": 2.9565788364920034e-06,
+      "loss": 0.7869,
+      "step": 297
+    },
+    {
+      "epoch": 0.9009826152683296,
+      "grad_norm": 0.1838418464531271,
+      "learning_rate": 2.944693720854081e-06,
+      "loss": 0.7976,
+      "step": 298
+    },
+    {
+      "epoch": 0.9040060468631897,
+      "grad_norm": 0.2238627689541774,
+      "learning_rate": 2.932798217186429e-06,
+      "loss": 0.7886,
+      "step": 299
+    },
+    {
+      "epoch": 0.9070294784580499,
+      "grad_norm": 0.2223361558094008,
+      "learning_rate": 2.920892603367596e-06,
+      "loss": 0.8163,
+      "step": 300
+    },
+    {
+      "epoch": 0.91005291005291,
+      "grad_norm": 0.1664138917818463,
+      "learning_rate": 2.908977157512305e-06,
+      "loss": 0.7859,
+      "step": 301
+    },
+    {
+      "epoch": 0.9130763416477702,
+      "grad_norm": 0.218098712406248,
+      "learning_rate": 2.897052157964952e-06,
+      "loss": 0.818,
+      "step": 302
+    },
+    {
+      "epoch": 0.9160997732426304,
+      "grad_norm": 0.25476932805817953,
+      "learning_rate": 2.8851178832931076e-06,
+      "loss": 0.7936,
+      "step": 303
+    },
+    {
+      "epoch": 0.9191232048374905,
+      "grad_norm": 0.20454797870655053,
+      "learning_rate": 2.8731746122810105e-06,
+      "loss": 0.8009,
+      "step": 304
+    },
+    {
+      "epoch": 0.9221466364323507,
+      "grad_norm": 0.2171163509058848,
+      "learning_rate": 2.8612226239230536e-06,
+      "loss": 0.8012,
+      "step": 305
+    },
+    {
+      "epoch": 0.9251700680272109,
+      "grad_norm": 0.3201406418230194,
+      "learning_rate": 2.8492621974172653e-06,
+      "loss": 0.8347,
+      "step": 306
+    },
+    {
+      "epoch": 0.9281934996220711,
+      "grad_norm": 0.20044446217181253,
+      "learning_rate": 2.8372936121587895e-06,
+      "loss": 0.8066,
+      "step": 307
+    },
+    {
+      "epoch": 0.9312169312169312,
+      "grad_norm": 0.16283549638272465,
+      "learning_rate": 2.8253171477333585e-06,
+      "loss": 0.8049,
+      "step": 308
+    },
+    {
+      "epoch": 0.9342403628117913,
+      "grad_norm": 0.20912249423273097,
+      "learning_rate": 2.813333083910761e-06,
+      "loss": 0.8112,
+      "step": 309
+    },
+    {
+      "epoch": 0.9372637944066515,
+      "grad_norm": 0.28501513792396893,
+      "learning_rate": 2.8013417006383078e-06,
+      "loss": 0.8033,
+      "step": 310
+    },
+    {
+      "epoch": 0.9402872260015117,
+      "grad_norm": 0.17569005132324075,
+      "learning_rate": 2.7893432780342928e-06,
+      "loss": 0.7905,
+      "step": 311
+    },
+    {
+      "epoch": 0.9433106575963719,
+      "grad_norm": 0.1707451012967817,
+      "learning_rate": 2.7773380963814454e-06,
+      "loss": 0.7992,
+      "step": 312
+    },
+    {
+      "epoch": 0.9463340891912321,
+      "grad_norm": 0.23658188962283105,
+      "learning_rate": 2.76532643612039e-06,
+      "loss": 0.7959,
+      "step": 313
+    },
+    {
+      "epoch": 0.9493575207860923,
+      "grad_norm": 0.2417426081720488,
+      "learning_rate": 2.7533085778430884e-06,
+      "loss": 0.7719,
+      "step": 314
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.21779534491141914,
+      "learning_rate": 2.7412848022862883e-06,
+      "loss": 0.8148,
+      "step": 315
+    },
+    {
+      "epoch": 0.9554043839758125,
+      "grad_norm": 0.1937439406511132,
+      "learning_rate": 2.729255390324966e-06,
+      "loss": 0.8099,
+      "step": 316
+    },
+    {
+      "epoch": 0.9584278155706727,
+      "grad_norm": 0.22418232835047394,
+      "learning_rate": 2.717220622965762e-06,
+      "loss": 0.8029,
+      "step": 317
+    },
+    {
+      "epoch": 0.9614512471655329,
+      "grad_norm": 0.24163066601859826,
+      "learning_rate": 2.7051807813404213e-06,
+      "loss": 0.8069,
+      "step": 318
+    },
+    {
+      "epoch": 0.9644746787603931,
+      "grad_norm": 0.17718761833134763,
+      "learning_rate": 2.6931361466992225e-06,
+      "loss": 0.7964,
+      "step": 319
+    },
+    {
+      "epoch": 0.9674981103552532,
+      "grad_norm": 0.21359305838545312,
+      "learning_rate": 2.6810870004044065e-06,
+      "loss": 0.7777,
+      "step": 320
+    },
+    {
+      "epoch": 0.9705215419501134,
+      "grad_norm": 0.2951108231827231,
+      "learning_rate": 2.6690336239236097e-06,
+      "loss": 0.7654,
+      "step": 321
+    },
+    {
+      "epoch": 0.9735449735449735,
+      "grad_norm": 0.17887426724913263,
+      "learning_rate": 2.6569762988232838e-06,
+      "loss": 0.8021,
+      "step": 322
+    },
+    {
+      "epoch": 0.9765684051398337,
+      "grad_norm": 0.16446650801438847,
+      "learning_rate": 2.644915306762121e-06,
+      "loss": 0.7996,
+      "step": 323
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.18349619699553313,
+      "learning_rate": 2.632850929484472e-06,
+      "loss": 0.769,
+      "step": 324
+    },
+    {
+      "epoch": 0.982615268329554,
+      "grad_norm": 0.23290485597057656,
+      "learning_rate": 2.620783448813768e-06,
+      "loss": 0.8104,
+      "step": 325
+    },
+    {
+      "epoch": 0.9856386999244142,
+      "grad_norm": 0.21697778026585082,
+      "learning_rate": 2.6087131466459344e-06,
+      "loss": 0.7919,
+      "step": 326
+    },
+    {
+      "epoch": 0.9886621315192744,
+      "grad_norm": 0.18436604515216662,
+      "learning_rate": 2.5966403049428056e-06,
+      "loss": 0.7819,
+      "step": 327
+    },
+    {
+      "epoch": 0.9916855631141346,
+      "grad_norm": 0.1916879714375915,
+      "learning_rate": 2.5845652057255414e-06,
+      "loss": 0.7565,
+      "step": 328
+    },
+    {
+      "epoch": 0.9947089947089947,
+      "grad_norm": 0.2338419771871179,
+      "learning_rate": 2.572488131068037e-06,
+      "loss": 0.8002,
+      "step": 329
+    },
+    {
+      "epoch": 0.9977324263038548,
+      "grad_norm": 0.19973120898443514,
+      "learning_rate": 2.560409363090331e-06,
+      "loss": 0.8019,
+      "step": 330
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 660,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 330,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.219445850938278e+18,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8dc356c79e92fd1dfe01156e2711a4d4a4aa39d1d0df2b0c7689e3a6050337
+size 8312

zero_to_fp32.py

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