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": "/gruntdata/event_graph/llm_models/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

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

latest

@@ -0,0 +1 @@
+global_step262

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2405c80e4ecc7508ec4db3fa5e6301fbe90e96c59ee21668d2e4d2746bb2455
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfa6e619467636a201d15d151e28e30da870ace525076ce69caf6599df0b842
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9cd60a89a9b04aad75dafd852316bc6a102357a88d9095b0dde203e41f8f70
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22fa26d92c21dc26a0e25aa3aecb4a6e1919aece75f88e057b8e112fbf237c86
+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 sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:636b9316043a83033cce566847f96f6f04de1799464b9db62e6755acb2834eff
+size 1064

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1881 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9745042492917846,
+  "eval_steps": 500,
+  "global_step": 264,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0113314447592068,
+      "grad_norm": 24.700892966997085,
+      "learning_rate": 1.8518518518518518e-07,
+      "loss": 1.6228,
+      "step": 1
+    },
+    {
+      "epoch": 0.0226628895184136,
+      "grad_norm": 25.319873190341358,
+      "learning_rate": 3.7037037037037036e-07,
+      "loss": 1.6327,
+      "step": 2
+    },
+    {
+      "epoch": 0.0339943342776204,
+      "grad_norm": 24.785410230478583,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 1.6085,
+      "step": 3
+    },
+    {
+      "epoch": 0.0453257790368272,
+      "grad_norm": 24.530949684513566,
+      "learning_rate": 7.407407407407407e-07,
+      "loss": 1.5921,
+      "step": 4
+    },
+    {
+      "epoch": 0.056657223796033995,
+      "grad_norm": 21.437475590002645,
+      "learning_rate": 9.259259259259259e-07,
+      "loss": 1.4876,
+      "step": 5
+    },
+    {
+      "epoch": 0.0679886685552408,
+      "grad_norm": 23.598738552751918,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.5618,
+      "step": 6
+    },
+    {
+      "epoch": 0.07932011331444759,
+      "grad_norm": 24.355821351281282,
+      "learning_rate": 1.2962962962962962e-06,
+      "loss": 1.5728,
+      "step": 7
+    },
+    {
+      "epoch": 0.0906515580736544,
+      "grad_norm": 17.949944552531893,
+      "learning_rate": 1.4814814814814815e-06,
+      "loss": 1.3796,
+      "step": 8
+    },
+    {
+      "epoch": 0.10198300283286119,
+      "grad_norm": 15.608410231061514,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.3663,
+      "step": 9
+    },
+    {
+      "epoch": 0.11331444759206799,
+      "grad_norm": 12.967898302916174,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 1.2852,
+      "step": 10
+    },
+    {
+      "epoch": 0.12464589235127478,
+      "grad_norm": 5.5745605303959005,
+      "learning_rate": 2.037037037037037e-06,
+      "loss": 1.1179,
+      "step": 11
+    },
+    {
+      "epoch": 0.1359773371104816,
+      "grad_norm": 5.003567410730206,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.1428,
+      "step": 12
+    },
+    {
+      "epoch": 0.14730878186968838,
+      "grad_norm": 4.580788434319785,
+      "learning_rate": 2.4074074074074075e-06,
+      "loss": 1.1386,
+      "step": 13
+    },
+    {
+      "epoch": 0.15864022662889518,
+      "grad_norm": 4.208213518050668,
+      "learning_rate": 2.5925925925925925e-06,
+      "loss": 1.1171,
+      "step": 14
+    },
+    {
+      "epoch": 0.16997167138810199,
+      "grad_norm": 3.6924260397238076,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.9945,
+      "step": 15
+    },
+    {
+      "epoch": 0.1813031161473088,
+      "grad_norm": 4.282401825239783,
+      "learning_rate": 2.962962962962963e-06,
+      "loss": 1.0298,
+      "step": 16
+    },
+    {
+      "epoch": 0.19263456090651557,
+      "grad_norm": 3.998142705803431,
+      "learning_rate": 3.1481481481481483e-06,
+      "loss": 0.998,
+      "step": 17
+    },
+    {
+      "epoch": 0.20396600566572237,
+      "grad_norm": 3.652954638326853,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0252,
+      "step": 18
+    },
+    {
+      "epoch": 0.21529745042492918,
+      "grad_norm": 3.1106976788005833,
+      "learning_rate": 3.5185185185185187e-06,
+      "loss": 0.948,
+      "step": 19
+    },
+    {
+      "epoch": 0.22662889518413598,
+      "grad_norm": 2.3583842636458874,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.9141,
+      "step": 20
+    },
+    {
+      "epoch": 0.23796033994334279,
+      "grad_norm": 2.331383902586234,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.91,
+      "step": 21
+    },
+    {
+      "epoch": 0.24929178470254956,
+      "grad_norm": 2.3290851154332155,
+      "learning_rate": 4.074074074074074e-06,
+      "loss": 0.92,
+      "step": 22
+    },
+    {
+      "epoch": 0.26062322946175637,
+      "grad_norm": 2.088852025013323,
+      "learning_rate": 4.2592592592592596e-06,
+      "loss": 0.8521,
+      "step": 23
+    },
+    {
+      "epoch": 0.2719546742209632,
+      "grad_norm": 1.8360508671725202,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.8143,
+      "step": 24
+    },
+    {
+      "epoch": 0.28328611898017,
+      "grad_norm": 1.7885693902522186,
+      "learning_rate": 4.62962962962963e-06,
+      "loss": 0.8486,
+      "step": 25
+    },
+    {
+      "epoch": 0.29461756373937675,
+      "grad_norm": 1.9031889309290633,
+      "learning_rate": 4.814814814814815e-06,
+      "loss": 0.834,
+      "step": 26
+    },
+    {
+      "epoch": 0.3059490084985836,
+      "grad_norm": 1.6679534815550068,
+      "learning_rate": 5e-06,
+      "loss": 0.8224,
+      "step": 27
+    },
+    {
+      "epoch": 0.31728045325779036,
+      "grad_norm": 1.6886754763902796,
+      "learning_rate": 4.999780362391087e-06,
+      "loss": 0.8133,
+      "step": 28
+    },
+    {
+      "epoch": 0.3286118980169972,
+      "grad_norm": 1.8004804802995344,
+      "learning_rate": 4.9991214881568884e-06,
+      "loss": 0.8145,
+      "step": 29
+    },
+    {
+      "epoch": 0.33994334277620397,
+      "grad_norm": 1.7444546855121879,
+      "learning_rate": 4.998023493068255e-06,
+      "loss": 0.8028,
+      "step": 30
+    },
+    {
+      "epoch": 0.35127478753541075,
+      "grad_norm": 1.6882783810092117,
+      "learning_rate": 4.996486570053999e-06,
+      "loss": 0.784,
+      "step": 31
+    },
+    {
+      "epoch": 0.3626062322946176,
+      "grad_norm": 1.7424306321156553,
+      "learning_rate": 4.994510989166998e-06,
+      "loss": 0.802,
+      "step": 32
+    },
+    {
+      "epoch": 0.37393767705382436,
+      "grad_norm": 1.5326860366155606,
+      "learning_rate": 4.99209709753674e-06,
+      "loss": 0.7578,
+      "step": 33
+    },
+    {
+      "epoch": 0.38526912181303113,
+      "grad_norm": 1.645466819050736,
+      "learning_rate": 4.9892453193083354e-06,
+      "loss": 0.7715,
+      "step": 34
+    },
+    {
+      "epoch": 0.39660056657223797,
+      "grad_norm": 1.8351805495790603,
+      "learning_rate": 4.9859561555679835e-06,
+      "loss": 0.7516,
+      "step": 35
+    },
+    {
+      "epoch": 0.40793201133144474,
+      "grad_norm": 1.5892721538246122,
+      "learning_rate": 4.982230184254934e-06,
+      "loss": 0.7658,
+      "step": 36
+    },
+    {
+      "epoch": 0.4192634560906516,
+      "grad_norm": 1.493020596244931,
+      "learning_rate": 4.978068060059929e-06,
+      "loss": 0.7676,
+      "step": 37
+    },
+    {
+      "epoch": 0.43059490084985835,
+      "grad_norm": 1.502680841198379,
+      "learning_rate": 4.9734705143101744e-06,
+      "loss": 0.7674,
+      "step": 38
+    },
+    {
+      "epoch": 0.44192634560906513,
+      "grad_norm": 1.526315536964418,
+      "learning_rate": 4.968438354840834e-06,
+      "loss": 0.747,
+      "step": 39
+    },
+    {
+      "epoch": 0.45325779036827196,
+      "grad_norm": 1.771193783955554,
+      "learning_rate": 4.962972465853087e-06,
+      "loss": 0.8251,
+      "step": 40
+    },
+    {
+      "epoch": 0.46458923512747874,
+      "grad_norm": 1.4751654383068609,
+      "learning_rate": 4.9570738077587635e-06,
+      "loss": 0.7587,
+      "step": 41
+    },
+    {
+      "epoch": 0.47592067988668557,
+      "grad_norm": 1.498540884039298,
+      "learning_rate": 4.950743417011591e-06,
+      "loss": 0.8311,
+      "step": 42
+    },
+    {
+      "epoch": 0.48725212464589235,
+      "grad_norm": 1.4059209239064798,
+      "learning_rate": 4.9439824059250794e-06,
+      "loss": 0.7655,
+      "step": 43
+    },
+    {
+      "epoch": 0.4985835694050991,
+      "grad_norm": 1.4871399277100446,
+      "learning_rate": 4.936791962477076e-06,
+      "loss": 0.7358,
+      "step": 44
+    },
+    {
+      "epoch": 0.509915014164306,
+      "grad_norm": 1.4257000290167645,
+      "learning_rate": 4.929173350101025e-06,
+      "loss": 0.7163,
+      "step": 45
+    },
+    {
+      "epoch": 0.5212464589235127,
+      "grad_norm": 1.4659192682033193,
+      "learning_rate": 4.921127907463972e-06,
+      "loss": 0.7061,
+      "step": 46
+    },
+    {
+      "epoch": 0.5325779036827195,
+      "grad_norm": 1.484618377703729,
+      "learning_rate": 4.912657048231343e-06,
+      "loss": 0.7651,
+      "step": 47
+    },
+    {
+      "epoch": 0.5439093484419264,
+      "grad_norm": 1.4947896835576073,
+      "learning_rate": 4.903762260818552e-06,
+      "loss": 0.7311,
+      "step": 48
+    },
+    {
+      "epoch": 0.5552407932011332,
+      "grad_norm": 1.3805335802092924,
+      "learning_rate": 4.89444510812947e-06,
+      "loss": 0.7327,
+      "step": 49
+    },
+    {
+      "epoch": 0.56657223796034,
+      "grad_norm": 1.5190953752467466,
+      "learning_rate": 4.884707227281807e-06,
+      "loss": 0.772,
+      "step": 50
+    },
+    {
+      "epoch": 0.5779036827195467,
+      "grad_norm": 1.5965731476318468,
+      "learning_rate": 4.874550329319457e-06,
+      "loss": 0.698,
+      "step": 51
+    },
+    {
+      "epoch": 0.5892351274787535,
+      "grad_norm": 1.4556721950898377,
+      "learning_rate": 4.863976198911845e-06,
+      "loss": 0.7267,
+      "step": 52
+    },
+    {
+      "epoch": 0.6005665722379604,
+      "grad_norm": 1.548206103166572,
+      "learning_rate": 4.852986694040347e-06,
+      "loss": 0.7188,
+      "step": 53
+    },
+    {
+      "epoch": 0.6118980169971672,
+      "grad_norm": 1.5029231129419343,
+      "learning_rate": 4.84158374567182e-06,
+      "loss": 0.7452,
+      "step": 54
+    },
+    {
+      "epoch": 0.623229461756374,
+      "grad_norm": 1.3962918545527763,
+      "learning_rate": 4.829769357419317e-06,
+      "loss": 0.7117,
+      "step": 55
+    },
+    {
+      "epoch": 0.6345609065155807,
+      "grad_norm": 1.3990946918305756,
+      "learning_rate": 4.817545605190026e-06,
+      "loss": 0.6797,
+      "step": 56
+    },
+    {
+      "epoch": 0.6458923512747875,
+      "grad_norm": 1.4406458676366833,
+      "learning_rate": 4.804914636820517e-06,
+      "loss": 0.7229,
+      "step": 57
+    },
+    {
+      "epoch": 0.6572237960339944,
+      "grad_norm": 1.4774647700554635,
+      "learning_rate": 4.791878671699343e-06,
+      "loss": 0.7117,
+      "step": 58
+    },
+    {
+      "epoch": 0.6685552407932012,
+      "grad_norm": 1.5167039884678175,
+      "learning_rate": 4.77844000037707e-06,
+      "loss": 0.7401,
+      "step": 59
+    },
+    {
+      "epoch": 0.6798866855524079,
+      "grad_norm": 1.427117682796941,
+      "learning_rate": 4.764600984163809e-06,
+      "loss": 0.7299,
+      "step": 60
+    },
+    {
+      "epoch": 0.6912181303116147,
+      "grad_norm": 1.4111273048659723,
+      "learning_rate": 4.750364054714302e-06,
+      "loss": 0.6947,
+      "step": 61
+    },
+    {
+      "epoch": 0.7025495750708215,
+      "grad_norm": 1.4031005513050043,
+      "learning_rate": 4.735731713600665e-06,
+      "loss": 0.7104,
+      "step": 62
+    },
+    {
+      "epoch": 0.7138810198300283,
+      "grad_norm": 1.3908217678623624,
+      "learning_rate": 4.72070653187283e-06,
+      "loss": 0.7215,
+      "step": 63
+    },
+    {
+      "epoch": 0.7252124645892352,
+      "grad_norm": 1.4016377075250317,
+      "learning_rate": 4.705291149606787e-06,
+      "loss": 0.6801,
+      "step": 64
+    },
+    {
+      "epoch": 0.7365439093484419,
+      "grad_norm": 1.373368498937934,
+      "learning_rate": 4.6894882754406965e-06,
+      "loss": 0.7115,
+      "step": 65
+    },
+    {
+      "epoch": 0.7478753541076487,
+      "grad_norm": 1.3083514867883594,
+      "learning_rate": 4.673300686098957e-06,
+      "loss": 0.6944,
+      "step": 66
+    },
+    {
+      "epoch": 0.7592067988668555,
+      "grad_norm": 1.408923716819617,
+      "learning_rate": 4.6567312259043e-06,
+      "loss": 0.7166,
+      "step": 67
+    },
+    {
+      "epoch": 0.7705382436260623,
+      "grad_norm": 1.4446149604718292,
+      "learning_rate": 4.639782806278021e-06,
+      "loss": 0.7643,
+      "step": 68
+    },
+    {
+      "epoch": 0.7818696883852692,
+      "grad_norm": 1.472987719405972,
+      "learning_rate": 4.622458405228411e-06,
+      "loss": 0.6748,
+      "step": 69
+    },
+    {
+      "epoch": 0.7932011331444759,
+      "grad_norm": 1.3910737638781718,
+      "learning_rate": 4.604761066827485e-06,
+      "loss": 0.6599,
+      "step": 70
+    },
+    {
+      "epoch": 0.8045325779036827,
+      "grad_norm": 1.4486804488805007,
+      "learning_rate": 4.586693900676116e-06,
+      "loss": 0.6844,
+      "step": 71
+    },
+    {
+      "epoch": 0.8158640226628895,
+      "grad_norm": 1.4339732853429255,
+      "learning_rate": 4.568260081357644e-06,
+      "loss": 0.6934,
+      "step": 72
+    },
+    {
+      "epoch": 0.8271954674220963,
+      "grad_norm": 1.4071241403434436,
+      "learning_rate": 4.549462847880066e-06,
+      "loss": 0.7042,
+      "step": 73
+    },
+    {
+      "epoch": 0.8385269121813032,
+      "grad_norm": 1.381067168557849,
+      "learning_rate": 4.5303055031069165e-06,
+      "loss": 0.6594,
+      "step": 74
+    },
+    {
+      "epoch": 0.8498583569405099,
+      "grad_norm": 1.370636257051823,
+      "learning_rate": 4.510791413176912e-06,
+      "loss": 0.7339,
+      "step": 75
+    },
+    {
+      "epoch": 0.8611898016997167,
+      "grad_norm": 1.3933507828709049,
+      "learning_rate": 4.490924006912497e-06,
+      "loss": 0.7319,
+      "step": 76
+    },
+    {
+      "epoch": 0.8725212464589235,
+      "grad_norm": 1.4434701376432475,
+      "learning_rate": 4.470706775217355e-06,
+      "loss": 0.7235,
+      "step": 77
+    },
+    {
+      "epoch": 0.8838526912181303,
+      "grad_norm": 1.3230684123602419,
+      "learning_rate": 4.450143270463031e-06,
+      "loss": 0.6653,
+      "step": 78
+    },
+    {
+      "epoch": 0.8951841359773371,
+      "grad_norm": 1.377425868827391,
+      "learning_rate": 4.429237105864735e-06,
+      "loss": 0.6929,
+      "step": 79
+    },
+    {
+      "epoch": 0.9065155807365439,
+      "grad_norm": 1.4118910710643473,
+      "learning_rate": 4.407991954846471e-06,
+      "loss": 0.6713,
+      "step": 80
+    },
+    {
+      "epoch": 0.9178470254957507,
+      "grad_norm": 1.2911698771129907,
+      "learning_rate": 4.386411550395576e-06,
+      "loss": 0.6828,
+      "step": 81
+    },
+    {
+      "epoch": 0.9291784702549575,
+      "grad_norm": 1.3062416329678588,
+      "learning_rate": 4.364499684406796e-06,
+      "loss": 0.6902,
+      "step": 82
+    },
+    {
+      "epoch": 0.9405099150141643,
+      "grad_norm": 1.4212108714610014,
+      "learning_rate": 4.3422602070160116e-06,
+      "loss": 0.7139,
+      "step": 83
+    },
+    {
+      "epoch": 0.9518413597733711,
+      "grad_norm": 1.4022201237779546,
+      "learning_rate": 4.319697025923736e-06,
+      "loss": 0.696,
+      "step": 84
+    },
+    {
+      "epoch": 0.9631728045325779,
+      "grad_norm": 1.4000079484179047,
+      "learning_rate": 4.296814105708482e-06,
+      "loss": 0.6978,
+      "step": 85
+    },
+    {
+      "epoch": 0.9745042492917847,
+      "grad_norm": 1.3135869027950182,
+      "learning_rate": 4.273615467130156e-06,
+      "loss": 0.7094,
+      "step": 86
+    },
+    {
+      "epoch": 0.9858356940509915,
+      "grad_norm": 1.5103342340296206,
+      "learning_rate": 4.250105186423564e-06,
+      "loss": 0.6864,
+      "step": 87
+    },
+    {
+      "epoch": 0.9971671388101983,
+      "grad_norm": 1.5395763391294515,
+      "learning_rate": 4.226287394582176e-06,
+      "loss": 0.6997,
+      "step": 88
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.5395763391294515,
+      "learning_rate": 4.202166276632274e-06,
+      "loss": 0.7015,
+      "step": 89
+    },
+    {
+      "epoch": 1.0113314447592068,
+      "grad_norm": 2.9632436977275973,
+      "learning_rate": 4.177746070897593e-06,
+      "loss": 0.6146,
+      "step": 90
+    },
+    {
+      "epoch": 1.0226628895184136,
+      "grad_norm": 1.3701820521458077,
+      "learning_rate": 4.15303106825461e-06,
+      "loss": 0.5952,
+      "step": 91
+    },
+    {
+      "epoch": 1.0339943342776203,
+      "grad_norm": 1.4232251740156472,
+      "learning_rate": 4.128025611378594e-06,
+      "loss": 0.6013,
+      "step": 92
+    },
+    {
+      "epoch": 1.045325779036827,
+      "grad_norm": 1.4243450179098962,
+      "learning_rate": 4.10273409398055e-06,
+      "loss": 0.5838,
+      "step": 93
+    },
+    {
+      "epoch": 1.056657223796034,
+      "grad_norm": 1.3024426134525557,
+      "learning_rate": 4.077160960035207e-06,
+      "loss": 0.5719,
+      "step": 94
+    },
+    {
+      "epoch": 1.0679886685552409,
+      "grad_norm": 1.346350514168427,
+      "learning_rate": 4.051310703000155e-06,
+      "loss": 0.5969,
+      "step": 95
+    },
+    {
+      "epoch": 1.0793201133144477,
+      "grad_norm": 1.370884384362504,
+      "learning_rate": 4.025187865026311e-06,
+      "loss": 0.6079,
+      "step": 96
+    },
+    {
+      "epoch": 1.0906515580736544,
+      "grad_norm": 1.462001933003737,
+      "learning_rate": 3.998797036159813e-06,
+      "loss": 0.6286,
+      "step": 97
+    },
+    {
+      "epoch": 1.1019830028328612,
+      "grad_norm": 1.332600598608553,
+      "learning_rate": 3.972142853535499e-06,
+      "loss": 0.606,
+      "step": 98
+    },
+    {
+      "epoch": 1.113314447592068,
+      "grad_norm": 1.426061501851815,
+      "learning_rate": 3.945230000562121e-06,
+      "loss": 0.6109,
+      "step": 99
+    },
+    {
+      "epoch": 1.1246458923512748,
+      "grad_norm": 1.4004325571146066,
+      "learning_rate": 3.918063206099421e-06,
+      "loss": 0.62,
+      "step": 100
+    },
+    {
+      "epoch": 1.1359773371104815,
+      "grad_norm": 1.3396518626669338,
+      "learning_rate": 3.890647243627218e-06,
+      "loss": 0.5934,
+      "step": 101
+    },
+    {
+      "epoch": 1.1473087818696883,
+      "grad_norm": 1.380208956021839,
+      "learning_rate": 3.862986930406669e-06,
+      "loss": 0.5968,
+      "step": 102
+    },
+    {
+      "epoch": 1.158640226628895,
+      "grad_norm": 1.3961154205163853,
+      "learning_rate": 3.83508712663382e-06,
+      "loss": 0.6032,
+      "step": 103
+    },
+    {
+      "epoch": 1.1699716713881019,
+      "grad_norm": 1.3448453940648393,
+      "learning_rate": 3.8069527345856233e-06,
+      "loss": 0.5915,
+      "step": 104
+    },
+    {
+      "epoch": 1.1813031161473089,
+      "grad_norm": 1.3902990971135147,
+      "learning_rate": 3.7785886977585562e-06,
+      "loss": 0.5918,
+      "step": 105
+    },
+    {
+      "epoch": 1.1926345609065157,
+      "grad_norm": 1.3820749771088052,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.5969,
+      "step": 106
+    },
+    {
+      "epoch": 1.2039660056657224,
+      "grad_norm": 1.4716970228552981,
+      "learning_rate": 3.7211916646325315e-06,
+      "loss": 0.5941,
+      "step": 107
+    },
+    {
+      "epoch": 1.2152974504249292,
+      "grad_norm": 1.34235642577707,
+      "learning_rate": 3.6921687535712657e-06,
+      "loss": 0.5803,
+      "step": 108
+    },
+    {
+      "epoch": 1.226628895184136,
+      "grad_norm": 1.360958822094796,
+      "learning_rate": 3.662936366434435e-06,
+      "loss": 0.5882,
+      "step": 109
+    },
+    {
+      "epoch": 1.2379603399433428,
+      "grad_norm": 1.3865643140417971,
+      "learning_rate": 3.6334996396473298e-06,
+      "loss": 0.6127,
+      "step": 110
+    },
+    {
+      "epoch": 1.2492917847025495,
+      "grad_norm": 1.3096840589094985,
+      "learning_rate": 3.6038637455397802e-06,
+      "loss": 0.5703,
+      "step": 111
+    },
+    {
+      "epoch": 1.2606232294617563,
+      "grad_norm": 1.4346753864435622,
+      "learning_rate": 3.57403389143732e-06,
+      "loss": 0.5997,
+      "step": 112
+    },
+    {
+      "epoch": 1.271954674220963,
+      "grad_norm": 1.4377459031956494,
+      "learning_rate": 3.5440153187462146e-06,
+      "loss": 0.6251,
+      "step": 113
+    },
+    {
+      "epoch": 1.28328611898017,
+      "grad_norm": 1.4225200803648703,
+      "learning_rate": 3.513813302032485e-06,
+      "loss": 0.6202,
+      "step": 114
+    },
+    {
+      "epoch": 1.2946175637393766,
+      "grad_norm": 1.3836498692303638,
+      "learning_rate": 3.4834331480951213e-06,
+      "loss": 0.5944,
+      "step": 115
+    },
+    {
+      "epoch": 1.3059490084985836,
+      "grad_norm": 1.281401506633823,
+      "learning_rate": 3.4528801950336177e-06,
+      "loss": 0.551,
+      "step": 116
+    },
+    {
+      "epoch": 1.3172804532577904,
+      "grad_norm": 1.4771037032630314,
+      "learning_rate": 3.4221598113100196e-06,
+      "loss": 0.6072,
+      "step": 117
+    },
+    {
+      "epoch": 1.3286118980169972,
+      "grad_norm": 1.4652916781647747,
+      "learning_rate": 3.391277394805628e-06,
+      "loss": 0.6166,
+      "step": 118
+    },
+    {
+      "epoch": 1.339943342776204,
+      "grad_norm": 1.3590014582336747,
+      "learning_rate": 3.3602383718725363e-06,
+      "loss": 0.5753,
+      "step": 119
+    },
+    {
+      "epoch": 1.3512747875354107,
+      "grad_norm": 1.3644484003880029,
+      "learning_rate": 3.32904819638017e-06,
+      "loss": 0.5892,
+      "step": 120
+    },
+    {
+      "epoch": 1.3626062322946175,
+      "grad_norm": 1.3191831153419338,
+      "learning_rate": 3.2977123487569816e-06,
+      "loss": 0.5624,
+      "step": 121
+    },
+    {
+      "epoch": 1.3739376770538243,
+      "grad_norm": 1.3319312452343077,
+      "learning_rate": 3.2662363350274874e-06,
+      "loss": 0.5851,
+      "step": 122
+    },
+    {
+      "epoch": 1.385269121813031,
+      "grad_norm": 1.4257384239422966,
+      "learning_rate": 3.234625685844803e-06,
+      "loss": 0.5893,
+      "step": 123
+    },
+    {
+      "epoch": 1.3966005665722379,
+      "grad_norm": 1.3953828272396132,
+      "learning_rate": 3.202885955518849e-06,
+      "loss": 0.5973,
+      "step": 124
+    },
+    {
+      "epoch": 1.4079320113314449,
+      "grad_norm": 1.395900408790709,
+      "learning_rate": 3.171022721040409e-06,
+      "loss": 0.588,
+      "step": 125
+    },
+    {
+      "epoch": 1.4192634560906516,
+      "grad_norm": 1.4082770595189713,
+      "learning_rate": 3.139041581101187e-06,
+      "loss": 0.5955,
+      "step": 126
+    },
+    {
+      "epoch": 1.4305949008498584,
+      "grad_norm": 1.4111017631505742,
+      "learning_rate": 3.10694815511007e-06,
+      "loss": 0.6304,
+      "step": 127
+    },
+    {
+      "epoch": 1.4419263456090652,
+      "grad_norm": 1.3684496285444403,
+      "learning_rate": 3.0747480822057342e-06,
+      "loss": 0.5895,
+      "step": 128
+    },
+    {
+      "epoch": 1.453257790368272,
+      "grad_norm": 1.3150808865823653,
+      "learning_rate": 3.0424470202657953e-06,
+      "loss": 0.577,
+      "step": 129
+    },
+    {
+      "epoch": 1.4645892351274787,
+      "grad_norm": 1.4075517143230738,
+      "learning_rate": 3.0100506449126622e-06,
+      "loss": 0.5939,
+      "step": 130
+    },
+    {
+      "epoch": 1.4759206798866855,
+      "grad_norm": 1.3153882543446243,
+      "learning_rate": 2.9775646485162697e-06,
+      "loss": 0.5735,
+      "step": 131
+    },
+    {
+      "epoch": 1.4872521246458923,
+      "grad_norm": 1.3348680664842318,
+      "learning_rate": 2.9449947391938768e-06,
+      "loss": 0.625,
+      "step": 132
+    },
+    {
+      "epoch": 1.498583569405099,
+      "grad_norm": 1.3489224682673129,
+      "learning_rate": 2.9123466398070855e-06,
+      "loss": 0.5981,
+      "step": 133
+    },
+    {
+      "epoch": 1.509915014164306,
+      "grad_norm": 1.3429701772744527,
+      "learning_rate": 2.8796260869562865e-06,
+      "loss": 0.5887,
+      "step": 134
+    },
+    {
+      "epoch": 1.5212464589235126,
+      "grad_norm": 1.4722400862474931,
+      "learning_rate": 2.8468388299726714e-06,
+      "loss": 0.5831,
+      "step": 135
+    },
+    {
+      "epoch": 1.5325779036827196,
+      "grad_norm": 1.2672960818674879,
+      "learning_rate": 2.8139906299080205e-06,
+      "loss": 0.5825,
+      "step": 136
+    },
+    {
+      "epoch": 1.5439093484419264,
+      "grad_norm": 1.3627343997731545,
+      "learning_rate": 2.781087258522431e-06,
+      "loss": 0.5832,
+      "step": 137
+    },
+    {
+      "epoch": 1.5552407932011332,
+      "grad_norm": 1.2876772239163903,
+      "learning_rate": 2.7481344972701545e-06,
+      "loss": 0.5531,
+      "step": 138
+    },
+    {
+      "epoch": 1.56657223796034,
+      "grad_norm": 1.3472454325008387,
+      "learning_rate": 2.7151381362837424e-06,
+      "loss": 0.5842,
+      "step": 139
+    },
+    {
+      "epoch": 1.5779036827195467,
+      "grad_norm": 1.3762098724750873,
+      "learning_rate": 2.682103973356659e-06,
+      "loss": 0.5712,
+      "step": 140
+    },
+    {
+      "epoch": 1.5892351274787535,
+      "grad_norm": 1.3492795625450165,
+      "learning_rate": 2.64903781292455e-06,
+      "loss": 0.5782,
+      "step": 141
+    },
+    {
+      "epoch": 1.6005665722379603,
+      "grad_norm": 1.3499587695758297,
+      "learning_rate": 2.615945465045346e-06,
+      "loss": 0.5669,
+      "step": 142
+    },
+    {
+      "epoch": 1.6118980169971673,
+      "grad_norm": 1.3511311195079772,
+      "learning_rate": 2.5828327443783775e-06,
+      "loss": 0.551,
+      "step": 143
+    },
+    {
+      "epoch": 1.6232294617563738,
+      "grad_norm": 1.33090787217115,
+      "learning_rate": 2.5497054691626754e-06,
+      "loss": 0.579,
+      "step": 144
+    },
+    {
+      "epoch": 1.6345609065155808,
+      "grad_norm": 1.3670590438796546,
+      "learning_rate": 2.5165694601946566e-06,
+      "loss": 0.5959,
+      "step": 145
+    },
+    {
+      "epoch": 1.6458923512747874,
+      "grad_norm": 1.3299516191015563,
+      "learning_rate": 2.483430539805344e-06,
+      "loss": 0.5979,
+      "step": 146
+    },
+    {
+      "epoch": 1.6572237960339944,
+      "grad_norm": 1.4129085459444395,
+      "learning_rate": 2.4502945308373246e-06,
+      "loss": 0.585,
+      "step": 147
+    },
+    {
+      "epoch": 1.6685552407932012,
+      "grad_norm": 1.4275247309590513,
+      "learning_rate": 2.4171672556216237e-06,
+      "loss": 0.576,
+      "step": 148
+    },
+    {
+      "epoch": 1.679886685552408,
+      "grad_norm": 1.3619200458990444,
+      "learning_rate": 2.3840545349546538e-06,
+      "loss": 0.5841,
+      "step": 149
+    },
+    {
+      "epoch": 1.6912181303116147,
+      "grad_norm": 1.3819435365787816,
+      "learning_rate": 2.3509621870754505e-06,
+      "loss": 0.5685,
+      "step": 150
+    },
+    {
+      "epoch": 1.7025495750708215,
+      "grad_norm": 1.3294738919196907,
+      "learning_rate": 2.317896026643341e-06,
+      "loss": 0.5871,
+      "step": 151
+    },
+    {
+      "epoch": 1.7138810198300283,
+      "grad_norm": 1.2730007734790987,
+      "learning_rate": 2.2848618637162584e-06,
+      "loss": 0.5592,
+      "step": 152
+    },
+    {
+      "epoch": 1.725212464589235,
+      "grad_norm": 1.3785771168476042,
+      "learning_rate": 2.2518655027298468e-06,
+      "loss": 0.577,
+      "step": 153
+    },
+    {
+      "epoch": 1.736543909348442,
+      "grad_norm": 1.3530333929384266,
+      "learning_rate": 2.21891274147757e-06,
+      "loss": 0.5503,
+      "step": 154
+    },
+    {
+      "epoch": 1.7478753541076486,
+      "grad_norm": 1.4267187662110872,
+      "learning_rate": 2.1860093700919804e-06,
+      "loss": 0.6071,
+      "step": 155
+    },
+    {
+      "epoch": 1.7592067988668556,
+      "grad_norm": 1.3951110903420234,
+      "learning_rate": 2.15316117002733e-06,
+      "loss": 0.5629,
+      "step": 156
+    },
+    {
+      "epoch": 1.7705382436260622,
+      "grad_norm": 1.3033237896515593,
+      "learning_rate": 2.1203739130437147e-06,
+      "loss": 0.5452,
+      "step": 157
+    },
+    {
+      "epoch": 1.7818696883852692,
+      "grad_norm": 1.380166287245991,
+      "learning_rate": 2.0876533601929153e-06,
+      "loss": 0.5811,
+      "step": 158
+    },
+    {
+      "epoch": 1.793201133144476,
+      "grad_norm": 1.2839541967552655,
+      "learning_rate": 2.055005260806125e-06,
+      "loss": 0.5672,
+      "step": 159
+    },
+    {
+      "epoch": 1.8045325779036827,
+      "grad_norm": 1.3067862009338267,
+      "learning_rate": 2.0224353514837307e-06,
+      "loss": 0.5683,
+      "step": 160
+    },
+    {
+      "epoch": 1.8158640226628895,
+      "grad_norm": 1.3243283509277737,
+      "learning_rate": 1.989949355087339e-06,
+      "loss": 0.5689,
+      "step": 161
+    },
+    {
+      "epoch": 1.8271954674220963,
+      "grad_norm": 1.3356790286830134,
+      "learning_rate": 1.957552979734205e-06,
+      "loss": 0.5802,
+      "step": 162
+    },
+    {
+      "epoch": 1.8385269121813033,
+      "grad_norm": 1.2892603884545701,
+      "learning_rate": 1.9252519177942666e-06,
+      "loss": 0.5692,
+      "step": 163
+    },
+    {
+      "epoch": 1.8498583569405098,
+      "grad_norm": 1.4440754700865919,
+      "learning_rate": 1.8930518448899304e-06,
+      "loss": 0.5965,
+      "step": 164
+    },
+    {
+      "epoch": 1.8611898016997168,
+      "grad_norm": 1.387136746836695,
+      "learning_rate": 1.8609584188988135e-06,
+      "loss": 0.5736,
+      "step": 165
+    },
+    {
+      "epoch": 1.8725212464589234,
+      "grad_norm": 1.1917095159893407,
+      "learning_rate": 1.8289772789595917e-06,
+      "loss": 0.6144,
+      "step": 166
+    },
+    {
+      "epoch": 1.8838526912181304,
+      "grad_norm": 1.375742481693197,
+      "learning_rate": 1.7971140444811514e-06,
+      "loss": 0.5763,
+      "step": 167
+    },
+    {
+      "epoch": 1.8951841359773371,
+      "grad_norm": 1.2404940123916632,
+      "learning_rate": 1.7653743141551983e-06,
+      "loss": 0.6063,
+      "step": 168
+    },
+    {
+      "epoch": 1.906515580736544,
+      "grad_norm": 1.3989557605487426,
+      "learning_rate": 1.7337636649725132e-06,
+      "loss": 0.5892,
+      "step": 169
+    },
+    {
+      "epoch": 1.9178470254957507,
+      "grad_norm": 1.2710248336513368,
+      "learning_rate": 1.7022876512430197e-06,
+      "loss": 0.5813,
+      "step": 170
+    },
+    {
+      "epoch": 1.9291784702549575,
+      "grad_norm": 1.2716638071587159,
+      "learning_rate": 1.6709518036198307e-06,
+      "loss": 0.5565,
+      "step": 171
+    },
+    {
+      "epoch": 1.9405099150141643,
+      "grad_norm": 1.277667152903096,
+      "learning_rate": 1.6397616281274648e-06,
+      "loss": 0.5727,
+      "step": 172
+    },
+    {
+      "epoch": 1.951841359773371,
+      "grad_norm": 1.296382463166991,
+      "learning_rate": 1.6087226051943728e-06,
+      "loss": 0.593,
+      "step": 173
+    },
+    {
+      "epoch": 1.963172804532578,
+      "grad_norm": 1.2844540181786357,
+      "learning_rate": 1.5778401886899808e-06,
+      "loss": 0.5841,
+      "step": 174
+    },
+    {
+      "epoch": 1.9745042492917846,
+      "grad_norm": 1.3053433701687789,
+      "learning_rate": 1.5471198049663822e-06,
+      "loss": 0.575,
+      "step": 175
+    },
+    {
+      "epoch": 1.9858356940509916,
+      "grad_norm": 1.268811845033466,
+      "learning_rate": 1.51656685190488e-06,
+      "loss": 0.588,
+      "step": 176
+    },
+    {
+      "epoch": 1.9971671388101981,
+      "grad_norm": 1.247792131322831,
+      "learning_rate": 1.4861866979675155e-06,
+      "loss": 0.5534,
+      "step": 177
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.247792131322831,
+      "learning_rate": 1.455984681253787e-06,
+      "loss": 0.5438,
+      "step": 178
+    },
+    {
+      "epoch": 2.011331444759207,
+      "grad_norm": 2.7694057916801307,
+      "learning_rate": 1.4259661085626802e-06,
+      "loss": 0.5062,
+      "step": 179
+    },
+    {
+      "epoch": 2.0226628895184136,
+      "grad_norm": 1.2786953899807016,
+      "learning_rate": 1.3961362544602215e-06,
+      "loss": 0.4878,
+      "step": 180
+    },
+    {
+      "epoch": 2.0339943342776206,
+      "grad_norm": 1.3338942724237564,
+      "learning_rate": 1.3665003603526706e-06,
+      "loss": 0.5131,
+      "step": 181
+    },
+    {
+      "epoch": 2.045325779036827,
+      "grad_norm": 1.3381680372557467,
+      "learning_rate": 1.3370636335655656e-06,
+      "loss": 0.4976,
+      "step": 182
+    },
+    {
+      "epoch": 2.056657223796034,
+      "grad_norm": 1.2513390840039769,
+      "learning_rate": 1.3078312464287355e-06,
+      "loss": 0.5211,
+      "step": 183
+    },
+    {
+      "epoch": 2.0679886685552407,
+      "grad_norm": 1.2770532289534442,
+      "learning_rate": 1.2788083353674694e-06,
+      "loss": 0.5007,
+      "step": 184
+    },
+    {
+      "epoch": 2.0793201133144477,
+      "grad_norm": 1.2927230496024624,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.4622,
+      "step": 185
+    },
+    {
+      "epoch": 2.090651558073654,
+      "grad_norm": 1.2508343832786988,
+      "learning_rate": 1.2214113022414448e-06,
+      "loss": 0.4844,
+      "step": 186
+    },
+    {
+      "epoch": 2.101983002832861,
+      "grad_norm": 1.207057675657945,
+      "learning_rate": 1.1930472654143777e-06,
+      "loss": 0.4948,
+      "step": 187
+    },
+    {
+      "epoch": 2.113314447592068,
+      "grad_norm": 1.2515484350526327,
+      "learning_rate": 1.1649128733661802e-06,
+      "loss": 0.4975,
+      "step": 188
+    },
+    {
+      "epoch": 2.1246458923512748,
+      "grad_norm": 1.2820103087615313,
+      "learning_rate": 1.1370130695933317e-06,
+      "loss": 0.5033,
+      "step": 189
+    },
+    {
+      "epoch": 2.1359773371104818,
+      "grad_norm": 1.3883649461446737,
+      "learning_rate": 1.1093527563727827e-06,
+      "loss": 0.4959,
+      "step": 190
+    },
+    {
+      "epoch": 2.1473087818696883,
+      "grad_norm": 1.2985788114536188,
+      "learning_rate": 1.0819367939005802e-06,
+      "loss": 0.5109,
+      "step": 191
+    },
+    {
+      "epoch": 2.1586402266288953,
+      "grad_norm": 1.3965326476598117,
+      "learning_rate": 1.0547699994378787e-06,
+      "loss": 0.4812,
+      "step": 192
+    },
+    {
+      "epoch": 2.169971671388102,
+      "grad_norm": 1.3349013266585352,
+      "learning_rate": 1.0278571464645013e-06,
+      "loss": 0.4926,
+      "step": 193
+    },
+    {
+      "epoch": 2.181303116147309,
+      "grad_norm": 1.3212505511291743,
+      "learning_rate": 1.0012029638401871e-06,
+      "loss": 0.4882,
+      "step": 194
+    },
+    {
+      "epoch": 2.1926345609065154,
+      "grad_norm": 1.30500171720855,
+      "learning_rate": 9.74812134973689e-07,
+      "loss": 0.5173,
+      "step": 195
+    },
+    {
+      "epoch": 2.2039660056657224,
+      "grad_norm": 1.2488171277934157,
+      "learning_rate": 9.486892969998465e-07,
+      "loss": 0.482,
+      "step": 196
+    },
+    {
+      "epoch": 2.215297450424929,
+      "grad_norm": 1.2854653346406788,
+      "learning_rate": 9.228390399647944e-07,
+      "loss": 0.5015,
+      "step": 197
+    },
+    {
+      "epoch": 2.226628895184136,
+      "grad_norm": 1.323794953427552,
+      "learning_rate": 8.972659060194505e-07,
+      "loss": 0.4735,
+      "step": 198
+    },
+    {
+      "epoch": 2.237960339943343,
+      "grad_norm": 1.3376265040553337,
+      "learning_rate": 8.719743886214071e-07,
+      "loss": 0.4875,
+      "step": 199
+    },
+    {
+      "epoch": 2.2492917847025495,
+      "grad_norm": 1.3285002033736215,
+      "learning_rate": 8.469689317453907e-07,
+      "loss": 0.4962,
+      "step": 200
+    },
+    {
+      "epoch": 2.2606232294617565,
+      "grad_norm": 1.2555976735704084,
+      "learning_rate": 8.222539291024079e-07,
+      "loss": 0.5005,
+      "step": 201
+    },
+    {
+      "epoch": 2.271954674220963,
+      "grad_norm": 1.2410255920694668,
+      "learning_rate": 7.978337233677269e-07,
+      "loss": 0.4882,
+      "step": 202
+    },
+    {
+      "epoch": 2.28328611898017,
+      "grad_norm": 1.2713376284380098,
+      "learning_rate": 7.737126054178238e-07,
+      "loss": 0.4739,
+      "step": 203
+    },
+    {
+      "epoch": 2.2946175637393766,
+      "grad_norm": 1.2772097228177208,
+      "learning_rate": 7.49894813576437e-07,
+      "loss": 0.4652,
+      "step": 204
+    },
+    {
+      "epoch": 2.3059490084985836,
+      "grad_norm": 1.3985331094997697,
+      "learning_rate": 7.26384532869844e-07,
+      "loss": 0.4983,
+      "step": 205
+    },
+    {
+      "epoch": 2.31728045325779,
+      "grad_norm": 1.2385757104958386,
+      "learning_rate": 7.031858942915187e-07,
+      "loss": 0.4848,
+      "step": 206
+    },
+    {
+      "epoch": 2.328611898016997,
+      "grad_norm": 1.298621814561205,
+      "learning_rate": 6.803029740762648e-07,
+      "loss": 0.499,
+      "step": 207
+    },
+    {
+      "epoch": 2.3399433427762037,
+      "grad_norm": 1.1982592548193622,
+      "learning_rate": 6.577397929839891e-07,
+      "loss": 0.5074,
+      "step": 208
+    },
+    {
+      "epoch": 2.3512747875354107,
+      "grad_norm": 1.3230369234558008,
+      "learning_rate": 6.355003155932052e-07,
+      "loss": 0.5082,
+      "step": 209
+    },
+    {
+      "epoch": 2.3626062322946177,
+      "grad_norm": 1.2353352817463088,
+      "learning_rate": 6.135884496044245e-07,
+      "loss": 0.5024,
+      "step": 210
+    },
+    {
+      "epoch": 2.3739376770538243,
+      "grad_norm": 1.2866413763490911,
+      "learning_rate": 5.920080451535296e-07,
+      "loss": 0.5158,
+      "step": 211
+    },
+    {
+      "epoch": 2.3852691218130313,
+      "grad_norm": 1.366484849292798,
+      "learning_rate": 5.707628941352655e-07,
+      "loss": 0.5068,
+      "step": 212
+    },
+    {
+      "epoch": 2.396600566572238,
+      "grad_norm": 1.287762702589202,
+      "learning_rate": 5.4985672953697e-07,
+      "loss": 0.4563,
+      "step": 213
+    },
+    {
+      "epoch": 2.407932011331445,
+      "grad_norm": 1.2310856033033788,
+      "learning_rate": 5.292932247826449e-07,
+      "loss": 0.5104,
+      "step": 214
+    },
+    {
+      "epoch": 2.4192634560906514,
+      "grad_norm": 1.2722457695575675,
+      "learning_rate": 5.090759930875039e-07,
+      "loss": 0.4745,
+      "step": 215
+    },
+    {
+      "epoch": 2.4305949008498584,
+      "grad_norm": 1.1881380406354796,
+      "learning_rate": 4.892085868230881e-07,
+      "loss": 0.4684,
+      "step": 216
+    },
+    {
+      "epoch": 2.441926345609065,
+      "grad_norm": 1.2279337924506066,
+      "learning_rate": 4.696944968930847e-07,
+      "loss": 0.4766,
+      "step": 217
+    },
+    {
+      "epoch": 2.453257790368272,
+      "grad_norm": 1.2965879507443776,
+      "learning_rate": 4.505371521199342e-07,
+      "loss": 0.4887,
+      "step": 218
+    },
+    {
+      "epoch": 2.4645892351274785,
+      "grad_norm": 1.2726278849407309,
+      "learning_rate": 4.317399186423574e-07,
+      "loss": 0.49,
+      "step": 219
+    },
+    {
+      "epoch": 2.4759206798866855,
+      "grad_norm": 1.2083763664947262,
+      "learning_rate": 4.1330609932388493e-07,
+      "loss": 0.4714,
+      "step": 220
+    },
+    {
+      "epoch": 2.4872521246458925,
+      "grad_norm": 1.2790819302434515,
+      "learning_rate": 3.9523893317251624e-07,
+      "loss": 0.4924,
+      "step": 221
+    },
+    {
+      "epoch": 2.498583569405099,
+      "grad_norm": 1.2824144839819291,
+      "learning_rate": 3.7754159477158994e-07,
+      "loss": 0.4969,
+      "step": 222
+    },
+    {
+      "epoch": 2.509915014164306,
+      "grad_norm": 1.2322829650550764,
+      "learning_rate": 3.602171937219789e-07,
+      "loss": 0.4922,
+      "step": 223
+    },
+    {
+      "epoch": 2.5212464589235126,
+      "grad_norm": 1.2932932363502108,
+      "learning_rate": 3.4326877409570083e-07,
+      "loss": 0.5135,
+      "step": 224
+    },
+    {
+      "epoch": 2.5325779036827196,
+      "grad_norm": 1.3265821035298209,
+      "learning_rate": 3.266993139010438e-07,
+      "loss": 0.4824,
+      "step": 225
+    },
+    {
+      "epoch": 2.543909348441926,
+      "grad_norm": 1.2634627344428153,
+      "learning_rate": 3.1051172455930395e-07,
+      "loss": 0.4756,
+      "step": 226
+    },
+    {
+      "epoch": 2.555240793201133,
+      "grad_norm": 1.2955666908690064,
+      "learning_rate": 2.947088503932136e-07,
+      "loss": 0.49,
+      "step": 227
+    },
+    {
+      "epoch": 2.56657223796034,
+      "grad_norm": 1.2966827797243252,
+      "learning_rate": 2.792934681271708e-07,
+      "loss": 0.5022,
+      "step": 228
+    },
+    {
+      "epoch": 2.5779036827195467,
+      "grad_norm": 1.294488037545825,
+      "learning_rate": 2.642682863993354e-07,
+      "loss": 0.4995,
+      "step": 229
+    },
+    {
+      "epoch": 2.5892351274787533,
+      "grad_norm": 1.2899319442218364,
+      "learning_rate": 2.4963594528569835e-07,
+      "loss": 0.5022,
+      "step": 230
+    },
+    {
+      "epoch": 2.6005665722379603,
+      "grad_norm": 1.2411992299049828,
+      "learning_rate": 2.3539901583619186e-07,
+      "loss": 0.4815,
+      "step": 231
+    },
+    {
+      "epoch": 2.6118980169971673,
+      "grad_norm": 1.290057331367847,
+      "learning_rate": 2.2155999962293035e-07,
+      "loss": 0.4777,
+      "step": 232
+    },
+    {
+      "epoch": 2.623229461756374,
+      "grad_norm": 1.336160271366626,
+      "learning_rate": 2.081213283006575e-07,
+      "loss": 0.4814,
+      "step": 233
+    },
+    {
+      "epoch": 2.634560906515581,
+      "grad_norm": 1.2513839029803793,
+      "learning_rate": 1.9508536317948358e-07,
+      "loss": 0.4871,
+      "step": 234
+    },
+    {
+      "epoch": 2.6458923512747874,
+      "grad_norm": 1.212015408532025,
+      "learning_rate": 1.824543948099744e-07,
+      "loss": 0.4726,
+      "step": 235
+    },
+    {
+      "epoch": 2.6572237960339944,
+      "grad_norm": 1.2427046825799253,
+      "learning_rate": 1.702306425806838e-07,
+      "loss": 0.4807,
+      "step": 236
+    },
+    {
+      "epoch": 2.668555240793201,
+      "grad_norm": 1.2778407829783978,
+      "learning_rate": 1.584162543281806e-07,
+      "loss": 0.4957,
+      "step": 237
+    },
+    {
+      "epoch": 2.679886685552408,
+      "grad_norm": 1.226886722658913,
+      "learning_rate": 1.4701330595965401e-07,
+      "loss": 0.4898,
+      "step": 238
+    },
+    {
+      "epoch": 2.691218130311615,
+      "grad_norm": 1.300360670595622,
+      "learning_rate": 1.3602380108815537e-07,
+      "loss": 0.4841,
+      "step": 239
+    },
+    {
+      "epoch": 2.7025495750708215,
+      "grad_norm": 1.313490684903286,
+      "learning_rate": 1.2544967068054332e-07,
+      "loss": 0.4954,
+      "step": 240
+    },
+    {
+      "epoch": 2.713881019830028,
+      "grad_norm": 1.2920263932419636,
+      "learning_rate": 1.152927727181935e-07,
+      "loss": 0.5249,
+      "step": 241
+    },
+    {
+      "epoch": 2.725212464589235,
+      "grad_norm": 1.3447396451038305,
+      "learning_rate": 1.0555489187053097e-07,
+      "loss": 0.5207,
+      "step": 242
+    },
+    {
+      "epoch": 2.736543909348442,
+      "grad_norm": 1.3527682966828949,
+      "learning_rate": 9.623773918144896e-08,
+      "loss": 0.5077,
+      "step": 243
+    },
+    {
+      "epoch": 2.7478753541076486,
+      "grad_norm": 1.368471140884032,
+      "learning_rate": 8.734295176865748e-08,
+      "loss": 0.5081,
+      "step": 244
+    },
+    {
+      "epoch": 2.7592067988668556,
+      "grad_norm": 1.278186747537926,
+      "learning_rate": 7.88720925360284e-08,
+      "loss": 0.4944,
+      "step": 245
+    },
+    {
+      "epoch": 2.770538243626062,
+      "grad_norm": 1.337416906476136,
+      "learning_rate": 7.082664989897486e-08,
+      "loss": 0.4764,
+      "step": 246
+    },
+    {
+      "epoch": 2.781869688385269,
+      "grad_norm": 1.280766158552745,
+      "learning_rate": 6.320803752292465e-08,
+      "loss": 0.4567,
+      "step": 247
+    },
+    {
+      "epoch": 2.7932011331444757,
+      "grad_norm": 1.1973951885363563,
+      "learning_rate": 5.601759407492108e-08,
+      "loss": 0.4896,
+      "step": 248
+    },
+    {
+      "epoch": 2.8045325779036827,
+      "grad_norm": 1.3298617699728477,
+      "learning_rate": 4.9256582988409795e-08,
+      "loss": 0.5015,
+      "step": 249
+    },
+    {
+      "epoch": 2.8158640226628897,
+      "grad_norm": 1.2840493283766243,
+      "learning_rate": 4.292619224123717e-08,
+      "loss": 0.4702,
+      "step": 250
+    },
+    {
+      "epoch": 2.8271954674220963,
+      "grad_norm": 1.2753413052551887,
+      "learning_rate": 3.702753414691368e-08,
+      "loss": 0.4677,
+      "step": 251
+    },
+    {
+      "epoch": 2.8385269121813033,
+      "grad_norm": 1.2669874412423119,
+      "learning_rate": 3.15616451591666e-08,
+      "loss": 0.485,
+      "step": 252
+    },
+    {
+      "epoch": 2.84985835694051,
+      "grad_norm": 1.2670916015981173,
+      "learning_rate": 2.6529485689825996e-08,
+      "loss": 0.4979,
+      "step": 253
+    },
+    {
+      "epoch": 2.861189801699717,
+      "grad_norm": 1.3102429493654797,
+      "learning_rate": 2.1931939940071368e-08,
+      "loss": 0.4719,
+      "step": 254
+    },
+    {
+      "epoch": 2.8725212464589234,
+      "grad_norm": 1.2716849784011235,
+      "learning_rate": 1.7769815745066476e-08,
+      "loss": 0.5018,
+      "step": 255
+    },
+    {
+      "epoch": 2.8838526912181304,
+      "grad_norm": 1.2711203429937163,
+      "learning_rate": 1.4043844432016507e-08,
+      "loss": 0.5098,
+      "step": 256
+    },
+    {
+      "epoch": 2.8951841359773374,
+      "grad_norm": 1.3331489651068749,
+      "learning_rate": 1.0754680691665299e-08,
+      "loss": 0.4731,
+      "step": 257
+    },
+    {
+      "epoch": 2.906515580736544,
+      "grad_norm": 1.3288134823029176,
+      "learning_rate": 7.90290246326042e-09,
+      "loss": 0.5416,
+      "step": 258
+    },
+    {
+      "epoch": 2.9178470254957505,
+      "grad_norm": 1.2953779393999099,
+      "learning_rate": 5.489010833002739e-09,
+      "loss": 0.4851,
+      "step": 259
+    },
+    {
+      "epoch": 2.9291784702549575,
+      "grad_norm": 1.3104504966732855,
+      "learning_rate": 3.51342994600129e-09,
+      "loss": 0.5082,
+      "step": 260
+    },
+    {
+      "epoch": 2.9405099150141645,
+      "grad_norm": 1.2404192298354901,
+      "learning_rate": 1.976506931745392e-09,
+      "loss": 0.4797,
+      "step": 261
+    },
+    {
+      "epoch": 2.951841359773371,
+      "grad_norm": 1.25894417590066,
+      "learning_rate": 8.78511843112051e-10,
+      "loss": 0.5091,
+      "step": 262
+    },
+    {
+      "epoch": 2.963172804532578,
+      "grad_norm": 1.3062783600910168,
+      "learning_rate": 2.1963760891391406e-10,
+      "loss": 0.495,
+      "step": 263
+    },
+    {
+      "epoch": 2.9745042492917846,
+      "grad_norm": 1.2953858272939929,
+      "learning_rate": 0.0,
+      "loss": 0.4696,
+      "step": 264
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 264,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 28634663264256.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68245ae1dac9231dafee8a98989a5114b045c7c1ab0ee9f3bfd8bd5508a3914a
+size 7608

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)