add: add model weight files

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/apdcephfs_qy3/share_1443437/nlp_common/LLM_Models/qwen/Qwen2-7B-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_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "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": "4.41.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217cc2741ab7512c77f858975269c2761ae05971e8586020e6749e4ba5dcb381
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f635bc78a7a9099fa911f9969a6a1be04ecfaf4188cc00c90164da4c8bf0185d
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef4937476e8eb86229893b72268c26e28b676e179e8f07b63431447967c2bba
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5889769a9feeda1af7f8dac4cdf3e1af2d48e9d21283433ce72828ed9b52969
+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 sha256:36d2a2034ebb05cb71c510897f2795b31164e50f17b270bc25d2be3ad9a17b22
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060dfdb1c49102cbdc8868a6031e68787601b4ccd782f3fb9b137e20c1fd2c7a
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af01895cb66e616591f2e4baa8dcd8151530eab133c73571ccb31c74f35422ce
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677921992b1e0cef3aee776f245975003d22f51d9bd6ed20f248ded1deb72fa9
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69353c629541c690c5471f8ec05fdab2bfecf3d37afaa436bc45939da6db68f
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e40ba6668cc03c9162c68a933d164bf38ae2d196a9a6fec03ae615491201185
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870968fea834e24b2e099cf3e4fe1e3fb8caf38d8f8e5b790d7d47386d4d05f5
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e19618bee7c6ef43256fea25abe19bca88535eb1e7dc213cde8929ae4e8180
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352ea964838cb4c73533fd678ef15712779c86f713a3f69d2961f73d4ad24fa2
+size 1064

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1972 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.001801801801802,
+  "eval_steps": 500,
+  "global_step": 833,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010810810810810811,
+      "grad_norm": 12.305854329298121,
+      "learning_rate": 2.9999652701989443e-05,
+      "loss": 2.4911,
+      "step": 3
+    },
+    {
+      "epoch": 0.021621621621621623,
+      "grad_norm": 4.240144865945876,
+      "learning_rate": 2.9998610824039904e-05,
+      "loss": 2.0652,
+      "step": 6
+    },
+    {
+      "epoch": 0.032432432432432434,
+      "grad_norm": 3.2725279352000864,
+      "learning_rate": 2.9996874414396984e-05,
+      "loss": 1.9611,
+      "step": 9
+    },
+    {
+      "epoch": 0.043243243243243246,
+      "grad_norm": 3.303814919197607,
+      "learning_rate": 2.9994443553467584e-05,
+      "loss": 2.0248,
+      "step": 12
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 3.003679341904051,
+      "learning_rate": 2.9991318353816112e-05,
+      "loss": 1.9903,
+      "step": 15
+    },
+    {
+      "epoch": 0.06486486486486487,
+      "grad_norm": 2.986093823263424,
+      "learning_rate": 2.9987498960159325e-05,
+      "loss": 1.8813,
+      "step": 18
+    },
+    {
+      "epoch": 0.07567567567567568,
+      "grad_norm": 2.790555184817465,
+      "learning_rate": 2.99829855493596e-05,
+      "loss": 1.976,
+      "step": 21
+    },
+    {
+      "epoch": 0.08648648648648649,
+      "grad_norm": 2.986932414712697,
+      "learning_rate": 2.997777833041674e-05,
+      "loss": 1.9653,
+      "step": 24
+    },
+    {
+      "epoch": 0.0972972972972973,
+      "grad_norm": 2.656324556829213,
+      "learning_rate": 2.9971877544458325e-05,
+      "loss": 1.8551,
+      "step": 27
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 3.2168328469993335,
+      "learning_rate": 2.996528346472851e-05,
+      "loss": 1.9812,
+      "step": 30
+    },
+    {
+      "epoch": 0.11891891891891893,
+      "grad_norm": 2.696843177932571,
+      "learning_rate": 2.9957996396575407e-05,
+      "loss": 1.9728,
+      "step": 33
+    },
+    {
+      "epoch": 0.12972972972972974,
+      "grad_norm": 3.2884895488967603,
+      "learning_rate": 2.995001667743691e-05,
+      "loss": 2.0118,
+      "step": 36
+    },
+    {
+      "epoch": 0.14054054054054055,
+      "grad_norm": 2.7402908143169555,
+      "learning_rate": 2.9941344676825106e-05,
+      "loss": 1.9478,
+      "step": 39
+    },
+    {
+      "epoch": 0.15135135135135136,
+      "grad_norm": 2.375732605463657,
+      "learning_rate": 2.993198079630913e-05,
+      "loss": 1.9092,
+      "step": 42
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 2.6770114768040143,
+      "learning_rate": 2.9921925469496594e-05,
+      "loss": 2.0062,
+      "step": 45
+    },
+    {
+      "epoch": 0.17297297297297298,
+      "grad_norm": 2.7654577179498943,
+      "learning_rate": 2.9911179162013495e-05,
+      "loss": 1.9634,
+      "step": 48
+    },
+    {
+      "epoch": 0.1837837837837838,
+      "grad_norm": 2.9383093484984966,
+      "learning_rate": 2.9899742371482663e-05,
+      "loss": 1.9553,
+      "step": 51
+    },
+    {
+      "epoch": 0.1945945945945946,
+      "grad_norm": 2.5901057077516443,
+      "learning_rate": 2.988761562750071e-05,
+      "loss": 1.9399,
+      "step": 54
+    },
+    {
+      "epoch": 0.20540540540540542,
+      "grad_norm": 2.381483900812707,
+      "learning_rate": 2.9874799491613513e-05,
+      "loss": 1.9434,
+      "step": 57
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 2.4229562035711263,
+      "learning_rate": 2.9861294557290205e-05,
+      "loss": 1.9481,
+      "step": 60
+    },
+    {
+      "epoch": 0.22702702702702704,
+      "grad_norm": 2.5010028477455393,
+      "learning_rate": 2.9847101449895692e-05,
+      "loss": 1.9495,
+      "step": 63
+    },
+    {
+      "epoch": 0.23783783783783785,
+      "grad_norm": 2.3138487877840244,
+      "learning_rate": 2.9832220826661707e-05,
+      "loss": 1.9259,
+      "step": 66
+    },
+    {
+      "epoch": 0.24864864864864866,
+      "grad_norm": 2.5123033559714245,
+      "learning_rate": 2.981665337665636e-05,
+      "loss": 1.9731,
+      "step": 69
+    },
+    {
+      "epoch": 0.2594594594594595,
+      "grad_norm": 2.6439754352664644,
+      "learning_rate": 2.9800399820752236e-05,
+      "loss": 1.9819,
+      "step": 72
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 2.3833028996710746,
+      "learning_rate": 2.9783460911593024e-05,
+      "loss": 1.8926,
+      "step": 75
+    },
+    {
+      "epoch": 0.2810810810810811,
+      "grad_norm": 2.4316596585025687,
+      "learning_rate": 2.9765837433558652e-05,
+      "loss": 1.9008,
+      "step": 78
+    },
+    {
+      "epoch": 0.2918918918918919,
+      "grad_norm": 2.492002538880973,
+      "learning_rate": 2.9747530202728965e-05,
+      "loss": 1.9837,
+      "step": 81
+    },
+    {
+      "epoch": 0.3027027027027027,
+      "grad_norm": 2.50223915481049,
+      "learning_rate": 2.9728540066845944e-05,
+      "loss": 1.9134,
+      "step": 84
+    },
+    {
+      "epoch": 0.31351351351351353,
+      "grad_norm": 2.79878301554176,
+      "learning_rate": 2.9708867905274444e-05,
+      "loss": 1.9226,
+      "step": 87
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 2.2798098795033477,
+      "learning_rate": 2.9688514628961473e-05,
+      "loss": 1.9029,
+      "step": 90
+    },
+    {
+      "epoch": 0.33513513513513515,
+      "grad_norm": 2.2032821621350536,
+      "learning_rate": 2.966748118039402e-05,
+      "loss": 1.917,
+      "step": 93
+    },
+    {
+      "epoch": 0.34594594594594597,
+      "grad_norm": 2.434797694487723,
+      "learning_rate": 2.9645768533555387e-05,
+      "loss": 1.9226,
+      "step": 96
+    },
+    {
+      "epoch": 0.3567567567567568,
+      "grad_norm": 2.2306447173589947,
+      "learning_rate": 2.9623377693880123e-05,
+      "loss": 1.9273,
+      "step": 99
+    },
+    {
+      "epoch": 0.3675675675675676,
+      "grad_norm": 2.4678527947600046,
+      "learning_rate": 2.9600309698207435e-05,
+      "loss": 1.8761,
+      "step": 102
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 2.172069501103823,
+      "learning_rate": 2.957656561473319e-05,
+      "loss": 1.9297,
+      "step": 105
+    },
+    {
+      "epoch": 0.3891891891891892,
+      "grad_norm": 2.009177875410658,
+      "learning_rate": 2.955214654296045e-05,
+      "loss": 1.8419,
+      "step": 108
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.8950203407246216,
+      "learning_rate": 2.952705361364855e-05,
+      "loss": 1.9594,
+      "step": 111
+    },
+    {
+      "epoch": 0.41081081081081083,
+      "grad_norm": 2.5653163311951106,
+      "learning_rate": 2.950128798876075e-05,
+      "loss": 1.8869,
+      "step": 114
+    },
+    {
+      "epoch": 0.42162162162162165,
+      "grad_norm": 2.732827590601958,
+      "learning_rate": 2.947485086141042e-05,
+      "loss": 1.8974,
+      "step": 117
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 2.144285276139079,
+      "learning_rate": 2.9447743455805793e-05,
+      "loss": 1.9196,
+      "step": 120
+    },
+    {
+      "epoch": 0.44324324324324327,
+      "grad_norm": 2.4409981534782914,
+      "learning_rate": 2.9419967027193267e-05,
+      "loss": 1.9428,
+      "step": 123
+    },
+    {
+      "epoch": 0.4540540540540541,
+      "grad_norm": 2.646738039623452,
+      "learning_rate": 2.9391522861799298e-05,
+      "loss": 1.9737,
+      "step": 126
+    },
+    {
+      "epoch": 0.4648648648648649,
+      "grad_norm": 2.3721501035510233,
+      "learning_rate": 2.9362412276770833e-05,
+      "loss": 1.9554,
+      "step": 129
+    },
+    {
+      "epoch": 0.4756756756756757,
+      "grad_norm": 2.423435489971938,
+      "learning_rate": 2.93326366201143e-05,
+      "loss": 1.9787,
+      "step": 132
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 2.207859877546887,
+      "learning_rate": 2.9302197270633207e-05,
+      "loss": 1.9259,
+      "step": 135
+    },
+    {
+      "epoch": 0.4972972972972973,
+      "grad_norm": 2.4856913311288733,
+      "learning_rate": 2.9271095637864295e-05,
+      "loss": 1.9433,
+      "step": 138
+    },
+    {
+      "epoch": 0.5081081081081081,
+      "grad_norm": 2.440879046484796,
+      "learning_rate": 2.9239333162012256e-05,
+      "loss": 1.8939,
+      "step": 141
+    },
+    {
+      "epoch": 0.518918918918919,
+      "grad_norm": 2.45798549198192,
+      "learning_rate": 2.9206911313883037e-05,
+      "loss": 1.9845,
+      "step": 144
+    },
+    {
+      "epoch": 0.5297297297297298,
+      "grad_norm": 2.3336768971980706,
+      "learning_rate": 2.9173831594815768e-05,
+      "loss": 1.916,
+      "step": 147
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 2.39094175177689,
+      "learning_rate": 2.9140095536613182e-05,
+      "loss": 1.8494,
+      "step": 150
+    },
+    {
+      "epoch": 0.5513513513513514,
+      "grad_norm": 2.429522504872439,
+      "learning_rate": 2.9105704701470744e-05,
+      "loss": 1.9189,
+      "step": 153
+    },
+    {
+      "epoch": 0.5621621621621622,
+      "grad_norm": 2.7779327685196957,
+      "learning_rate": 2.907066068190426e-05,
+      "loss": 2.027,
+      "step": 156
+    },
+    {
+      "epoch": 0.572972972972973,
+      "grad_norm": 2.4829217011923106,
+      "learning_rate": 2.903496510067618e-05,
+      "loss": 1.9414,
+      "step": 159
+    },
+    {
+      "epoch": 0.5837837837837838,
+      "grad_norm": 2.307375658362859,
+      "learning_rate": 2.899861961072041e-05,
+      "loss": 1.9,
+      "step": 162
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 2.5317691911892855,
+      "learning_rate": 2.896162589506579e-05,
+      "loss": 1.9359,
+      "step": 165
+    },
+    {
+      "epoch": 0.6054054054054054,
+      "grad_norm": 2.4918163002128138,
+      "learning_rate": 2.8923985666758178e-05,
+      "loss": 1.8599,
+      "step": 168
+    },
+    {
+      "epoch": 0.6162162162162163,
+      "grad_norm": 2.076258038368402,
+      "learning_rate": 2.888570066878109e-05,
+      "loss": 1.9127,
+      "step": 171
+    },
+    {
+      "epoch": 0.6270270270270271,
+      "grad_norm": 2.185928367527268,
+      "learning_rate": 2.884677267397502e-05,
+      "loss": 1.8128,
+      "step": 174
+    },
+    {
+      "epoch": 0.6378378378378379,
+      "grad_norm": 2.866856917703555,
+      "learning_rate": 2.88072034849553e-05,
+      "loss": 1.9267,
+      "step": 177
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 2.403239863727176,
+      "learning_rate": 2.8766994934028697e-05,
+      "loss": 1.9034,
+      "step": 180
+    },
+    {
+      "epoch": 0.6594594594594595,
+      "grad_norm": 2.156072962852351,
+      "learning_rate": 2.8726148883108505e-05,
+      "loss": 1.9516,
+      "step": 183
+    },
+    {
+      "epoch": 0.6702702702702703,
+      "grad_norm": 2.511207967261495,
+      "learning_rate": 2.868466722362836e-05,
+      "loss": 1.8811,
+      "step": 186
+    },
+    {
+      "epoch": 0.6810810810810811,
+      "grad_norm": 2.3602190597776467,
+      "learning_rate": 2.8642551876454625e-05,
+      "loss": 1.9503,
+      "step": 189
+    },
+    {
+      "epoch": 0.6918918918918919,
+      "grad_norm": 2.482488878028461,
+      "learning_rate": 2.8599804791797483e-05,
+      "loss": 1.8807,
+      "step": 192
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 2.587845075067827,
+      "learning_rate": 2.8556427949120587e-05,
+      "loss": 1.9359,
+      "step": 195
+    },
+    {
+      "epoch": 0.7135135135135136,
+      "grad_norm": 2.209476666719861,
+      "learning_rate": 2.851242335704943e-05,
+      "loss": 1.898,
+      "step": 198
+    },
+    {
+      "epoch": 0.7243243243243244,
+      "grad_norm": 2.419802615785546,
+      "learning_rate": 2.8467793053278318e-05,
+      "loss": 1.8444,
+      "step": 201
+    },
+    {
+      "epoch": 0.7351351351351352,
+      "grad_norm": 2.226045413120279,
+      "learning_rate": 2.842253910447601e-05,
+      "loss": 1.8982,
+      "step": 204
+    },
+    {
+      "epoch": 0.745945945945946,
+      "grad_norm": 2.44484302970035,
+      "learning_rate": 2.837666360619002e-05,
+      "loss": 1.9596,
+      "step": 207
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 2.43331348143749,
+      "learning_rate": 2.8330168682749594e-05,
+      "loss": 1.9313,
+      "step": 210
+    },
+    {
+      "epoch": 0.7675675675675676,
+      "grad_norm": 2.0567115700480247,
+      "learning_rate": 2.8283056487167313e-05,
+      "loss": 1.9314,
+      "step": 213
+    },
+    {
+      "epoch": 0.7783783783783784,
+      "grad_norm": 2.3852531892957223,
+      "learning_rate": 2.8235329201039424e-05,
+      "loss": 1.8631,
+      "step": 216
+    },
+    {
+      "epoch": 0.7891891891891892,
+      "grad_norm": 2.136466132414422,
+      "learning_rate": 2.8186989034444794e-05,
+      "loss": 1.859,
+      "step": 219
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.592701276826683,
+      "learning_rate": 2.8138038225842577e-05,
+      "loss": 1.96,
+      "step": 222
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 2.0512819357757,
+      "learning_rate": 2.808847904196857e-05,
+      "loss": 1.8646,
+      "step": 225
+    },
+    {
+      "epoch": 0.8216216216216217,
+      "grad_norm": 2.1496899989713767,
+      "learning_rate": 2.8038313777730237e-05,
+      "loss": 1.8924,
+      "step": 228
+    },
+    {
+      "epoch": 0.8324324324324325,
+      "grad_norm": 2.150493531375372,
+      "learning_rate": 2.798754475610044e-05,
+      "loss": 1.7991,
+      "step": 231
+    },
+    {
+      "epoch": 0.8432432432432433,
+      "grad_norm": 2.094639871928105,
+      "learning_rate": 2.7936174328009864e-05,
+      "loss": 1.9364,
+      "step": 234
+    },
+    {
+      "epoch": 0.8540540540540541,
+      "grad_norm": 2.3155422463173623,
+      "learning_rate": 2.7884204872238182e-05,
+      "loss": 1.8647,
+      "step": 237
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 2.2606435766654234,
+      "learning_rate": 2.7831638795303873e-05,
+      "loss": 1.8224,
+      "step": 240
+    },
+    {
+      "epoch": 0.8756756756756757,
+      "grad_norm": 2.2579963330786774,
+      "learning_rate": 2.7778478531352795e-05,
+      "loss": 1.8282,
+      "step": 243
+    },
+    {
+      "epoch": 0.8864864864864865,
+      "grad_norm": 1.9817080023633638,
+      "learning_rate": 2.7724726542045463e-05,
+      "loss": 1.8818,
+      "step": 246
+    },
+    {
+      "epoch": 0.8972972972972973,
+      "grad_norm": 2.24441068506298,
+      "learning_rate": 2.7670385316443084e-05,
+      "loss": 1.9305,
+      "step": 249
+    },
+    {
+      "epoch": 0.9081081081081082,
+      "grad_norm": 2.541165407563793,
+      "learning_rate": 2.7615457370892257e-05,
+      "loss": 1.8736,
+      "step": 252
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 1.9510813262964137,
+      "learning_rate": 2.7559945248908468e-05,
+      "loss": 1.8999,
+      "step": 255
+    },
+    {
+      "epoch": 0.9297297297297298,
+      "grad_norm": 2.4719694412540245,
+      "learning_rate": 2.7503851521058333e-05,
+      "loss": 1.8846,
+      "step": 258
+    },
+    {
+      "epoch": 0.9405405405405406,
+      "grad_norm": 2.3098919918683096,
+      "learning_rate": 2.744717878484053e-05,
+      "loss": 1.8999,
+      "step": 261
+    },
+    {
+      "epoch": 0.9513513513513514,
+      "grad_norm": 2.465948183249405,
+      "learning_rate": 2.7389929664565523e-05,
+      "loss": 1.8028,
+      "step": 264
+    },
+    {
+      "epoch": 0.9621621621621622,
+      "grad_norm": 2.204108562575812,
+      "learning_rate": 2.733210681123406e-05,
+      "loss": 1.9526,
+      "step": 267
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 2.3661976037384815,
+      "learning_rate": 2.7273712902414396e-05,
+      "loss": 1.8472,
+      "step": 270
+    },
+    {
+      "epoch": 0.9837837837837838,
+      "grad_norm": 2.1596420136763137,
+      "learning_rate": 2.7214750642118315e-05,
+      "loss": 1.849,
+      "step": 273
+    },
+    {
+      "epoch": 0.9945945945945946,
+      "grad_norm": 2.1642232408896453,
+      "learning_rate": 2.715522276067591e-05,
+      "loss": 1.8476,
+      "step": 276
+    },
+    {
+      "epoch": 1.0054054054054054,
+      "grad_norm": 2.102003078375359,
+      "learning_rate": 2.709513201460915e-05,
+      "loss": 1.6092,
+      "step": 279
+    },
+    {
+      "epoch": 1.0162162162162163,
+      "grad_norm": 2.580181780728641,
+      "learning_rate": 2.7034481186504253e-05,
+      "loss": 1.3409,
+      "step": 282
+    },
+    {
+      "epoch": 1.027027027027027,
+      "grad_norm": 1.987111465217205,
+      "learning_rate": 2.6973273084882802e-05,
+      "loss": 1.3026,
+      "step": 285
+    },
+    {
+      "epoch": 1.037837837837838,
+      "grad_norm": 1.835737689431998,
+      "learning_rate": 2.691151054407172e-05,
+      "loss": 1.2992,
+      "step": 288
+    },
+    {
+      "epoch": 1.0486486486486486,
+      "grad_norm": 2.075134750486952,
+      "learning_rate": 2.684919642407202e-05,
+      "loss": 1.2751,
+      "step": 291
+    },
+    {
+      "epoch": 1.0594594594594595,
+      "grad_norm": 2.154847674569881,
+      "learning_rate": 2.6786333610426353e-05,
+      "loss": 1.2951,
+      "step": 294
+    },
+    {
+      "epoch": 1.0702702702702702,
+      "grad_norm": 2.201259061666919,
+      "learning_rate": 2.67229250140854e-05,
+      "loss": 1.2813,
+      "step": 297
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 2.099199218269766,
+      "learning_rate": 2.6658973571273077e-05,
+      "loss": 1.2422,
+      "step": 300
+    },
+    {
+      "epoch": 1.0918918918918918,
+      "grad_norm": 2.1682257578187185,
+      "learning_rate": 2.6594482243350558e-05,
+      "loss": 1.2958,
+      "step": 303
+    },
+    {
+      "epoch": 1.1027027027027028,
+      "grad_norm": 1.9450085810744047,
+      "learning_rate": 2.6529454016679175e-05,
+      "loss": 1.2175,
+      "step": 306
+    },
+    {
+      "epoch": 1.1135135135135135,
+      "grad_norm": 1.9627021282761483,
+      "learning_rate": 2.6463891902482087e-05,
+      "loss": 1.2143,
+      "step": 309
+    },
+    {
+      "epoch": 1.1243243243243244,
+      "grad_norm": 2.0335479254484716,
+      "learning_rate": 2.639779893670487e-05,
+      "loss": 1.2425,
+      "step": 312
+    },
+    {
+      "epoch": 1.135135135135135,
+      "grad_norm": 2.004046748177982,
+      "learning_rate": 2.6331178179874934e-05,
+      "loss": 1.2834,
+      "step": 315
+    },
+    {
+      "epoch": 1.145945945945946,
+      "grad_norm": 2.1051127397939333,
+      "learning_rate": 2.6264032716959778e-05,
+      "loss": 1.2787,
+      "step": 318
+    },
+    {
+      "epoch": 1.1567567567567567,
+      "grad_norm": 1.941259889065534,
+      "learning_rate": 2.6196365657224166e-05,
+      "loss": 1.2456,
+      "step": 321
+    },
+    {
+      "epoch": 1.1675675675675676,
+      "grad_norm": 2.4331557433084643,
+      "learning_rate": 2.612818013408613e-05,
+      "loss": 1.2398,
+      "step": 324
+    },
+    {
+      "epoch": 1.1783783783783783,
+      "grad_norm": 2.125511278222413,
+      "learning_rate": 2.6059479304971867e-05,
+      "loss": 1.2717,
+      "step": 327
+    },
+    {
+      "epoch": 1.1891891891891893,
+      "grad_norm": 2.254173095275699,
+      "learning_rate": 2.5990266351169554e-05,
+      "loss": 1.2694,
+      "step": 330
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.9756822137444563,
+      "learning_rate": 2.5920544477682012e-05,
+      "loss": 1.2747,
+      "step": 333
+    },
+    {
+      "epoch": 1.2108108108108109,
+      "grad_norm": 2.1110444161525077,
+      "learning_rate": 2.5850316913078298e-05,
+      "loss": 1.295,
+      "step": 336
+    },
+    {
+      "epoch": 1.2216216216216216,
+      "grad_norm": 2.1222020915135995,
+      "learning_rate": 2.5779586909344206e-05,
+      "loss": 1.3109,
+      "step": 339
+    },
+    {
+      "epoch": 1.2324324324324325,
+      "grad_norm": 1.8417665825926723,
+      "learning_rate": 2.570835774173169e-05,
+      "loss": 1.3056,
+      "step": 342
+    },
+    {
+      "epoch": 1.2432432432432432,
+      "grad_norm": 2.0280022835044016,
+      "learning_rate": 2.563663270860717e-05,
+      "loss": 1.32,
+      "step": 345
+    },
+    {
+      "epoch": 1.2540540540540541,
+      "grad_norm": 2.025208781667826,
+      "learning_rate": 2.5564415131298824e-05,
+      "loss": 1.2705,
+      "step": 348
+    },
+    {
+      "epoch": 1.2648648648648648,
+      "grad_norm": 1.9120753635362695,
+      "learning_rate": 2.5491708353942773e-05,
+      "loss": 1.2645,
+      "step": 351
+    },
+    {
+      "epoch": 1.2756756756756757,
+      "grad_norm": 1.9983727272207963,
+      "learning_rate": 2.5418515743328232e-05,
+      "loss": 1.2795,
+      "step": 354
+    },
+    {
+      "epoch": 1.2864864864864864,
+      "grad_norm": 2.0065772123507735,
+      "learning_rate": 2.534484068874162e-05,
+      "loss": 1.3017,
+      "step": 357
+    },
+    {
+      "epoch": 1.2972972972972974,
+      "grad_norm": 2.0474786433390335,
+      "learning_rate": 2.5270686601809577e-05,
+      "loss": 1.25,
+      "step": 360
+    },
+    {
+      "epoch": 1.308108108108108,
+      "grad_norm": 1.9384897745280192,
+      "learning_rate": 2.5196056916341016e-05,
+      "loss": 1.2294,
+      "step": 363
+    },
+    {
+      "epoch": 1.318918918918919,
+      "grad_norm": 1.9918888965378558,
+      "learning_rate": 2.512095508816812e-05,
+      "loss": 1.2941,
+      "step": 366
+    },
+    {
+      "epoch": 1.3297297297297297,
+      "grad_norm": 1.9846908820959408,
+      "learning_rate": 2.5045384594986285e-05,
+      "loss": 1.2538,
+      "step": 369
+    },
+    {
+      "epoch": 1.3405405405405406,
+      "grad_norm": 2.080792691569016,
+      "learning_rate": 2.4969348936193102e-05,
+      "loss": 1.2543,
+      "step": 372
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 2.0125722435554514,
+      "learning_rate": 2.4892851632726306e-05,
+      "loss": 1.2757,
+      "step": 375
+    },
+    {
+      "epoch": 1.3621621621621622,
+      "grad_norm": 1.9764284092403845,
+      "learning_rate": 2.481589622690075e-05,
+      "loss": 1.2625,
+      "step": 378
+    },
+    {
+      "epoch": 1.372972972972973,
+      "grad_norm": 2.027142138762262,
+      "learning_rate": 2.4738486282244333e-05,
+      "loss": 1.2831,
+      "step": 381
+    },
+    {
+      "epoch": 1.3837837837837839,
+      "grad_norm": 1.9798502988269455,
+      "learning_rate": 2.4660625383333028e-05,
+      "loss": 1.2673,
+      "step": 384
+    },
+    {
+      "epoch": 1.3945945945945946,
+      "grad_norm": 2.047403010408032,
+      "learning_rate": 2.4582317135624886e-05,
+      "loss": 1.2698,
+      "step": 387
+    },
+    {
+      "epoch": 1.4054054054054055,
+      "grad_norm": 2.012366168035498,
+      "learning_rate": 2.450356516529304e-05,
+      "loss": 1.3192,
+      "step": 390
+    },
+    {
+      "epoch": 1.4162162162162162,
+      "grad_norm": 2.05238416440222,
+      "learning_rate": 2.4424373119057852e-05,
+      "loss": 1.2696,
+      "step": 393
+    },
+    {
+      "epoch": 1.427027027027027,
+      "grad_norm": 2.2479201479489923,
+      "learning_rate": 2.4344744664018e-05,
+      "loss": 1.3024,
+      "step": 396
+    },
+    {
+      "epoch": 1.4378378378378378,
+      "grad_norm": 2.1894458789904583,
+      "learning_rate": 2.4264683487480687e-05,
+      "loss": 1.3099,
+      "step": 399
+    },
+    {
+      "epoch": 1.4486486486486487,
+      "grad_norm": 2.037077094665106,
+      "learning_rate": 2.4184193296790887e-05,
+      "loss": 1.2514,
+      "step": 402
+    },
+    {
+      "epoch": 1.4594594594594594,
+      "grad_norm": 2.0273525133084087,
+      "learning_rate": 2.410327781915969e-05,
+      "loss": 1.2798,
+      "step": 405
+    },
+    {
+      "epoch": 1.4702702702702704,
+      "grad_norm": 2.1689507381607713,
+      "learning_rate": 2.402194080149167e-05,
+      "loss": 1.3066,
+      "step": 408
+    },
+    {
+      "epoch": 1.481081081081081,
+      "grad_norm": 1.9503795898614715,
+      "learning_rate": 2.394018601021143e-05,
+      "loss": 1.2582,
+      "step": 411
+    },
+    {
+      "epoch": 1.491891891891892,
+      "grad_norm": 2.2761809415998706,
+      "learning_rate": 2.385801723108914e-05,
+      "loss": 1.2981,
+      "step": 414
+    },
+    {
+      "epoch": 1.5027027027027027,
+      "grad_norm": 2.0356459303417296,
+      "learning_rate": 2.3775438269065277e-05,
+      "loss": 1.2505,
+      "step": 417
+    },
+    {
+      "epoch": 1.5135135135135136,
+      "grad_norm": 1.9297970402246538,
+      "learning_rate": 2.3692452948074395e-05,
+      "loss": 1.2546,
+      "step": 420
+    },
+    {
+      "epoch": 1.5243243243243243,
+      "grad_norm": 2.0123397178971714,
+      "learning_rate": 2.360906511086809e-05,
+      "loss": 1.2571,
+      "step": 423
+    },
+    {
+      "epoch": 1.535135135135135,
+      "grad_norm": 2.3184894064368033,
+      "learning_rate": 2.352527861883702e-05,
+      "loss": 1.2625,
+      "step": 426
+    },
+    {
+      "epoch": 1.545945945945946,
+      "grad_norm": 1.936734476547218,
+      "learning_rate": 2.3441097351832113e-05,
+      "loss": 1.3054,
+      "step": 429
+    },
+    {
+      "epoch": 1.5567567567567568,
+      "grad_norm": 2.030353788212261,
+      "learning_rate": 2.3356525207984916e-05,
+      "loss": 1.2755,
+      "step": 432
+    },
+    {
+      "epoch": 1.5675675675675675,
+      "grad_norm": 2.039094018045801,
+      "learning_rate": 2.3271566103527063e-05,
+      "loss": 1.2686,
+      "step": 435
+    },
+    {
+      "epoch": 1.5783783783783782,
+      "grad_norm": 1.9514327297087253,
+      "learning_rate": 2.318622397260896e-05,
+      "loss": 1.2683,
+      "step": 438
+    },
+    {
+      "epoch": 1.5891891891891892,
+      "grad_norm": 1.8736269848724938,
+      "learning_rate": 2.3100502767117566e-05,
+      "loss": 1.2255,
+      "step": 441
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.9037413275565993,
+      "learning_rate": 2.301440645649344e-05,
+      "loss": 1.2669,
+      "step": 444
+    },
+    {
+      "epoch": 1.6108108108108108,
+      "grad_norm": 2.172424343159148,
+      "learning_rate": 2.2927939027546895e-05,
+      "loss": 1.2601,
+      "step": 447
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 2.1709165438362152,
+      "learning_rate": 2.284110448427341e-05,
+      "loss": 1.2992,
+      "step": 450
+    },
+    {
+      "epoch": 1.6324324324324324,
+      "grad_norm": 1.9517268177516773,
+      "learning_rate": 2.2753906847668197e-05,
+      "loss": 1.2602,
+      "step": 453
+    },
+    {
+      "epoch": 1.6432432432432433,
+      "grad_norm": 2.142716687001655,
+      "learning_rate": 2.266635015554002e-05,
+      "loss": 1.2387,
+      "step": 456
+    },
+    {
+      "epoch": 1.654054054054054,
+      "grad_norm": 1.892430237031948,
+      "learning_rate": 2.2578438462324214e-05,
+      "loss": 1.2796,
+      "step": 459
+    },
+    {
+      "epoch": 1.6648648648648647,
+      "grad_norm": 1.9831414889207626,
+      "learning_rate": 2.2490175838894928e-05,
+      "loss": 1.2693,
+      "step": 462
+    },
+    {
+      "epoch": 1.6756756756756757,
+      "grad_norm": 1.968788091532238,
+      "learning_rate": 2.2401566372376635e-05,
+      "loss": 1.2826,
+      "step": 465
+    },
+    {
+      "epoch": 1.6864864864864866,
+      "grad_norm": 2.028829960671371,
+      "learning_rate": 2.231261416595486e-05,
+      "loss": 1.2412,
+      "step": 468
+    },
+    {
+      "epoch": 1.6972972972972973,
+      "grad_norm": 2.0761836559826126,
+      "learning_rate": 2.222332333868618e-05,
+      "loss": 1.2907,
+      "step": 471
+    },
+    {
+      "epoch": 1.708108108108108,
+      "grad_norm": 2.0505303769583714,
+      "learning_rate": 2.2133698025307487e-05,
+      "loss": 1.2164,
+      "step": 474
+    },
+    {
+      "epoch": 1.718918918918919,
+      "grad_norm": 1.9892599771865245,
+      "learning_rate": 2.2043742376044507e-05,
+      "loss": 1.3029,
+      "step": 477
+    },
+    {
+      "epoch": 1.7297297297297298,
+      "grad_norm": 2.056680185472525,
+      "learning_rate": 2.195346055641966e-05,
+      "loss": 1.2532,
+      "step": 480
+    },
+    {
+      "epoch": 1.7405405405405405,
+      "grad_norm": 2.020031485543879,
+      "learning_rate": 2.186285674705911e-05,
+      "loss": 1.2752,
+      "step": 483
+    },
+    {
+      "epoch": 1.7513513513513512,
+      "grad_norm": 1.976348646730665,
+      "learning_rate": 2.1771935143499233e-05,
+      "loss": 1.281,
+      "step": 486
+    },
+    {
+      "epoch": 1.7621621621621621,
+      "grad_norm": 1.9671362390239506,
+      "learning_rate": 2.1680699955992295e-05,
+      "loss": 1.2567,
+      "step": 489
+    },
+    {
+      "epoch": 1.772972972972973,
+      "grad_norm": 1.9862314788875317,
+      "learning_rate": 2.1589155409311514e-05,
+      "loss": 1.2722,
+      "step": 492
+    },
+    {
+      "epoch": 1.7837837837837838,
+      "grad_norm": 1.8794017228975768,
+      "learning_rate": 2.1497305742555416e-05,
+      "loss": 1.2267,
+      "step": 495
+    },
+    {
+      "epoch": 1.7945945945945945,
+      "grad_norm": 1.8537400724418822,
+      "learning_rate": 2.140515520895154e-05,
+      "loss": 1.2856,
+      "step": 498
+    },
+    {
+      "epoch": 1.8054054054054054,
+      "grad_norm": 2.2140372302917424,
+      "learning_rate": 2.131270807565948e-05,
+      "loss": 1.2668,
+      "step": 501
+    },
+    {
+      "epoch": 1.8162162162162163,
+      "grad_norm": 2.1224010879465514,
+      "learning_rate": 2.1219968623573292e-05,
+      "loss": 1.3403,
+      "step": 504
+    },
+    {
+      "epoch": 1.827027027027027,
+      "grad_norm": 2.150717671959958,
+      "learning_rate": 2.1126941147123285e-05,
+      "loss": 1.3294,
+      "step": 507
+    },
+    {
+      "epoch": 1.8378378378378377,
+      "grad_norm": 1.9412785818269171,
+      "learning_rate": 2.1033629954077123e-05,
+      "loss": 1.298,
+      "step": 510
+    },
+    {
+      "epoch": 1.8486486486486486,
+      "grad_norm": 1.9061258724957593,
+      "learning_rate": 2.0940039365340363e-05,
+      "loss": 1.2984,
+      "step": 513
+    },
+    {
+      "epoch": 1.8594594594594596,
+      "grad_norm": 1.91000429693783,
+      "learning_rate": 2.0846173714756372e-05,
+      "loss": 1.2541,
+      "step": 516
+    },
+    {
+      "epoch": 1.8702702702702703,
+      "grad_norm": 2.0253367045491957,
+      "learning_rate": 2.0752037348905656e-05,
+      "loss": 1.3045,
+      "step": 519
+    },
+    {
+      "epoch": 1.881081081081081,
+      "grad_norm": 2.099866673823967,
+      "learning_rate": 2.0657634626904544e-05,
+      "loss": 1.2841,
+      "step": 522
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 2.053590437534557,
+      "learning_rate": 2.056296992020339e-05,
+      "loss": 1.2732,
+      "step": 525
+    },
+    {
+      "epoch": 1.9027027027027028,
+      "grad_norm": 2.037664067587095,
+      "learning_rate": 2.046804761238409e-05,
+      "loss": 1.2661,
+      "step": 528
+    },
+    {
+      "epoch": 1.9135135135135135,
+      "grad_norm": 2.1032576901560875,
+      "learning_rate": 2.037287209895713e-05,
+      "loss": 1.2815,
+      "step": 531
+    },
+    {
+      "epoch": 1.9243243243243242,
+      "grad_norm": 2.0365409183820393,
+      "learning_rate": 2.0277447787158057e-05,
+      "loss": 1.281,
+      "step": 534
+    },
+    {
+      "epoch": 1.9351351351351351,
+      "grad_norm": 1.9303661726886707,
+      "learning_rate": 2.0181779095743335e-05,
+      "loss": 1.3122,
+      "step": 537
+    },
+    {
+      "epoch": 1.945945945945946,
+      "grad_norm": 2.0989107332254164,
+      "learning_rate": 2.008587045478581e-05,
+      "loss": 1.2766,
+      "step": 540
+    },
+    {
+      "epoch": 1.9567567567567568,
+      "grad_norm": 2.2610013717867607,
+      "learning_rate": 1.9989726305469497e-05,
+      "loss": 1.2744,
+      "step": 543
+    },
+    {
+      "epoch": 1.9675675675675675,
+      "grad_norm": 1.9759438397315554,
+      "learning_rate": 1.989335109988397e-05,
+      "loss": 1.2821,
+      "step": 546
+    },
+    {
+      "epoch": 1.9783783783783784,
+      "grad_norm": 2.0630705322166185,
+      "learning_rate": 1.9796749300818185e-05,
+      "loss": 1.2964,
+      "step": 549
+    },
+    {
+      "epoch": 1.9891891891891893,
+      "grad_norm": 2.062855518861247,
+      "learning_rate": 1.9699925381553824e-05,
+      "loss": 1.3101,
+      "step": 552
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.004529311768417,
+      "learning_rate": 1.960288382565816e-05,
+      "loss": 1.2436,
+      "step": 555
+    },
+    {
+      "epoch": 2.0108108108108107,
+      "grad_norm": 1.8731442249653363,
+      "learning_rate": 1.9505629126776435e-05,
+      "loss": 0.7428,
+      "step": 558
+    },
+    {
+      "epoch": 2.0216216216216214,
+      "grad_norm": 2.7743566111060356,
+      "learning_rate": 1.9408165788423776e-05,
+      "loss": 0.6521,
+      "step": 561
+    },
+    {
+      "epoch": 2.0324324324324325,
+      "grad_norm": 2.4263480281287326,
+      "learning_rate": 1.9310498323776642e-05,
+      "loss": 0.6719,
+      "step": 564
+    },
+    {
+      "epoch": 2.0432432432432432,
+      "grad_norm": 1.7971900573296662,
+      "learning_rate": 1.9212631255463864e-05,
+      "loss": 0.6507,
+      "step": 567
+    },
+    {
+      "epoch": 2.054054054054054,
+      "grad_norm": 1.9536502652307774,
+      "learning_rate": 1.911456911535719e-05,
+      "loss": 0.6713,
+      "step": 570
+    },
+    {
+      "epoch": 2.064864864864865,
+      "grad_norm": 1.6734389443783486,
+      "learning_rate": 1.9016316444361443e-05,
+      "loss": 0.6513,
+      "step": 573
+    },
+    {
+      "epoch": 2.075675675675676,
+      "grad_norm": 2.0889794055853446,
+      "learning_rate": 1.8917877792204238e-05,
+      "loss": 0.6391,
+      "step": 576
+    },
+    {
+      "epoch": 2.0864864864864865,
+      "grad_norm": 1.952453907013592,
+      "learning_rate": 1.881925771722533e-05,
+      "loss": 0.6278,
+      "step": 579
+    },
+    {
+      "epoch": 2.097297297297297,
+      "grad_norm": 1.9394182987242035,
+      "learning_rate": 1.872046078616549e-05,
+      "loss": 0.6268,
+      "step": 582
+    },
+    {
+      "epoch": 2.108108108108108,
+      "grad_norm": 1.7760412655871423,
+      "learning_rate": 1.862149157395506e-05,
+      "loss": 0.6217,
+      "step": 585
+    },
+    {
+      "epoch": 2.118918918918919,
+      "grad_norm": 1.697555380465673,
+      "learning_rate": 1.852235466350212e-05,
+      "loss": 0.6496,
+      "step": 588
+    },
+    {
+      "epoch": 2.1297297297297297,
+      "grad_norm": 1.9579376565670537,
+      "learning_rate": 1.8423054645480228e-05,
+      "loss": 0.6388,
+      "step": 591
+    },
+    {
+      "epoch": 2.1405405405405404,
+      "grad_norm": 2.1761144428281565,
+      "learning_rate": 1.8323596118115882e-05,
+      "loss": 0.6293,
+      "step": 594
+    },
+    {
+      "epoch": 2.1513513513513516,
+      "grad_norm": 1.7805116699629946,
+      "learning_rate": 1.8223983686975576e-05,
+      "loss": 0.6321,
+      "step": 597
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 2.0913504208478773,
+      "learning_rate": 1.8124221964752535e-05,
+      "loss": 0.6312,
+      "step": 600
+    },
+    {
+      "epoch": 2.172972972972973,
+      "grad_norm": 1.7500638235123256,
+      "learning_rate": 1.80243155710531e-05,
+      "loss": 0.6217,
+      "step": 603
+    },
+    {
+      "epoch": 2.1837837837837837,
+      "grad_norm": 1.8271358171780696,
+      "learning_rate": 1.7924269132182855e-05,
+      "loss": 0.6711,
+      "step": 606
+    },
+    {
+      "epoch": 2.1945945945945944,
+      "grad_norm": 1.9546793256337727,
+      "learning_rate": 1.782408728093235e-05,
+      "loss": 0.6392,
+      "step": 609
+    },
+    {
+      "epoch": 2.2054054054054055,
+      "grad_norm": 1.7882856434212824,
+      "learning_rate": 1.7723774656362602e-05,
+      "loss": 0.6395,
+      "step": 612
+    },
+    {
+      "epoch": 2.2162162162162162,
+      "grad_norm": 1.7898241991442447,
+      "learning_rate": 1.762333590359028e-05,
+      "loss": 0.6521,
+      "step": 615
+    },
+    {
+      "epoch": 2.227027027027027,
+      "grad_norm": 1.6654897277159277,
+      "learning_rate": 1.752277567357258e-05,
+      "loss": 0.646,
+      "step": 618
+    },
+    {
+      "epoch": 2.237837837837838,
+      "grad_norm": 1.8175887991140565,
+      "learning_rate": 1.7422098622891873e-05,
+      "loss": 0.613,
+      "step": 621
+    },
+    {
+      "epoch": 2.2486486486486488,
+      "grad_norm": 2.208881509880086,
+      "learning_rate": 1.7321309413540087e-05,
+      "loss": 0.6375,
+      "step": 624
+    },
+    {
+      "epoch": 2.2594594594594595,
+      "grad_norm": 1.8520498287505407,
+      "learning_rate": 1.722041271270281e-05,
+      "loss": 0.6613,
+      "step": 627
+    },
+    {
+      "epoch": 2.27027027027027,
+      "grad_norm": 2.0512133133202988,
+      "learning_rate": 1.7119413192543165e-05,
+      "loss": 0.6292,
+      "step": 630
+    },
+    {
+      "epoch": 2.281081081081081,
+      "grad_norm": 1.773677981324912,
+      "learning_rate": 1.701831552998548e-05,
+      "loss": 0.6399,
+      "step": 633
+    },
+    {
+      "epoch": 2.291891891891892,
+      "grad_norm": 1.8469844530131443,
+      "learning_rate": 1.6917124406498697e-05,
+      "loss": 0.6622,
+      "step": 636
+    },
+    {
+      "epoch": 2.3027027027027027,
+      "grad_norm": 2.0663988043195265,
+      "learning_rate": 1.68158445078796e-05,
+      "loss": 0.6428,
+      "step": 639
+    },
+    {
+      "epoch": 2.3135135135135134,
+      "grad_norm": 1.7259116146942584,
+      "learning_rate": 1.671448052403583e-05,
+      "loss": 0.6528,
+      "step": 642
+    },
+    {
+      "epoch": 2.3243243243243246,
+      "grad_norm": 1.9046842309367298,
+      "learning_rate": 1.6613037148768702e-05,
+      "loss": 0.6619,
+      "step": 645
+    },
+    {
+      "epoch": 2.3351351351351353,
+      "grad_norm": 1.8564656298207483,
+      "learning_rate": 1.6511519079555887e-05,
+      "loss": 0.6665,
+      "step": 648
+    },
+    {
+      "epoch": 2.345945945945946,
+      "grad_norm": 1.8614483941828683,
+      "learning_rate": 1.640993101733383e-05,
+      "loss": 0.6494,
+      "step": 651
+    },
+    {
+      "epoch": 2.3567567567567567,
+      "grad_norm": 1.8411704889596792,
+      "learning_rate": 1.6308277666280133e-05,
+      "loss": 0.6286,
+      "step": 654
+    },
+    {
+      "epoch": 2.3675675675675674,
+      "grad_norm": 1.810238547613111,
+      "learning_rate": 1.6206563733595666e-05,
+      "loss": 0.6544,
+      "step": 657
+    },
+    {
+      "epoch": 2.3783783783783785,
+      "grad_norm": 1.803680767305892,
+      "learning_rate": 1.610479392928663e-05,
+      "loss": 0.6449,
+      "step": 660
+    },
+    {
+      "epoch": 2.389189189189189,
+      "grad_norm": 1.7701921715064215,
+      "learning_rate": 1.600297296594643e-05,
+      "loss": 0.6604,
+      "step": 663
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.6556840871349028,
+      "learning_rate": 1.5901105558537472e-05,
+      "loss": 0.6775,
+      "step": 666
+    },
+    {
+      "epoch": 2.410810810810811,
+      "grad_norm": 1.734110836750224,
+      "learning_rate": 1.579919642417281e-05,
+      "loss": 0.6482,
+      "step": 669
+    },
+    {
+      "epoch": 2.4216216216216218,
+      "grad_norm": 2.000655482106033,
+      "learning_rate": 1.569725028189772e-05,
+      "loss": 0.648,
+      "step": 672
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 1.7669642313010707,
+      "learning_rate": 1.5595271852471204e-05,
+      "loss": 0.6548,
+      "step": 675
+    },
+    {
+      "epoch": 2.443243243243243,
+      "grad_norm": 1.7114555298061667,
+      "learning_rate": 1.5493265858147335e-05,
+      "loss": 0.6291,
+      "step": 678
+    },
+    {
+      "epoch": 2.454054054054054,
+      "grad_norm": 1.982145197600375,
+      "learning_rate": 1.5391237022456636e-05,
+      "loss": 0.6648,
+      "step": 681
+    },
+    {
+      "epoch": 2.464864864864865,
+      "grad_norm": 2.057868578472174,
+      "learning_rate": 1.5289190069987332e-05,
+      "loss": 0.652,
+      "step": 684
+    },
+    {
+      "epoch": 2.4756756756756757,
+      "grad_norm": 1.6966492734095149,
+      "learning_rate": 1.5187129726166565e-05,
+      "loss": 0.6524,
+      "step": 687
+    },
+    {
+      "epoch": 2.4864864864864864,
+      "grad_norm": 1.7126379411947121,
+      "learning_rate": 1.5085060717041585e-05,
+      "loss": 0.6691,
+      "step": 690
+    },
+    {
+      "epoch": 2.4972972972972975,
+      "grad_norm": 2.027436021235288,
+      "learning_rate": 1.4982987769060898e-05,
+      "loss": 0.6551,
+      "step": 693
+    },
+    {
+      "epoch": 2.5081081081081082,
+      "grad_norm": 1.856345058930321,
+      "learning_rate": 1.4880915608855402e-05,
+      "loss": 0.6596,
+      "step": 696
+    },
+    {
+      "epoch": 2.518918918918919,
+      "grad_norm": 1.8317958549352111,
+      "learning_rate": 1.477884896301953e-05,
+      "loss": 0.6283,
+      "step": 699
+    },
+    {
+      "epoch": 2.5297297297297296,
+      "grad_norm": 1.7233177960794333,
+      "learning_rate": 1.467679255789234e-05,
+      "loss": 0.659,
+      "step": 702
+    },
+    {
+      "epoch": 2.5405405405405403,
+      "grad_norm": 1.70587685226235,
+      "learning_rate": 1.4574751119338703e-05,
+      "loss": 0.6375,
+      "step": 705
+    },
+    {
+      "epoch": 2.5513513513513515,
+      "grad_norm": 1.8655585555708385,
+      "learning_rate": 1.4472729372530432e-05,
+      "loss": 0.6242,
+      "step": 708
+    },
+    {
+      "epoch": 2.562162162162162,
+      "grad_norm": 1.8001992070479,
+      "learning_rate": 1.4370732041727495e-05,
+      "loss": 0.643,
+      "step": 711
+    },
+    {
+      "epoch": 2.572972972972973,
+      "grad_norm": 1.848601528720487,
+      "learning_rate": 1.426876385005922e-05,
+      "loss": 0.653,
+      "step": 714
+    },
+    {
+      "epoch": 2.583783783783784,
+      "grad_norm": 1.7058353790178475,
+      "learning_rate": 1.4166829519305628e-05,
+      "loss": 0.6189,
+      "step": 717
+    },
+    {
+      "epoch": 2.5945945945945947,
+      "grad_norm": 1.7284279167710883,
+      "learning_rate": 1.406493376967876e-05,
+      "loss": 0.6447,
+      "step": 720
+    },
+    {
+      "epoch": 2.6054054054054054,
+      "grad_norm": 1.9360862264128509,
+      "learning_rate": 1.396308131960409e-05,
+      "loss": 0.6396,
+      "step": 723
+    },
+    {
+      "epoch": 2.616216216216216,
+      "grad_norm": 1.6785593995242742,
+      "learning_rate": 1.386127688550206e-05,
+      "loss": 0.6305,
+      "step": 726
+    },
+    {
+      "epoch": 2.627027027027027,
+      "grad_norm": 1.7901370985866867,
+      "learning_rate": 1.3759525181569663e-05,
+      "loss": 0.6379,
+      "step": 729
+    },
+    {
+      "epoch": 2.637837837837838,
+      "grad_norm": 1.7497083646634908,
+      "learning_rate": 1.3657830919562151e-05,
+      "loss": 0.6252,
+      "step": 732
+    },
+    {
+      "epoch": 2.6486486486486487,
+      "grad_norm": 1.8186530224800674,
+      "learning_rate": 1.3556198808574828e-05,
+      "loss": 0.6751,
+      "step": 735
+    },
+    {
+      "epoch": 2.6594594594594594,
+      "grad_norm": 1.7289128215137377,
+      "learning_rate": 1.3454633554825029e-05,
+      "loss": 0.6467,
+      "step": 738
+    },
+    {
+      "epoch": 2.6702702702702705,
+      "grad_norm": 1.7639526554500256,
+      "learning_rate": 1.335313986143416e-05,
+      "loss": 0.6166,
+      "step": 741
+    },
+    {
+      "epoch": 2.6810810810810812,
+      "grad_norm": 1.7186641679091503,
+      "learning_rate": 1.3251722428209933e-05,
+      "loss": 0.6845,
+      "step": 744
+    },
+    {
+      "epoch": 2.691891891891892,
+      "grad_norm": 1.6965540327042066,
+      "learning_rate": 1.3150385951428714e-05,
+      "loss": 0.6487,
+      "step": 747
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 1.8567952974204969,
+      "learning_rate": 1.3049135123618073e-05,
+      "loss": 0.6457,
+      "step": 750
+    },
+    {
+      "epoch": 2.7135135135135133,
+      "grad_norm": 1.6295081249921362,
+      "learning_rate": 1.2947974633339499e-05,
+      "loss": 0.6445,
+      "step": 753
+    },
+    {
+      "epoch": 2.7243243243243245,
+      "grad_norm": 1.7231568913626358,
+      "learning_rate": 1.2846909164971244e-05,
+      "loss": 0.6434,
+      "step": 756
+    },
+    {
+      "epoch": 2.735135135135135,
+      "grad_norm": 1.8455193518645283,
+      "learning_rate": 1.2745943398491462e-05,
+      "loss": 0.65,
+      "step": 759
+    },
+    {
+      "epoch": 2.745945945945946,
+      "grad_norm": 1.827106966674069,
+      "learning_rate": 1.2645082009261468e-05,
+      "loss": 0.6628,
+      "step": 762
+    },
+    {
+      "epoch": 2.756756756756757,
+      "grad_norm": 1.7633688689382077,
+      "learning_rate": 1.254432966780924e-05,
+      "loss": 0.6491,
+      "step": 765
+    },
+    {
+      "epoch": 2.7675675675675677,
+      "grad_norm": 1.7284101689900349,
+      "learning_rate": 1.2443691039613128e-05,
+      "loss": 0.6258,
+      "step": 768
+    },
+    {
+      "epoch": 2.7783783783783784,
+      "grad_norm": 1.87274147264611,
+      "learning_rate": 1.2343170784885859e-05,
+      "loss": 0.6476,
+      "step": 771
+    },
+    {
+      "epoch": 2.789189189189189,
+      "grad_norm": 1.6928834129022787,
+      "learning_rate": 1.2242773558358701e-05,
+      "loss": 0.638,
+      "step": 774
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.7838050014292766,
+      "learning_rate": 1.2142504009065914e-05,
+      "loss": 0.6402,
+      "step": 777
+    },
+    {
+      "epoch": 2.810810810810811,
+      "grad_norm": 1.7473000738048472,
+      "learning_rate": 1.2042366780129507e-05,
+      "loss": 0.615,
+      "step": 780
+    },
+    {
+      "epoch": 2.8216216216216217,
+      "grad_norm": 1.8638020286903605,
+      "learning_rate": 1.1942366508544195e-05,
+      "loss": 0.6425,
+      "step": 783
+    },
+    {
+      "epoch": 2.8324324324324324,
+      "grad_norm": 1.874577580434278,
+      "learning_rate": 1.1842507824962694e-05,
+      "loss": 0.6504,
+      "step": 786
+    },
+    {
+      "epoch": 2.8432432432432435,
+      "grad_norm": 1.755404683062205,
+      "learning_rate": 1.1742795353481291e-05,
+      "loss": 0.6541,
+      "step": 789
+    },
+    {
+      "epoch": 2.854054054054054,
+      "grad_norm": 1.8072551565675472,
+      "learning_rate": 1.1643233711425716e-05,
+      "loss": 0.6683,
+      "step": 792
+    },
+    {
+      "epoch": 2.864864864864865,
+      "grad_norm": 1.6667276846485022,
+      "learning_rate": 1.1543827509137329e-05,
+      "loss": 0.6486,
+      "step": 795
+    },
+    {
+      "epoch": 2.8756756756756756,
+      "grad_norm": 1.688942735670296,
+      "learning_rate": 1.144458134975964e-05,
+      "loss": 0.6652,
+      "step": 798
+    },
+    {
+      "epoch": 2.8864864864864863,
+      "grad_norm": 1.753840610632178,
+      "learning_rate": 1.1345499829025136e-05,
+      "loss": 0.6634,
+      "step": 801
+    },
+    {
+      "epoch": 2.8972972972972975,
+      "grad_norm": 1.9607814129942556,
+      "learning_rate": 1.1246587535042492e-05,
+      "loss": 0.6426,
+      "step": 804
+    },
+    {
+      "epoch": 2.908108108108108,
+      "grad_norm": 1.813335779829059,
+      "learning_rate": 1.1147849048084105e-05,
+      "loss": 0.6315,
+      "step": 807
+    },
+    {
+      "epoch": 2.918918918918919,
+      "grad_norm": 1.7402704693393687,
+      "learning_rate": 1.1049288940373972e-05,
+      "loss": 0.6228,
+      "step": 810
+    },
+    {
+      "epoch": 2.92972972972973,
+      "grad_norm": 1.7680419333729458,
+      "learning_rate": 1.0950911775876014e-05,
+      "loss": 0.6,
+      "step": 813
+    },
+    {
+      "epoch": 2.9405405405405407,
+      "grad_norm": 1.843223644664368,
+      "learning_rate": 1.0852722110082693e-05,
+      "loss": 0.6476,
+      "step": 816
+    },
+    {
+      "epoch": 2.9513513513513514,
+      "grad_norm": 1.7069834663839671,
+      "learning_rate": 1.0754724489804098e-05,
+      "loss": 0.6593,
+      "step": 819
+    },
+    {
+      "epoch": 2.962162162162162,
+      "grad_norm": 1.734691145206824,
+      "learning_rate": 1.0656923452957354e-05,
+      "loss": 0.6252,
+      "step": 822
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 1.6530132045637638,
+      "learning_rate": 1.0559323528356542e-05,
+      "loss": 0.6218,
+      "step": 825
+    },
+    {
+      "epoch": 2.983783783783784,
+      "grad_norm": 1.7766789557037792,
+      "learning_rate": 1.0461929235502952e-05,
+      "loss": 0.6494,
+      "step": 828
+    },
+    {
+      "epoch": 2.9945945945945946,
+      "grad_norm": 1.777411804411515,
+      "learning_rate": 1.036474508437579e-05,
+      "loss": 0.6409,
+      "step": 831
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 1385,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 833,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 151014030311424.0,
+  "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 sha256:9032d21f71645c8c878ced111a5ac48ae0883a303c373d3216d895098f5ec20d
+size 7096

zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/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 . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, 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_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``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
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+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_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    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_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)