add: add model weight files

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/apdcephfs_qy3/share_1443437/nlp_common/LLM_Models/Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.0.dev0"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eddbaab0dd87907a3664207ba1d5d44ebd3f567707242fd23794d16385325379
+size 4865522496

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513c8486242d140f97fa1d61980b2f8ccff1da1e2b11daf8cea0dc1437a92e08
+size 4907529424

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9478ff981d155ded2d25bf19acbb98d719a618fc7456ce36ce0e8b9b918e0182
+size 4907529456

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b64667576734edac02f7f7c42259933a215fd46414d992e0d6a3ed05543a9b
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22747854662c5c6b165b3017acfd73f1a66e165884fa7dbdca1b726fadc624b6
+size 4907496272

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24495564800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.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:bc9dbe3641a6ae5b4c7bb59a1b47c80bf7d86a0f2ae513de42b04233e8400d76
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": 44.04393707727108,
+      "learning_rate": 2.9999066991504905e-05,
+      "loss": 2.3711,
+      "step": 3
+    },
+    {
+      "epoch": 0.021621621621621623,
+      "grad_norm": 31.04171552882201,
+      "learning_rate": 2.9996268082086924e-05,
+      "loss": 4.159,
+      "step": 6
+    },
+    {
+      "epoch": 0.032432432432432434,
+      "grad_norm": 11.54576214967521,
+      "learning_rate": 2.9991603619933566e-05,
+      "loss": 1.9733,
+      "step": 9
+    },
+    {
+      "epoch": 0.043243243243243246,
+      "grad_norm": 7.08841552325599,
+      "learning_rate": 2.9985074185309204e-05,
+      "loss": 1.7978,
+      "step": 12
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 5.949508626432288,
+      "learning_rate": 2.99766805904829e-05,
+      "loss": 1.7347,
+      "step": 15
+    },
+    {
+      "epoch": 0.06486486486486487,
+      "grad_norm": 6.168616775238258,
+      "learning_rate": 2.9966423879627356e-05,
+      "loss": 1.6033,
+      "step": 18
+    },
+    {
+      "epoch": 0.07567567567567568,
+      "grad_norm": 5.728079542384497,
+      "learning_rate": 2.9954305328689024e-05,
+      "loss": 1.7134,
+      "step": 21
+    },
+    {
+      "epoch": 0.08648648648648649,
+      "grad_norm": 6.284326561040228,
+      "learning_rate": 2.9940326445229367e-05,
+      "loss": 1.6933,
+      "step": 24
+    },
+    {
+      "epoch": 0.0972972972972973,
+      "grad_norm": 6.92658975011714,
+      "learning_rate": 2.9924488968237316e-05,
+      "loss": 1.5923,
+      "step": 27
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 6.538508694879061,
+      "learning_rate": 2.9906794867912953e-05,
+      "loss": 1.6931,
+      "step": 30
+    },
+    {
+      "epoch": 0.11891891891891893,
+      "grad_norm": 4.685530306007965,
+      "learning_rate": 2.98872463454224e-05,
+      "loss": 1.6559,
+      "step": 33
+    },
+    {
+      "epoch": 0.12972972972972974,
+      "grad_norm": 5.65503266442286,
+      "learning_rate": 2.9865845832623993e-05,
+      "loss": 1.6982,
+      "step": 36
+    },
+    {
+      "epoch": 0.14054054054054055,
+      "grad_norm": 4.886380857119004,
+      "learning_rate": 2.9842595991765766e-05,
+      "loss": 1.6503,
+      "step": 39
+    },
+    {
+      "epoch": 0.15135135135135136,
+      "grad_norm": 5.026086310034092,
+      "learning_rate": 2.981749971515426e-05,
+      "loss": 1.632,
+      "step": 42
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 4.795570770299284,
+      "learning_rate": 2.9790560124794702e-05,
+      "loss": 1.6824,
+      "step": 45
+    },
+    {
+      "epoch": 0.17297297297297298,
+      "grad_norm": 4.756143563325781,
+      "learning_rate": 2.976178057200266e-05,
+      "loss": 1.6694,
+      "step": 48
+    },
+    {
+      "epoch": 0.1837837837837838,
+      "grad_norm": 5.364943432581566,
+      "learning_rate": 2.9731164636987088e-05,
+      "loss": 1.6659,
+      "step": 51
+    },
+    {
+      "epoch": 0.1945945945945946,
+      "grad_norm": 5.181051766279552,
+      "learning_rate": 2.9698716128404985e-05,
+      "loss": 1.6443,
+      "step": 54
+    },
+    {
+      "epoch": 0.20540540540540542,
+      "grad_norm": 4.828479392346181,
+      "learning_rate": 2.9664439082887568e-05,
+      "loss": 1.6519,
+      "step": 57
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 5.824361936201152,
+      "learning_rate": 2.9628337764538135e-05,
+      "loss": 1.6532,
+      "step": 60
+    },
+    {
+      "epoch": 0.22702702702702704,
+      "grad_norm": 6.393887712988006,
+      "learning_rate": 2.9590416664401566e-05,
+      "loss": 1.6409,
+      "step": 63
+    },
+    {
+      "epoch": 0.23783783783783785,
+      "grad_norm": 5.8650966692501765,
+      "learning_rate": 2.955068049990568e-05,
+      "loss": 1.6105,
+      "step": 66
+    },
+    {
+      "epoch": 0.24864864864864866,
+      "grad_norm": 4.755849083042293,
+      "learning_rate": 2.9509134214274343e-05,
+      "loss": 1.6618,
+      "step": 69
+    },
+    {
+      "epoch": 0.2594594594594595,
+      "grad_norm": 3.9789106042521962,
+      "learning_rate": 2.9465782975912553e-05,
+      "loss": 1.6645,
+      "step": 72
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 4.592578050100414,
+      "learning_rate": 2.942063217776346e-05,
+      "loss": 1.605,
+      "step": 75
+    },
+    {
+      "epoch": 0.2810810810810811,
+      "grad_norm": 4.299733571350802,
+      "learning_rate": 2.9373687436637492e-05,
+      "loss": 1.6233,
+      "step": 78
+    },
+    {
+      "epoch": 0.2918918918918919,
+      "grad_norm": 4.585181401202116,
+      "learning_rate": 2.9324954592513626e-05,
+      "loss": 1.6587,
+      "step": 81
+    },
+    {
+      "epoch": 0.3027027027027027,
+      "grad_norm": 4.530135718622418,
+      "learning_rate": 2.927443970781287e-05,
+      "loss": 1.6333,
+      "step": 84
+    },
+    {
+      "epoch": 0.31351351351351353,
+      "grad_norm": 5.349009947479682,
+      "learning_rate": 2.9222149066644088e-05,
+      "loss": 1.6431,
+      "step": 87
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 4.266181060344957,
+      "learning_rate": 2.916808917402228e-05,
+      "loss": 1.598,
+      "step": 90
+    },
+    {
+      "epoch": 0.33513513513513515,
+      "grad_norm": 4.628674419343668,
+      "learning_rate": 2.911226675505932e-05,
+      "loss": 1.6375,
+      "step": 93
+    },
+    {
+      "epoch": 0.34594594594594597,
+      "grad_norm": 5.058644550344611,
+      "learning_rate": 2.905468875412735e-05,
+      "loss": 1.6427,
+      "step": 96
+    },
+    {
+      "epoch": 0.3567567567567568,
+      "grad_norm": 4.417115318512762,
+      "learning_rate": 2.8995362333994906e-05,
+      "loss": 1.6333,
+      "step": 99
+    },
+    {
+      "epoch": 0.3675675675675676,
+      "grad_norm": 4.0811273644284345,
+      "learning_rate": 2.8934294874935848e-05,
+      "loss": 1.5855,
+      "step": 102
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 3.962543949681069,
+      "learning_rate": 2.887149397381126e-05,
+      "loss": 1.6171,
+      "step": 105
+    },
+    {
+      "epoch": 0.3891891891891892,
+      "grad_norm": 3.934001274285887,
+      "learning_rate": 2.8806967443124372e-05,
+      "loss": 1.5538,
+      "step": 108
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.891305018487301,
+      "learning_rate": 2.8740723310048682e-05,
+      "loss": 1.6476,
+      "step": 111
+    },
+    {
+      "epoch": 0.41081081081081083,
+      "grad_norm": 4.553656766898869,
+      "learning_rate": 2.8672769815429385e-05,
+      "loss": 1.5889,
+      "step": 114
+    },
+    {
+      "epoch": 0.42162162162162165,
+      "grad_norm": 4.450034079395778,
+      "learning_rate": 2.860311541275818e-05,
+      "loss": 1.5896,
+      "step": 117
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 3.9485209950285274,
+      "learning_rate": 2.8531768767121656e-05,
+      "loss": 1.6198,
+      "step": 120
+    },
+    {
+      "epoch": 0.44324324324324327,
+      "grad_norm": 4.35512448284715,
+      "learning_rate": 2.845873875412335e-05,
+      "loss": 1.6443,
+      "step": 123
+    },
+    {
+      "epoch": 0.4540540540540541,
+      "grad_norm": 4.651266887881564,
+      "learning_rate": 2.838403445877958e-05,
+      "loss": 1.6542,
+      "step": 126
+    },
+    {
+      "epoch": 0.4648648648648649,
+      "grad_norm": 4.5294288157069,
+      "learning_rate": 2.8307665174389323e-05,
+      "loss": 1.655,
+      "step": 129
+    },
+    {
+      "epoch": 0.4756756756756757,
+      "grad_norm": 4.104985239339571,
+      "learning_rate": 2.822964040137805e-05,
+      "loss": 1.6827,
+      "step": 132
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 3.7948515475231286,
+      "learning_rate": 2.8149969846115894e-05,
+      "loss": 1.6333,
+      "step": 135
+    },
+    {
+      "epoch": 0.4972972972972973,
+      "grad_norm": 4.449225329061536,
+      "learning_rate": 2.8068663419710182e-05,
+      "loss": 1.6185,
+      "step": 138
+    },
+    {
+      "epoch": 0.5081081081081081,
+      "grad_norm": 4.391987231579949,
+      "learning_rate": 2.7985731236772448e-05,
+      "loss": 1.6078,
+      "step": 141
+    },
+    {
+      "epoch": 0.518918918918919,
+      "grad_norm": 4.982415169833182,
+      "learning_rate": 2.7901183614160185e-05,
+      "loss": 1.6529,
+      "step": 144
+    },
+    {
+      "epoch": 0.5297297297297298,
+      "grad_norm": 4.176595151214056,
+      "learning_rate": 2.7815031069693412e-05,
+      "loss": 1.6073,
+      "step": 147
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 4.3206148554703105,
+      "learning_rate": 2.7727284320846246e-05,
+      "loss": 1.5561,
+      "step": 150
+    },
+    {
+      "epoch": 0.5513513513513514,
+      "grad_norm": 4.424758608775709,
+      "learning_rate": 2.7637954283413632e-05,
+      "loss": 1.6253,
+      "step": 153
+    },
+    {
+      "epoch": 0.5621621621621622,
+      "grad_norm": 5.349711813640235,
+      "learning_rate": 2.75470520701534e-05,
+      "loss": 1.7059,
+      "step": 156
+    },
+    {
+      "epoch": 0.572972972972973,
+      "grad_norm": 4.578654891344146,
+      "learning_rate": 2.7454588989403858e-05,
+      "loss": 1.6107,
+      "step": 159
+    },
+    {
+      "epoch": 0.5837837837837838,
+      "grad_norm": 40.22880683574773,
+      "learning_rate": 2.7360576543676972e-05,
+      "loss": 1.6278,
+      "step": 162
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 4.155039894851776,
+      "learning_rate": 2.7265026428227476e-05,
+      "loss": 1.6301,
+      "step": 165
+    },
+    {
+      "epoch": 0.6054054054054054,
+      "grad_norm": 4.159866031946415,
+      "learning_rate": 2.7167950529597963e-05,
+      "loss": 1.5342,
+      "step": 168
+    },
+    {
+      "epoch": 0.6162162162162163,
+      "grad_norm": 4.087141493968059,
+      "learning_rate": 2.706936092414018e-05,
+      "loss": 1.6033,
+      "step": 171
+    },
+    {
+      "epoch": 0.6270270270270271,
+      "grad_norm": 3.825646270675215,
+      "learning_rate": 2.696926987651271e-05,
+      "loss": 1.5288,
+      "step": 174
+    },
+    {
+      "epoch": 0.6378378378378379,
+      "grad_norm": 3.917523159059879,
+      "learning_rate": 2.686768983815526e-05,
+      "loss": 1.6363,
+      "step": 177
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 4.202629239471907,
+      "learning_rate": 2.676463344573965e-05,
+      "loss": 1.6052,
+      "step": 180
+    },
+    {
+      "epoch": 0.6594594594594595,
+      "grad_norm": 3.6368092847747304,
+      "learning_rate": 2.666011351959783e-05,
+      "loss": 1.6309,
+      "step": 183
+    },
+    {
+      "epoch": 0.6702702702702703,
+      "grad_norm": 4.253168243144118,
+      "learning_rate": 2.6554143062126995e-05,
+      "loss": 1.5592,
+      "step": 186
+    },
+    {
+      "epoch": 0.6810810810810811,
+      "grad_norm": 4.995354779998164,
+      "learning_rate": 2.6446735256172092e-05,
+      "loss": 1.6303,
+      "step": 189
+    },
+    {
+      "epoch": 0.6918918918918919,
+      "grad_norm": 4.421549411402136,
+      "learning_rate": 2.6337903463385836e-05,
+      "loss": 1.5769,
+      "step": 192
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 4.32615026522547,
+      "learning_rate": 2.6227661222566516e-05,
+      "loss": 1.613,
+      "step": 195
+    },
+    {
+      "epoch": 0.7135135135135136,
+      "grad_norm": 3.8575639988103836,
+      "learning_rate": 2.6116022247973773e-05,
+      "loss": 1.5844,
+      "step": 198
+    },
+    {
+      "epoch": 0.7243243243243244,
+      "grad_norm": 3.7279832633133028,
+      "learning_rate": 2.6003000427622484e-05,
+      "loss": 1.5301,
+      "step": 201
+    },
+    {
+      "epoch": 0.7351351351351352,
+      "grad_norm": 4.190711163922663,
+      "learning_rate": 2.5888609821555127e-05,
+      "loss": 1.592,
+      "step": 204
+    },
+    {
+      "epoch": 0.745945945945946,
+      "grad_norm": 4.733000892445367,
+      "learning_rate": 2.577286466009266e-05,
+      "loss": 1.6574,
+      "step": 207
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 4.577219211132897,
+      "learning_rate": 2.5655779342064276e-05,
+      "loss": 1.6289,
+      "step": 210
+    },
+    {
+      "epoch": 0.7675675675675676,
+      "grad_norm": 4.048131970531039,
+      "learning_rate": 2.553736843301615e-05,
+      "loss": 1.6169,
+      "step": 213
+    },
+    {
+      "epoch": 0.7783783783783784,
+      "grad_norm": 4.018546715630257,
+      "learning_rate": 2.5417646663399502e-05,
+      "loss": 1.5489,
+      "step": 216
+    },
+    {
+      "epoch": 0.7891891891891892,
+      "grad_norm": 3.7010313992210992,
+      "learning_rate": 2.529662892673806e-05,
+      "loss": 1.5596,
+      "step": 219
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.557965597883243,
+      "learning_rate": 2.5174330277775354e-05,
+      "loss": 1.6145,
+      "step": 222
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 4.181549208740728,
+      "learning_rate": 2.5050765930601836e-05,
+      "loss": 1.5339,
+      "step": 225
+    },
+    {
+      "epoch": 0.8216216216216217,
+      "grad_norm": 3.7892758830012823,
+      "learning_rate": 2.4925951256762254e-05,
+      "loss": 1.5862,
+      "step": 228
+    },
+    {
+      "epoch": 0.8324324324324325,
+      "grad_norm": 3.6130747678919666,
+      "learning_rate": 2.4799901783343407e-05,
+      "loss": 1.4857,
+      "step": 231
+    },
+    {
+      "epoch": 0.8432432432432433,
+      "grad_norm": 3.639537345617851,
+      "learning_rate": 2.467263319104256e-05,
+      "loss": 1.5902,
+      "step": 234
+    },
+    {
+      "epoch": 0.8540540540540541,
+      "grad_norm": 4.0474919753332035,
+      "learning_rate": 2.4544161312216752e-05,
+      "loss": 1.5395,
+      "step": 237
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 3.800979434984059,
+      "learning_rate": 2.441450212891323e-05,
+      "loss": 1.5284,
+      "step": 240
+    },
+    {
+      "epoch": 0.8756756756756757,
+      "grad_norm": 3.3611120493742983,
+      "learning_rate": 2.4283671770881256e-05,
+      "loss": 1.515,
+      "step": 243
+    },
+    {
+      "epoch": 0.8864864864864865,
+      "grad_norm": 3.459228078638404,
+      "learning_rate": 2.415168651356556e-05,
+      "loss": 1.5745,
+      "step": 246
+    },
+    {
+      "epoch": 0.8972972972972973,
+      "grad_norm": 3.6185129562881513,
+      "learning_rate": 2.4018562776081643e-05,
+      "loss": 1.5989,
+      "step": 249
+    },
+    {
+      "epoch": 0.9081081081081082,
+      "grad_norm": 4.499909371969758,
+      "learning_rate": 2.388431711917324e-05,
+      "loss": 1.5609,
+      "step": 252
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 3.6576864938242832,
+      "learning_rate": 2.3748966243152127e-05,
+      "loss": 1.5623,
+      "step": 255
+    },
+    {
+      "epoch": 0.9297297297297298,
+      "grad_norm": 4.261199238023545,
+      "learning_rate": 2.3612526985820586e-05,
+      "loss": 1.5523,
+      "step": 258
+    },
+    {
+      "epoch": 0.9405405405405406,
+      "grad_norm": 4.730374719738293,
+      "learning_rate": 2.347501632037678e-05,
+      "loss": 1.5813,
+      "step": 261
+    },
+    {
+      "epoch": 0.9513513513513514,
+      "grad_norm": 3.7110704143642503,
+      "learning_rate": 2.333645135330324e-05,
+      "loss": 1.4888,
+      "step": 264
+    },
+    {
+      "epoch": 0.9621621621621622,
+      "grad_norm": 3.481005791064881,
+      "learning_rate": 2.3196849322238816e-05,
+      "loss": 1.6186,
+      "step": 267
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 3.9410070667987913,
+      "learning_rate": 2.3056227593834306e-05,
+      "loss": 1.5343,
+      "step": 270
+    },
+    {
+      "epoch": 0.9837837837837838,
+      "grad_norm": 3.73687483401855,
+      "learning_rate": 2.291460366159199e-05,
+      "loss": 1.527,
+      "step": 273
+    },
+    {
+      "epoch": 0.9945945945945946,
+      "grad_norm": 3.636935348418019,
+      "learning_rate": 2.277199514368947e-05,
+      "loss": 1.5228,
+      "step": 276
+    },
+    {
+      "epoch": 1.0054054054054054,
+      "grad_norm": 3.5028224113856457,
+      "learning_rate": 2.2628419780787887e-05,
+      "loss": 1.3043,
+      "step": 279
+    },
+    {
+      "epoch": 1.0162162162162163,
+      "grad_norm": 3.2714761796276455,
+      "learning_rate": 2.2483895433825023e-05,
+      "loss": 1.0507,
+      "step": 282
+    },
+    {
+      "epoch": 1.027027027027027,
+      "grad_norm": 3.180825722720309,
+      "learning_rate": 2.2338440081793332e-05,
+      "loss": 1.0155,
+      "step": 285
+    },
+    {
+      "epoch": 1.037837837837838,
+      "grad_norm": 2.9167211293609894,
+      "learning_rate": 2.2192071819503365e-05,
+      "loss": 1.0087,
+      "step": 288
+    },
+    {
+      "epoch": 1.0486486486486486,
+      "grad_norm": 3.1930797413555077,
+      "learning_rate": 2.2044808855332743e-05,
+      "loss": 0.9847,
+      "step": 291
+    },
+    {
+      "epoch": 1.0594594594594595,
+      "grad_norm": 3.0743072086936474,
+      "learning_rate": 2.1896669508961002e-05,
+      "loss": 1.0024,
+      "step": 294
+    },
+    {
+      "epoch": 1.0702702702702702,
+      "grad_norm": 3.3931402915538613,
+      "learning_rate": 2.1747672209090627e-05,
+      "loss": 1.0063,
+      "step": 297
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 3.427840497426894,
+      "learning_rate": 2.1597835491154495e-05,
+      "loss": 0.9924,
+      "step": 300
+    },
+    {
+      "epoch": 1.0918918918918918,
+      "grad_norm": 3.209752499479298,
+      "learning_rate": 2.1447177995010024e-05,
+      "loss": 1.0114,
+      "step": 303
+    },
+    {
+      "epoch": 1.1027027027027028,
+      "grad_norm": 2.9188122615255487,
+      "learning_rate": 2.1295718462620383e-05,
+      "loss": 0.9348,
+      "step": 306
+    },
+    {
+      "epoch": 1.1135135135135135,
+      "grad_norm": 3.2169410708018464,
+      "learning_rate": 2.1143475735722965e-05,
+      "loss": 0.9456,
+      "step": 309
+    },
+    {
+      "epoch": 1.1243243243243244,
+      "grad_norm": 3.2550857985332815,
+      "learning_rate": 2.099046875348543e-05,
+      "loss": 0.9704,
+      "step": 312
+    },
+    {
+      "epoch": 1.135135135135135,
+      "grad_norm": 3.200798957813093,
+      "learning_rate": 2.0836716550149685e-05,
+      "loss": 1.0187,
+      "step": 315
+    },
+    {
+      "epoch": 1.145945945945946,
+      "grad_norm": 3.026699827485341,
+      "learning_rate": 2.068223825266397e-05,
+      "loss": 0.9959,
+      "step": 318
+    },
+    {
+      "epoch": 1.1567567567567567,
+      "grad_norm": 2.966340597816754,
+      "learning_rate": 2.0527053078303463e-05,
+      "loss": 0.9672,
+      "step": 321
+    },
+    {
+      "epoch": 1.1675675675675676,
+      "grad_norm": 3.4796215218810578,
+      "learning_rate": 2.0371180332279642e-05,
+      "loss": 0.9631,
+      "step": 324
+    },
+    {
+      "epoch": 1.1783783783783783,
+      "grad_norm": 2.9446475013457203,
+      "learning_rate": 2.0214639405338653e-05,
+      "loss": 0.9922,
+      "step": 327
+    },
+    {
+      "epoch": 1.1891891891891893,
+      "grad_norm": 3.0107017661224447,
+      "learning_rate": 2.0057449771349123e-05,
+      "loss": 0.9846,
+      "step": 330
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.1589173902147203,
+      "learning_rate": 1.989963098487957e-05,
+      "loss": 0.9945,
+      "step": 333
+    },
+    {
+      "epoch": 1.2108108108108109,
+      "grad_norm": 3.291095419768011,
+      "learning_rate": 1.9741202678765785e-05,
+      "loss": 1.0006,
+      "step": 336
+    },
+    {
+      "epoch": 1.2216216216216216,
+      "grad_norm": 3.0439357766975768,
+      "learning_rate": 1.9582184561668496e-05,
+      "loss": 1.0247,
+      "step": 339
+    },
+    {
+      "epoch": 1.2324324324324325,
+      "grad_norm": 2.7398517472244133,
+      "learning_rate": 1.942259641562159e-05,
+      "loss": 1.0129,
+      "step": 342
+    },
+    {
+      "epoch": 1.2432432432432432,
+      "grad_norm": 3.0466059717106098,
+      "learning_rate": 1.9262458093571193e-05,
+      "loss": 1.0257,
+      "step": 345
+    },
+    {
+      "epoch": 1.2540540540540541,
+      "grad_norm": 2.8458132575753714,
+      "learning_rate": 1.9101789516905953e-05,
+      "loss": 0.9715,
+      "step": 348
+    },
+    {
+      "epoch": 1.2648648648648648,
+      "grad_norm": 2.8328426905654656,
+      "learning_rate": 1.8940610672978803e-05,
+      "loss": 0.961,
+      "step": 351
+    },
+    {
+      "epoch": 1.2756756756756757,
+      "grad_norm": 3.030835646521939,
+      "learning_rate": 1.8778941612620482e-05,
+      "loss": 0.9884,
+      "step": 354
+    },
+    {
+      "epoch": 1.2864864864864864,
+      "grad_norm": 2.8633899892085024,
+      "learning_rate": 1.8616802447645223e-05,
+      "loss": 0.9937,
+      "step": 357
+    },
+    {
+      "epoch": 1.2972972972972974,
+      "grad_norm": 3.338996158976475,
+      "learning_rate": 1.8454213348348797e-05,
+      "loss": 0.9809,
+      "step": 360
+    },
+    {
+      "epoch": 1.308108108108108,
+      "grad_norm": 2.924814513226331,
+      "learning_rate": 1.8291194540999322e-05,
+      "loss": 0.9526,
+      "step": 363
+    },
+    {
+      "epoch": 1.318918918918919,
+      "grad_norm": 3.090470952947,
+      "learning_rate": 1.8127766305321072e-05,
+      "loss": 0.9912,
+      "step": 366
+    },
+    {
+      "epoch": 1.3297297297297297,
+      "grad_norm": 2.9540976533352867,
+      "learning_rate": 1.7963948971971686e-05,
+      "loss": 0.9725,
+      "step": 369
+    },
+    {
+      "epoch": 1.3405405405405406,
+      "grad_norm": 2.9280101457384986,
+      "learning_rate": 1.7799762920012982e-05,
+      "loss": 0.9508,
+      "step": 372
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 3.129222083901634,
+      "learning_rate": 1.763522857437579e-05,
+      "loss": 0.9952,
+      "step": 375
+    },
+    {
+      "epoch": 1.3621621621621622,
+      "grad_norm": 3.3207813445482315,
+      "learning_rate": 1.747036640331908e-05,
+      "loss": 0.9778,
+      "step": 378
+    },
+    {
+      "epoch": 1.372972972972973,
+      "grad_norm": 2.941815984953935,
+      "learning_rate": 1.7305196915883662e-05,
+      "loss": 0.9922,
+      "step": 381
+    },
+    {
+      "epoch": 1.3837837837837839,
+      "grad_norm": 3.1943275224301475,
+      "learning_rate": 1.713974065934086e-05,
+      "loss": 0.9738,
+      "step": 384
+    },
+    {
+      "epoch": 1.3945945945945946,
+      "grad_norm": 2.9545782873135478,
+      "learning_rate": 1.6974018216636394e-05,
+      "loss": 0.9712,
+      "step": 387
+    },
+    {
+      "epoch": 1.4054054054054055,
+      "grad_norm": 2.832796057451163,
+      "learning_rate": 1.6808050203829845e-05,
+      "loss": 1.0121,
+      "step": 390
+    },
+    {
+      "epoch": 1.4162162162162162,
+      "grad_norm": 3.2139763823586196,
+      "learning_rate": 1.6641857267530003e-05,
+      "loss": 0.9702,
+      "step": 393
+    },
+    {
+      "epoch": 1.427027027027027,
+      "grad_norm": 3.3210065946822827,
+      "learning_rate": 1.6475460082326377e-05,
+      "loss": 1.0018,
+      "step": 396
+    },
+    {
+      "epoch": 1.4378378378378378,
+      "grad_norm": 3.166940843865695,
+      "learning_rate": 1.6308879348217293e-05,
+      "loss": 0.9959,
+      "step": 399
+    },
+    {
+      "epoch": 1.4486486486486487,
+      "grad_norm": 3.1486302485385878,
+      "learning_rate": 1.6142135788034743e-05,
+      "loss": 0.9477,
+      "step": 402
+    },
+    {
+      "epoch": 1.4594594594594594,
+      "grad_norm": 3.1328749208815547,
+      "learning_rate": 1.5975250144866492e-05,
+      "loss": 0.9854,
+      "step": 405
+    },
+    {
+      "epoch": 1.4702702702702704,
+      "grad_norm": 2.9503463010514035,
+      "learning_rate": 1.5808243179475568e-05,
+      "loss": 1.0001,
+      "step": 408
+    },
+    {
+      "epoch": 1.481081081081081,
+      "grad_norm": 2.8925905903725355,
+      "learning_rate": 1.564113566771764e-05,
+      "loss": 0.9475,
+      "step": 411
+    },
+    {
+      "epoch": 1.491891891891892,
+      "grad_norm": 3.2184062381528196,
+      "learning_rate": 1.547394839795645e-05,
+      "loss": 0.9862,
+      "step": 414
+    },
+    {
+      "epoch": 1.5027027027027027,
+      "grad_norm": 3.0205819182026077,
+      "learning_rate": 1.530670216847772e-05,
+      "loss": 0.9689,
+      "step": 417
+    },
+    {
+      "epoch": 1.5135135135135136,
+      "grad_norm": 2.886699137488658,
+      "learning_rate": 1.5139417784901836e-05,
+      "loss": 0.9578,
+      "step": 420
+    },
+    {
+      "epoch": 1.5243243243243243,
+      "grad_norm": 3.0019029659558494,
+      "learning_rate": 1.4972116057595592e-05,
+      "loss": 0.9526,
+      "step": 423
+    },
+    {
+      "epoch": 1.535135135135135,
+      "grad_norm": 3.141168035086649,
+      "learning_rate": 1.480481779908337e-05,
+      "loss": 0.9621,
+      "step": 426
+    },
+    {
+      "epoch": 1.545945945945946,
+      "grad_norm": 2.842053920465437,
+      "learning_rate": 1.463754382145802e-05,
+      "loss": 0.9821,
+      "step": 429
+    },
+    {
+      "epoch": 1.5567567567567568,
+      "grad_norm": 3.220671922556498,
+      "learning_rate": 1.4470314933791828e-05,
+      "loss": 0.9547,
+      "step": 432
+    },
+    {
+      "epoch": 1.5675675675675675,
+      "grad_norm": 2.9122625506605586,
+      "learning_rate": 1.430315193954783e-05,
+      "loss": 0.9678,
+      "step": 435
+    },
+    {
+      "epoch": 1.5783783783783782,
+      "grad_norm": 2.6568836209674274,
+      "learning_rate": 1.4136075633991864e-05,
+      "loss": 0.9566,
+      "step": 438
+    },
+    {
+      "epoch": 1.5891891891891892,
+      "grad_norm": 2.7282858715379077,
+      "learning_rate": 1.3969106801605577e-05,
+      "loss": 0.9195,
+      "step": 441
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.602059773028646,
+      "learning_rate": 1.3802266213500843e-05,
+      "loss": 0.955,
+      "step": 444
+    },
+    {
+      "epoch": 1.6108108108108108,
+      "grad_norm": 3.3786673839231423,
+      "learning_rate": 1.3635574624835798e-05,
+      "loss": 0.9645,
+      "step": 447
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 2.6986089589909,
+      "learning_rate": 1.3469052772232874e-05,
+      "loss": 0.98,
+      "step": 450
+    },
+    {
+      "epoch": 1.6324324324324324,
+      "grad_norm": 2.89235283174837,
+      "learning_rate": 1.3302721371199165e-05,
+      "loss": 0.9588,
+      "step": 453
+    },
+    {
+      "epoch": 1.6432432432432433,
+      "grad_norm": 2.935829812088402,
+      "learning_rate": 1.3136601113549349e-05,
+      "loss": 0.9354,
+      "step": 456
+    },
+    {
+      "epoch": 1.654054054054054,
+      "grad_norm": 2.737725384464134,
+      "learning_rate": 1.2970712664831644e-05,
+      "loss": 0.9574,
+      "step": 459
+    },
+    {
+      "epoch": 1.6648648648648647,
+      "grad_norm": 2.867513411111901,
+      "learning_rate": 1.2805076661756965e-05,
+      "loss": 0.9446,
+      "step": 462
+    },
+    {
+      "epoch": 1.6756756756756757,
+      "grad_norm": 2.787422977164954,
+      "learning_rate": 1.2639713709631709e-05,
+      "loss": 0.9558,
+      "step": 465
+    },
+    {
+      "epoch": 1.6864864864864866,
+      "grad_norm": 2.9076119130942026,
+      "learning_rate": 1.2474644379794421e-05,
+      "loss": 0.9286,
+      "step": 468
+    },
+    {
+      "epoch": 1.6972972972972973,
+      "grad_norm": 2.826910897786021,
+      "learning_rate": 1.2309889207056708e-05,
+      "loss": 0.9556,
+      "step": 471
+    },
+    {
+      "epoch": 1.708108108108108,
+      "grad_norm": 3.027330313518151,
+      "learning_rate": 1.2145468687148672e-05,
+      "loss": 0.9157,
+      "step": 474
+    },
+    {
+      "epoch": 1.718918918918919,
+      "grad_norm": 2.870766642781988,
+      "learning_rate": 1.1981403274169219e-05,
+      "loss": 0.9708,
+      "step": 477
+    },
+    {
+      "epoch": 1.7297297297297298,
+      "grad_norm": 2.745031713488,
+      "learning_rate": 1.1817713378041568e-05,
+      "loss": 0.9404,
+      "step": 480
+    },
+    {
+      "epoch": 1.7405405405405405,
+      "grad_norm": 2.8171111310049506,
+      "learning_rate": 1.1654419361974195e-05,
+      "loss": 0.9423,
+      "step": 483
+    },
+    {
+      "epoch": 1.7513513513513512,
+      "grad_norm": 2.8549039042787503,
+      "learning_rate": 1.1491541539927668e-05,
+      "loss": 0.951,
+      "step": 486
+    },
+    {
+      "epoch": 1.7621621621621621,
+      "grad_norm": 2.664120980356897,
+      "learning_rate": 1.1329100174087534e-05,
+      "loss": 0.9287,
+      "step": 489
+    },
+    {
+      "epoch": 1.772972972972973,
+      "grad_norm": 2.7039305514008096,
+      "learning_rate": 1.1167115472343693e-05,
+      "loss": 0.9584,
+      "step": 492
+    },
+    {
+      "epoch": 1.7837837837837838,
+      "grad_norm": 2.6778342659825025,
+      "learning_rate": 1.1005607585776527e-05,
+      "loss": 0.9151,
+      "step": 495
+    },
+    {
+      "epoch": 1.7945945945945945,
+      "grad_norm": 2.6005910068753857,
+      "learning_rate": 1.0844596606150055e-05,
+      "loss": 0.9501,
+      "step": 498
+    },
+    {
+      "epoch": 1.8054054054054054,
+      "grad_norm": 2.6765741105098364,
+      "learning_rate": 1.0684102563412519e-05,
+      "loss": 0.931,
+      "step": 501
+    },
+    {
+      "epoch": 1.8162162162162163,
+      "grad_norm": 2.811327607536862,
+      "learning_rate": 1.0524145423204623e-05,
+      "loss": 0.9793,
+      "step": 504
+    },
+    {
+      "epoch": 1.827027027027027,
+      "grad_norm": 2.92527323842401,
+      "learning_rate": 1.036474508437579e-05,
+      "loss": 0.9776,
+      "step": 507
+    },
+    {
+      "epoch": 1.8378378378378377,
+      "grad_norm": 2.789416429817517,
+      "learning_rate": 1.020592137650872e-05,
+      "loss": 0.947,
+      "step": 510
+    },
+    {
+      "epoch": 1.8486486486486486,
+      "grad_norm": 2.754589393028259,
+      "learning_rate": 1.004769405745257e-05,
+      "loss": 0.9685,
+      "step": 513
+    },
+    {
+      "epoch": 1.8594594594594596,
+      "grad_norm": 2.593923465827381,
+      "learning_rate": 9.890082810865046e-06,
+      "loss": 0.9317,
+      "step": 516
+    },
+    {
+      "epoch": 1.8702702702702703,
+      "grad_norm": 3.005765748087634,
+      "learning_rate": 9.733107243763754e-06,
+      "loss": 0.9612,
+      "step": 519
+    },
+    {
+      "epoch": 1.881081081081081,
+      "grad_norm": 2.6391444135921462,
+      "learning_rate": 9.576786884087037e-06,
+      "loss": 0.9431,
+      "step": 522
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 2.7958859686864823,
+      "learning_rate": 9.421141178264702e-06,
+      "loss": 0.9473,
+      "step": 525
+    },
+    {
+      "epoch": 1.9027027027027028,
+      "grad_norm": 2.8853568858381746,
+      "learning_rate": 9.266189488798854e-06,
+      "loss": 0.9404,
+      "step": 528
+    },
+    {
+      "epoch": 1.9135135135135135,
+      "grad_norm": 3.011863176958825,
+      "learning_rate": 9.111951091855164e-06,
+      "loss": 0.9424,
+      "step": 531
+    },
+    {
+      "epoch": 1.9243243243243242,
+      "grad_norm": 2.624513223364359,
+      "learning_rate": 8.95844517486492e-06,
+      "loss": 0.9404,
+      "step": 534
+    },
+    {
+      "epoch": 1.9351351351351351,
+      "grad_norm": 2.629936136635792,
+      "learning_rate": 8.805690834138076e-06,
+      "loss": 0.9588,
+      "step": 537
+    },
+    {
+      "epoch": 1.945945945945946,
+      "grad_norm": 2.8522026479916023,
+      "learning_rate": 8.65370707248763e-06,
+      "loss": 0.9339,
+      "step": 540
+    },
+    {
+      "epoch": 1.9567567567567568,
+      "grad_norm": 3.097766550094928,
+      "learning_rate": 8.502512796865686e-06,
+      "loss": 0.9394,
+      "step": 543
+    },
+    {
+      "epoch": 1.9675675675675675,
+      "grad_norm": 2.749849929848188,
+      "learning_rate": 8.352126816011382e-06,
+      "loss": 0.9402,
+      "step": 546
+    },
+    {
+      "epoch": 1.9783783783783784,
+      "grad_norm": 2.792496713680321,
+      "learning_rate": 8.202567838111078e-06,
+      "loss": 0.9403,
+      "step": 549
+    },
+    {
+      "epoch": 1.9891891891891893,
+      "grad_norm": 2.742908628148625,
+      "learning_rate": 8.053854468471025e-06,
+      "loss": 0.9475,
+      "step": 552
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.80461985695162,
+      "learning_rate": 7.906005207202852e-06,
+      "loss": 0.9251,
+      "step": 555
+    },
+    {
+      "epoch": 2.0108108108108107,
+      "grad_norm": 2.712256627105201,
+      "learning_rate": 7.75903844692212e-06,
+      "loss": 0.4979,
+      "step": 558
+    },
+    {
+      "epoch": 2.0216216216216214,
+      "grad_norm": 2.2575975329190823,
+      "learning_rate": 7.61297247046029e-06,
+      "loss": 0.4357,
+      "step": 561
+    },
+    {
+      "epoch": 2.0324324324324325,
+      "grad_norm": 2.8247101377056865,
+      "learning_rate": 7.4678254485902675e-06,
+      "loss": 0.4334,
+      "step": 564
+    },
+    {
+      "epoch": 2.0432432432432432,
+      "grad_norm": 2.588953106795816,
+      "learning_rate": 7.3236154377659825e-06,
+      "loss": 0.4327,
+      "step": 567
+    },
+    {
+      "epoch": 2.054054054054054,
+      "grad_norm": 2.2112157456197807,
+      "learning_rate": 7.180360377876125e-06,
+      "loss": 0.4301,
+      "step": 570
+    },
+    {
+      "epoch": 2.064864864864865,
+      "grad_norm": 2.1916524154888903,
+      "learning_rate": 7.038078090012406e-06,
+      "loss": 0.4254,
+      "step": 573
+    },
+    {
+      "epoch": 2.075675675675676,
+      "grad_norm": 2.092153236540328,
+      "learning_rate": 6.896786274252595e-06,
+      "loss": 0.4066,
+      "step": 576
+    },
+    {
+      "epoch": 2.0864864864864865,
+      "grad_norm": 2.1223817949774033,
+      "learning_rate": 6.7565025074586145e-06,
+      "loss": 0.4018,
+      "step": 579
+    },
+    {
+      "epoch": 2.097297297297297,
+      "grad_norm": 1.975599624746057,
+      "learning_rate": 6.617244241089947e-06,
+      "loss": 0.3899,
+      "step": 582
+    },
+    {
+      "epoch": 2.108108108108108,
+      "grad_norm": 1.8893909454422486,
+      "learning_rate": 6.479028799032664e-06,
+      "loss": 0.397,
+      "step": 585
+    },
+    {
+      "epoch": 2.118918918918919,
+      "grad_norm": 1.875678473328706,
+      "learning_rate": 6.3418733754443136e-06,
+      "loss": 0.407,
+      "step": 588
+    },
+    {
+      "epoch": 2.1297297297297297,
+      "grad_norm": 2.210895295229888,
+      "learning_rate": 6.205795032614943e-06,
+      "loss": 0.4039,
+      "step": 591
+    },
+    {
+      "epoch": 2.1405405405405404,
+      "grad_norm": 2.2866290593300573,
+      "learning_rate": 6.07081069884453e-06,
+      "loss": 0.3975,
+      "step": 594
+    },
+    {
+      "epoch": 2.1513513513513516,
+      "grad_norm": 2.169724698947998,
+      "learning_rate": 5.936937166337093e-06,
+      "loss": 0.404,
+      "step": 597
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 2.5885052465204503,
+      "learning_rate": 5.804191089111711e-06,
+      "loss": 0.4137,
+      "step": 600
+    },
+    {
+      "epoch": 2.172972972972973,
+      "grad_norm": 2.1184895283704273,
+      "learning_rate": 5.6725889809307486e-06,
+      "loss": 0.4069,
+      "step": 603
+    },
+    {
+      "epoch": 2.1837837837837837,
+      "grad_norm": 2.055767847916725,
+      "learning_rate": 5.5421472132455285e-06,
+      "loss": 0.4309,
+      "step": 606
+    },
+    {
+      "epoch": 2.1945945945945944,
+      "grad_norm": 1.9387007802838037,
+      "learning_rate": 5.412882013159697e-06,
+      "loss": 0.3989,
+      "step": 609
+    },
+    {
+      "epoch": 2.2054054054054055,
+      "grad_norm": 1.9041479568200537,
+      "learning_rate": 5.284809461410556e-06,
+      "loss": 0.4013,
+      "step": 612
+    },
+    {
+      "epoch": 2.2162162162162162,
+      "grad_norm": 2.0548881191902018,
+      "learning_rate": 5.157945490368621e-06,
+      "loss": 0.4205,
+      "step": 615
+    },
+    {
+      "epoch": 2.227027027027027,
+      "grad_norm": 2.0831599061407204,
+      "learning_rate": 5.03230588205558e-06,
+      "loss": 0.4122,
+      "step": 618
+    },
+    {
+      "epoch": 2.237837837837838,
+      "grad_norm": 1.971310383757786,
+      "learning_rate": 4.907906266181014e-06,
+      "loss": 0.3837,
+      "step": 621
+    },
+    {
+      "epoch": 2.2486486486486488,
+      "grad_norm": 1.977557211024187,
+      "learning_rate": 4.784762118198041e-06,
+      "loss": 0.3981,
+      "step": 624
+    },
+    {
+      "epoch": 2.2594594594594595,
+      "grad_norm": 1.9559375507208316,
+      "learning_rate": 4.66288875737816e-06,
+      "loss": 0.4094,
+      "step": 627
+    },
+    {
+      "epoch": 2.27027027027027,
+      "grad_norm": 1.9123345255397275,
+      "learning_rate": 4.542301344905496e-06,
+      "loss": 0.3863,
+      "step": 630
+    },
+    {
+      "epoch": 2.281081081081081,
+      "grad_norm": 1.8524912274987262,
+      "learning_rate": 4.423014881990751e-06,
+      "loss": 0.3908,
+      "step": 633
+    },
+    {
+      "epoch": 2.291891891891892,
+      "grad_norm": 2.0911936019239246,
+      "learning_rate": 4.305044208005023e-06,
+      "loss": 0.4167,
+      "step": 636
+    },
+    {
+      "epoch": 2.3027027027027027,
+      "grad_norm": 1.9050565892596198,
+      "learning_rate": 4.188403998633775e-06,
+      "loss": 0.3955,
+      "step": 639
+    },
+    {
+      "epoch": 2.3135135135135134,
+      "grad_norm": 1.8967742593703636,
+      "learning_rate": 4.0731087640511735e-06,
+      "loss": 0.4163,
+      "step": 642
+    },
+    {
+      "epoch": 2.3243243243243246,
+      "grad_norm": 2.051977219640454,
+      "learning_rate": 3.959172847114991e-06,
+      "loss": 0.4024,
+      "step": 645
+    },
+    {
+      "epoch": 2.3351351351351353,
+      "grad_norm": 2.0012355554132792,
+      "learning_rate": 3.846610421582349e-06,
+      "loss": 0.4157,
+      "step": 648
+    },
+    {
+      "epoch": 2.345945945945946,
+      "grad_norm": 2.175698094340077,
+      "learning_rate": 3.7354354903464793e-06,
+      "loss": 0.4024,
+      "step": 651
+    },
+    {
+      "epoch": 2.3567567567567567,
+      "grad_norm": 2.0526759215687362,
+      "learning_rate": 3.625661883694753e-06,
+      "loss": 0.3939,
+      "step": 654
+    },
+    {
+      "epoch": 2.3675675675675674,
+      "grad_norm": 1.960306969771245,
+      "learning_rate": 3.5173032575881768e-06,
+      "loss": 0.4074,
+      "step": 657
+    },
+    {
+      "epoch": 2.3783783783783785,
+      "grad_norm": 2.1570885212061826,
+      "learning_rate": 3.4103730919625753e-06,
+      "loss": 0.3976,
+      "step": 660
+    },
+    {
+      "epoch": 2.389189189189189,
+      "grad_norm": 1.8949986677811612,
+      "learning_rate": 3.3048846890516658e-06,
+      "loss": 0.4,
+      "step": 663
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.982249761308161,
+      "learning_rate": 3.2008511717322593e-06,
+      "loss": 0.4133,
+      "step": 666
+    },
+    {
+      "epoch": 2.410810810810811,
+      "grad_norm": 1.980047898141974,
+      "learning_rate": 3.098285481891745e-06,
+      "loss": 0.3939,
+      "step": 669
+    },
+    {
+      "epoch": 2.4216216216216218,
+      "grad_norm": 2.0049995734478965,
+      "learning_rate": 2.9972003788181146e-06,
+      "loss": 0.3926,
+      "step": 672
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 1.8400258173639734,
+      "learning_rate": 2.8976084376126848e-06,
+      "loss": 0.3936,
+      "step": 675
+    },
+    {
+      "epoch": 2.443243243243243,
+      "grad_norm": 1.9448462664129043,
+      "learning_rate": 2.7995220476257482e-06,
+      "loss": 0.388,
+      "step": 678
+    },
+    {
+      "epoch": 2.454054054054054,
+      "grad_norm": 1.9031160601187072,
+      "learning_rate": 2.7029534109153186e-06,
+      "loss": 0.3909,
+      "step": 681
+    },
+    {
+      "epoch": 2.464864864864865,
+      "grad_norm": 2.279997846004982,
+      "learning_rate": 2.6079145407291877e-06,
+      "loss": 0.3895,
+      "step": 684
+    },
+    {
+      "epoch": 2.4756756756756757,
+      "grad_norm": 1.8403404089990134,
+      "learning_rate": 2.514417260010455e-06,
+      "loss": 0.3976,
+      "step": 687
+    },
+    {
+      "epoch": 2.4864864864864864,
+      "grad_norm": 1.7969451736164892,
+      "learning_rate": 2.4224731999267425e-06,
+      "loss": 0.3999,
+      "step": 690
+    },
+    {
+      "epoch": 2.4972972972972975,
+      "grad_norm": 1.9253974055183771,
+      "learning_rate": 2.3320937984232664e-06,
+      "loss": 0.3939,
+      "step": 693
+    },
+    {
+      "epoch": 2.5081081081081082,
+      "grad_norm": 1.913704985114193,
+      "learning_rate": 2.243290298799945e-06,
+      "loss": 0.3984,
+      "step": 696
+    },
+    {
+      "epoch": 2.518918918918919,
+      "grad_norm": 1.9790173152408796,
+      "learning_rate": 2.156073748312721e-06,
+      "loss": 0.3819,
+      "step": 699
+    },
+    {
+      "epoch": 2.5297297297297296,
+      "grad_norm": 2.276492968512024,
+      "learning_rate": 2.070454996799261e-06,
+      "loss": 0.4039,
+      "step": 702
+    },
+    {
+      "epoch": 2.5405405405405403,
+      "grad_norm": 1.7739681476430693,
+      "learning_rate": 1.9864446953292313e-06,
+      "loss": 0.3791,
+      "step": 705
+    },
+    {
+      "epoch": 2.5513513513513515,
+      "grad_norm": 2.0336913560870196,
+      "learning_rate": 1.9040532948792934e-06,
+      "loss": 0.3847,
+      "step": 708
+    },
+    {
+      "epoch": 2.562162162162162,
+      "grad_norm": 1.8946193097351467,
+      "learning_rate": 1.8232910450329832e-06,
+      "loss": 0.385,
+      "step": 711
+    },
+    {
+      "epoch": 2.572972972972973,
+      "grad_norm": 1.9817636629737283,
+      "learning_rate": 1.744167992705664e-06,
+      "loss": 0.3914,
+      "step": 714
+    },
+    {
+      "epoch": 2.583783783783784,
+      "grad_norm": 1.8202147731376643,
+      "learning_rate": 1.6666939808946619e-06,
+      "loss": 0.377,
+      "step": 717
+    },
+    {
+      "epoch": 2.5945945945945947,
+      "grad_norm": 1.804624257938459,
+      "learning_rate": 1.5908786474548004e-06,
+      "loss": 0.3834,
+      "step": 720
+    },
+    {
+      "epoch": 2.6054054054054054,
+      "grad_norm": 1.9478831371089558,
+      "learning_rate": 1.5167314238994367e-06,
+      "loss": 0.3802,
+      "step": 723
+    },
+    {
+      "epoch": 2.616216216216216,
+      "grad_norm": 1.8418242757562502,
+      "learning_rate": 1.4442615342271625e-06,
+      "loss": 0.3742,
+      "step": 726
+    },
+    {
+      "epoch": 2.627027027027027,
+      "grad_norm": 1.8235265917309187,
+      "learning_rate": 1.3734779937743403e-06,
+      "loss": 0.3763,
+      "step": 729
+    },
+    {
+      "epoch": 2.637837837837838,
+      "grad_norm": 1.8148562882498185,
+      "learning_rate": 1.3043896080935785e-06,
+      "loss": 0.3764,
+      "step": 732
+    },
+    {
+      "epoch": 2.6486486486486487,
+      "grad_norm": 1.9162200026873921,
+      "learning_rate": 1.237004971858307e-06,
+      "loss": 0.4009,
+      "step": 735
+    },
+    {
+      "epoch": 2.6594594594594594,
+      "grad_norm": 1.971484443435529,
+      "learning_rate": 1.1713324677936015e-06,
+      "loss": 0.3894,
+      "step": 738
+    },
+    {
+      "epoch": 2.6702702702702705,
+      "grad_norm": 2.6288039366865883,
+      "learning_rate": 1.1073802656333548e-06,
+      "loss": 0.3736,
+      "step": 741
+    },
+    {
+      "epoch": 2.6810810810810812,
+      "grad_norm": 1.8111148825496188,
+      "learning_rate": 1.0451563211039494e-06,
+      "loss": 0.3996,
+      "step": 744
+    },
+    {
+      "epoch": 2.691891891891892,
+      "grad_norm": 1.7806298978071708,
+      "learning_rate": 9.846683749345648e-07,
+      "loss": 0.383,
+      "step": 747
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 4.0497002081385185,
+      "learning_rate": 9.25923951894222e-07,
+      "loss": 0.3965,
+      "step": 750
+    },
+    {
+      "epoch": 2.7135135135135133,
+      "grad_norm": 1.8334211425058837,
+      "learning_rate": 8.68930359855683e-07,
+      "loss": 0.3989,
+      "step": 753
+    },
+    {
+      "epoch": 2.7243243243243245,
+      "grad_norm": 1.7500539556657924,
+      "learning_rate": 8.136946888863528e-07,
+      "loss": 0.395,
+      "step": 756
+    },
+    {
+      "epoch": 2.735135135135135,
+      "grad_norm": 1.9130969263501059,
+      "learning_rate": 7.602238103662646e-07,
+      "loss": 0.3853,
+      "step": 759
+    },
+    {
+      "epoch": 2.745945945945946,
+      "grad_norm": 1.8404236110308207,
+      "learning_rate": 7.085243761332738e-07,
+      "loss": 0.393,
+      "step": 762
+    },
+    {
+      "epoch": 2.756756756756757,
+      "grad_norm": 1.7456858490902225,
+      "learning_rate": 6.586028176555536e-07,
+      "loss": 0.3944,
+      "step": 765
+    },
+    {
+      "epoch": 2.7675675675675677,
+      "grad_norm": 1.837065449202062,
+      "learning_rate": 6.104653452315279e-07,
+      "loss": 0.3798,
+      "step": 768
+    },
+    {
+      "epoch": 2.7783783783783784,
+      "grad_norm": 2.3308657348413058,
+      "learning_rate": 5.641179472172875e-07,
+      "loss": 0.3798,
+      "step": 771
+    },
+    {
+      "epoch": 2.789189189189189,
+      "grad_norm": 1.7969746620946272,
+      "learning_rate": 5.195663892816432e-07,
+      "loss": 0.3817,
+      "step": 774
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.8403934823419463,
+      "learning_rate": 4.768162136888643e-07,
+      "loss": 0.3791,
+      "step": 777
+    },
+    {
+      "epoch": 2.810810810810811,
+      "grad_norm": 1.8084423900988431,
+      "learning_rate": 4.3587273860921985e-07,
+      "loss": 0.3613,
+      "step": 780
+    },
+    {
+      "epoch": 2.8216216216216217,
+      "grad_norm": 1.8704402298319724,
+      "learning_rate": 3.9674105745738155e-07,
+      "loss": 0.3771,
+      "step": 783
+    },
+    {
+      "epoch": 2.8324324324324324,
+      "grad_norm": 1.818023687371634,
+      "learning_rate": 3.594260382588105e-07,
+      "loss": 0.3888,
+      "step": 786
+    },
+    {
+      "epoch": 2.8432432432432435,
+      "grad_norm": 1.8608896733650853,
+      "learning_rate": 3.239323230441615e-07,
+      "loss": 0.3888,
+      "step": 789
+    },
+    {
+      "epoch": 2.854054054054054,
+      "grad_norm": 1.938515453919976,
+      "learning_rate": 2.902643272718086e-07,
+      "loss": 0.4002,
+      "step": 792
+    },
+    {
+      "epoch": 2.864864864864865,
+      "grad_norm": 1.94145103701424,
+      "learning_rate": 2.5842623927856244e-07,
+      "loss": 0.3858,
+      "step": 795
+    },
+    {
+      "epoch": 2.8756756756756756,
+      "grad_norm": 1.7260066637899822,
+      "learning_rate": 2.28422019758629e-07,
+      "loss": 0.3905,
+      "step": 798
+    },
+    {
+      "epoch": 2.8864864864864863,
+      "grad_norm": 1.8230164360318986,
+      "learning_rate": 2.0025540127090513e-07,
+      "loss": 0.3977,
+      "step": 801
+    },
+    {
+      "epoch": 2.8972972972972975,
+      "grad_norm": 1.7780456307114303,
+      "learning_rate": 1.7392988777463202e-07,
+      "loss": 0.3881,
+      "step": 804
+    },
+    {
+      "epoch": 2.908108108108108,
+      "grad_norm": 1.9497490854182644,
+      "learning_rate": 1.4944875419350855e-07,
+      "loss": 0.3797,
+      "step": 807
+    },
+    {
+      "epoch": 2.918918918918919,
+      "grad_norm": 1.6524262781562993,
+      "learning_rate": 1.268150460082823e-07,
+      "loss": 0.3645,
+      "step": 810
+    },
+    {
+      "epoch": 2.92972972972973,
+      "grad_norm": 1.8325737906994488,
+      "learning_rate": 1.0603157887788428e-07,
+      "loss": 0.3574,
+      "step": 813
+    },
+    {
+      "epoch": 2.9405405405405407,
+      "grad_norm": 1.8188448217016162,
+      "learning_rate": 8.710093828917076e-08,
+      "loss": 0.3829,
+      "step": 816
+    },
+    {
+      "epoch": 2.9513513513513514,
+      "grad_norm": 1.774843520134497,
+      "learning_rate": 7.002547923527058e-08,
+      "loss": 0.3945,
+      "step": 819
+    },
+    {
+      "epoch": 2.962162162162162,
+      "grad_norm": 1.7417401019158905,
+      "learning_rate": 5.4807325922632825e-08,
+      "loss": 0.37,
+      "step": 822
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 1.6997699000548114,
+      "learning_rate": 4.14483715067665e-08,
+      "loss": 0.3702,
+      "step": 825
+    },
+    {
+      "epoch": 2.983783783783784,
+      "grad_norm": 1.7185773019727228,
+      "learning_rate": 2.995027785673066e-08,
+      "loss": 0.3829,
+      "step": 828
+    },
+    {
+      "epoch": 2.9945945945945946,
+      "grad_norm": 1.7433824271169698,
+      "learning_rate": 2.0314475348401362e-08,
+      "loss": 0.3777,
+      "step": 831
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 845,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 232851391348736.0,
+  "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:d9542b63bd8930ae4e5f7ec4d5bd7a3f040f7b8cb6bfd6948da2ff10488d90d3
+size 7288

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)