Upload folder using huggingface_hub

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-Nemo-Base-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": 131073
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.0.dev0"
+}

latest

@@ -0,0 +1 @@
+global_step180

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d7836bb639b4738b36fa36c79a8717dd09b8baf129897e8431220e0c043c43
+size 4865532736

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c95fd82c96b0450c8ccd8f0ba522d9be0d2d9df2dce663c19a5ee535240503
+size 4907529424

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e87dddbe0dc4529f42ea62c85dd5e0e84ff664c4e1d1bbd60b5f858d027c0b
+size 4907529456

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86928011fb8b6bc7badbacade9958a92ee0bedf3df62ec193114b0a55e1d5cd
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a8a6e132c5b2e2940eb32a42d42ff81dabf69413b127fafe949db6e38f5def
+size 4907506512

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24495585280
+  },
+  "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 sha256:08282b46825aa78d10fe10e3fea89555c5b5a691b261a3ddfd58fcb58370edff
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbab71d98a3a9a92df82a6bba463947327c3a1bcf35cd9f4f46114641fc42dd9
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caac82d57d878d30219a4f9ec289a97ff90c53afc160b968f251b3fd3454b8d8
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19762d2d370222b01817da11bbaa6665d542293373186d66f754e7246bb861ed
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c7508b346a7d3c5c23392845f1d013331114ade778794b76e919cb3ed5d33e
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89de7d14dd20a191f56b74c816ef8b7fe5c171e31efbeadbf321c4539ed68c3
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c71152053553e6e22d670fbc4fd7550bf8a046b54cad7b71869787986a6a42c
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b67db12a26a26ffe03d9afc84a43857eb2e5b2fec2dd189653b415f74208190
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac11880ab7844d15750f898a7e872d86aabf1af83199f34aca9402fe6da59799
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,1293 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4773519163763065,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013937282229965157,
+      "grad_norm": 93.75749969482422,
+      "learning_rate": 2.2e-06,
+      "loss": 1.2675,
+      "step": 1
+    },
+    {
+      "epoch": 0.027874564459930314,
+      "grad_norm": 66.60814666748047,
+      "learning_rate": 4.4e-06,
+      "loss": 1.3582,
+      "step": 2
+    },
+    {
+      "epoch": 0.041811846689895474,
+      "grad_norm": 77.9828109741211,
+      "learning_rate": 6.5999999999999995e-06,
+      "loss": 1.2567,
+      "step": 3
+    },
+    {
+      "epoch": 0.05574912891986063,
+      "grad_norm": 17.5104923248291,
+      "learning_rate": 8.8e-06,
+      "loss": 1.1877,
+      "step": 4
+    },
+    {
+      "epoch": 0.06968641114982578,
+      "grad_norm": 10.045647621154785,
+      "learning_rate": 1.1e-05,
+      "loss": 1.1663,
+      "step": 5
+    },
+    {
+      "epoch": 0.08362369337979095,
+      "grad_norm": 12.031865119934082,
+      "learning_rate": 1.0999372667896238e-05,
+      "loss": 1.1769,
+      "step": 6
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 6.24857234954834,
+      "learning_rate": 1.0997490814692433e-05,
+      "loss": 1.1703,
+      "step": 7
+    },
+    {
+      "epoch": 0.11149825783972125,
+      "grad_norm": 4.496493816375732,
+      "learning_rate": 1.0994354869678378e-05,
+      "loss": 1.1608,
+      "step": 8
+    },
+    {
+      "epoch": 0.1254355400696864,
+      "grad_norm": 4.9181036949157715,
+      "learning_rate": 1.0989965548228246e-05,
+      "loss": 1.1165,
+      "step": 9
+    },
+    {
+      "epoch": 0.13937282229965156,
+      "grad_norm": 3.872187614440918,
+      "learning_rate": 1.0984323851637407e-05,
+      "loss": 1.1308,
+      "step": 10
+    },
+    {
+      "epoch": 0.15331010452961671,
+      "grad_norm": 4.341373920440674,
+      "learning_rate": 1.0977431066894e-05,
+      "loss": 1.1245,
+      "step": 11
+    },
+    {
+      "epoch": 0.1672473867595819,
+      "grad_norm": 3.867882013320923,
+      "learning_rate": 1.0969288766385357e-05,
+      "loss": 1.1486,
+      "step": 12
+    },
+    {
+      "epoch": 0.18118466898954705,
+      "grad_norm": 3.2795205116271973,
+      "learning_rate": 1.0959898807539295e-05,
+      "loss": 1.123,
+      "step": 13
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 3.429868698120117,
+      "learning_rate": 1.0949263332400415e-05,
+      "loss": 1.1169,
+      "step": 14
+    },
+    {
+      "epoch": 0.20905923344947736,
+      "grad_norm": 3.0912277698516846,
+      "learning_rate": 1.0937384767141438e-05,
+      "loss": 1.0832,
+      "step": 15
+    },
+    {
+      "epoch": 0.2229965156794425,
+      "grad_norm": 4.55407190322876,
+      "learning_rate": 1.0924265821509758e-05,
+      "loss": 1.1018,
+      "step": 16
+    },
+    {
+      "epoch": 0.23693379790940766,
+      "grad_norm": 3.4495749473571777,
+      "learning_rate": 1.090990948820929e-05,
+      "loss": 1.1186,
+      "step": 17
+    },
+    {
+      "epoch": 0.2508710801393728,
+      "grad_norm": 6.985757827758789,
+      "learning_rate": 1.0894319042217767e-05,
+      "loss": 1.1135,
+      "step": 18
+    },
+    {
+      "epoch": 0.26480836236933797,
+      "grad_norm": 3.7354323863983154,
+      "learning_rate": 1.0877498040039657e-05,
+      "loss": 1.1064,
+      "step": 19
+    },
+    {
+      "epoch": 0.2787456445993031,
+      "grad_norm": 4.375406265258789,
+      "learning_rate": 1.0859450318894847e-05,
+      "loss": 1.0767,
+      "step": 20
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 4.374971389770508,
+      "learning_rate": 1.0840179995843286e-05,
+      "loss": 1.1072,
+      "step": 21
+    },
+    {
+      "epoch": 0.30662020905923343,
+      "grad_norm": 3.129504442214966,
+      "learning_rate": 1.0819691466845815e-05,
+      "loss": 1.0414,
+      "step": 22
+    },
+    {
+      "epoch": 0.3205574912891986,
+      "grad_norm": 4.991695404052734,
+      "learning_rate": 1.079798940576134e-05,
+      "loss": 1.0773,
+      "step": 23
+    },
+    {
+      "epoch": 0.3344947735191638,
+      "grad_norm": 3.570375919342041,
+      "learning_rate": 1.0775078763280638e-05,
+      "loss": 1.0709,
+      "step": 24
+    },
+    {
+      "epoch": 0.34843205574912894,
+      "grad_norm": 7.718966007232666,
+      "learning_rate": 1.0750964765797001e-05,
+      "loss": 1.1019,
+      "step": 25
+    },
+    {
+      "epoch": 0.3623693379790941,
+      "grad_norm": 3.459160327911377,
+      "learning_rate": 1.072565291421398e-05,
+      "loss": 1.0505,
+      "step": 26
+    },
+    {
+      "epoch": 0.37630662020905925,
+      "grad_norm": 5.686498641967773,
+      "learning_rate": 1.069914898269052e-05,
+      "loss": 1.0897,
+      "step": 27
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 3.622288465499878,
+      "learning_rate": 1.067145901732376e-05,
+      "loss": 1.0817,
+      "step": 28
+    },
+    {
+      "epoch": 0.40418118466898956,
+      "grad_norm": 6.713829040527344,
+      "learning_rate": 1.0642589334769783e-05,
+      "loss": 1.0597,
+      "step": 29
+    },
+    {
+      "epoch": 0.4181184668989547,
+      "grad_norm": 3.2670044898986816,
+      "learning_rate": 1.061254652080265e-05,
+      "loss": 1.0631,
+      "step": 30
+    },
+    {
+      "epoch": 0.43205574912891986,
+      "grad_norm": 3.0448334217071533,
+      "learning_rate": 1.0581337428812077e-05,
+      "loss": 1.0697,
+      "step": 31
+    },
+    {
+      "epoch": 0.445993031358885,
+      "grad_norm": 4.583492755889893,
+      "learning_rate": 1.0548969178239997e-05,
+      "loss": 1.0564,
+      "step": 32
+    },
+    {
+      "epoch": 0.45993031358885017,
+      "grad_norm": 3.7002651691436768,
+      "learning_rate": 1.0515449152956496e-05,
+      "loss": 1.0852,
+      "step": 33
+    },
+    {
+      "epoch": 0.4738675958188153,
+      "grad_norm": 3.1550400257110596,
+      "learning_rate": 1.0480784999575381e-05,
+      "loss": 1.0576,
+      "step": 34
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 3.1954734325408936,
+      "learning_rate": 1.0444984625709842e-05,
+      "loss": 1.0965,
+      "step": 35
+    },
+    {
+      "epoch": 0.5017421602787456,
+      "grad_norm": 2.8396148681640625,
+      "learning_rate": 1.0408056198168555e-05,
+      "loss": 1.0401,
+      "step": 36
+    },
+    {
+      "epoch": 0.5156794425087108,
+      "grad_norm": 10.67453384399414,
+      "learning_rate": 1.0370008141092654e-05,
+      "loss": 1.0909,
+      "step": 37
+    },
+    {
+      "epoch": 0.5296167247386759,
+      "grad_norm": 3.554422378540039,
+      "learning_rate": 1.0330849134034033e-05,
+      "loss": 1.0534,
+      "step": 38
+    },
+    {
+      "epoch": 0.5435540069686411,
+      "grad_norm": 3.5049169063568115,
+      "learning_rate": 1.0290588109975334e-05,
+      "loss": 1.0366,
+      "step": 39
+    },
+    {
+      "epoch": 0.5574912891986062,
+      "grad_norm": 3.9955601692199707,
+      "learning_rate": 1.024923425329217e-05,
+      "loss": 1.0264,
+      "step": 40
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 3.2370924949645996,
+      "learning_rate": 1.0206796997657961e-05,
+      "loss": 1.0282,
+      "step": 41
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 3.0653462409973145,
+      "learning_rate": 1.0163286023891926e-05,
+      "loss": 1.066,
+      "step": 42
+    },
+    {
+      "epoch": 0.5993031358885017,
+      "grad_norm": 2.9653961658477783,
+      "learning_rate": 1.011871125775069e-05,
+      "loss": 1.068,
+      "step": 43
+    },
+    {
+      "epoch": 0.6132404181184669,
+      "grad_norm": 2.899329423904419,
+      "learning_rate": 1.0073082867664e-05,
+      "loss": 1.0075,
+      "step": 44
+    },
+    {
+      "epoch": 0.627177700348432,
+      "grad_norm": 3.231595277786255,
+      "learning_rate": 1.002641126241511e-05,
+      "loss": 1.0579,
+      "step": 45
+    },
+    {
+      "epoch": 0.6411149825783972,
+      "grad_norm": 3.7711715698242188,
+      "learning_rate": 9.978707088766316e-06,
+      "loss": 1.0511,
+      "step": 46
+    },
+    {
+      "epoch": 0.6550522648083623,
+      "grad_norm": 3.1697182655334473,
+      "learning_rate": 9.929981229030202e-06,
+      "loss": 1.0785,
+      "step": 47
+    },
+    {
+      "epoch": 0.6689895470383276,
+      "grad_norm": 2.8038201332092285,
+      "learning_rate": 9.88024479858717e-06,
+      "loss": 1.0389,
+      "step": 48
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 3.2184159755706787,
+      "learning_rate": 9.829509143349775e-06,
+      "loss": 1.0625,
+      "step": 49
+    },
+    {
+      "epoch": 0.6968641114982579,
+      "grad_norm": 2.9576430320739746,
+      "learning_rate": 9.77778583717451e-06,
+      "loss": 1.0217,
+      "step": 50
+    },
+    {
+      "epoch": 0.710801393728223,
+      "grad_norm": 2.918567657470703,
+      "learning_rate": 9.725086679221542e-06,
+      "loss": 1.0106,
+      "step": 51
+    },
+    {
+      "epoch": 0.7247386759581882,
+      "grad_norm": 2.8690834045410156,
+      "learning_rate": 9.671423691263104e-06,
+      "loss": 1.0427,
+      "step": 52
+    },
+    {
+      "epoch": 0.7386759581881533,
+      "grad_norm": 2.8049697875976562,
+      "learning_rate": 9.616809114941055e-06,
+      "loss": 1.0553,
+      "step": 53
+    },
+    {
+      "epoch": 0.7526132404181185,
+      "grad_norm": 3.5655879974365234,
+      "learning_rate": 9.561255408974332e-06,
+      "loss": 1.0308,
+      "step": 54
+    },
+    {
+      "epoch": 0.7665505226480837,
+      "grad_norm": 3.0086355209350586,
+      "learning_rate": 9.504775246316836e-06,
+      "loss": 1.0625,
+      "step": 55
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 3.2106897830963135,
+      "learning_rate": 9.447381511266482e-06,
+      "loss": 1.0582,
+      "step": 56
+    },
+    {
+      "epoch": 0.794425087108014,
+      "grad_norm": 3.013434410095215,
+      "learning_rate": 9.38908729652601e-06,
+      "loss": 1.0501,
+      "step": 57
+    },
+    {
+      "epoch": 0.8083623693379791,
+      "grad_norm": 3.194031000137329,
+      "learning_rate": 9.32990590021629e-06,
+      "loss": 1.0385,
+      "step": 58
+    },
+    {
+      "epoch": 0.8222996515679443,
+      "grad_norm": 2.9916939735412598,
+      "learning_rate": 9.269850822842717e-06,
+      "loss": 0.9978,
+      "step": 59
+    },
+    {
+      "epoch": 0.8362369337979094,
+      "grad_norm": 2.90720796585083,
+      "learning_rate": 9.208935764215487e-06,
+      "loss": 1.038,
+      "step": 60
+    },
+    {
+      "epoch": 0.8501742160278746,
+      "grad_norm": 2.983062505722046,
+      "learning_rate": 9.147174620324374e-06,
+      "loss": 1.0137,
+      "step": 61
+    },
+    {
+      "epoch": 0.8641114982578397,
+      "grad_norm": 3.021130084991455,
+      "learning_rate": 9.084581480168767e-06,
+      "loss": 1.0388,
+      "step": 62
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 3.831815242767334,
+      "learning_rate": 9.021170622543684e-06,
+      "loss": 1.0482,
+      "step": 63
+    },
+    {
+      "epoch": 0.89198606271777,
+      "grad_norm": 3.5826456546783447,
+      "learning_rate": 8.956956512782476e-06,
+      "loss": 1.0494,
+      "step": 64
+    },
+    {
+      "epoch": 0.9059233449477352,
+      "grad_norm": 3.445178747177124,
+      "learning_rate": 8.891953799456987e-06,
+      "loss": 0.9976,
+      "step": 65
+    },
+    {
+      "epoch": 0.9198606271777003,
+      "grad_norm": 2.8443377017974854,
+      "learning_rate": 8.826177311035906e-06,
+      "loss": 1.0646,
+      "step": 66
+    },
+    {
+      "epoch": 0.9337979094076655,
+      "grad_norm": 2.8210973739624023,
+      "learning_rate": 8.759642052502092e-06,
+      "loss": 1.0602,
+      "step": 67
+    },
+    {
+      "epoch": 0.9477351916376306,
+      "grad_norm": 2.9282021522521973,
+      "learning_rate": 8.692363201929623e-06,
+      "loss": 1.041,
+      "step": 68
+    },
+    {
+      "epoch": 0.9616724738675958,
+      "grad_norm": 2.916203260421753,
+      "learning_rate": 8.624356107021355e-06,
+      "loss": 1.035,
+      "step": 69
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 2.7474899291992188,
+      "learning_rate": 8.555636281607811e-06,
+      "loss": 1.0443,
+      "step": 70
+    },
+    {
+      "epoch": 0.9895470383275261,
+      "grad_norm": 3.2409560680389404,
+      "learning_rate": 8.486219402108133e-06,
+      "loss": 1.0502,
+      "step": 71
+    },
+    {
+      "epoch": 1.0034843205574913,
+      "grad_norm": 3.2006499767303467,
+      "learning_rate": 8.416121303953973e-06,
+      "loss": 1.0337,
+      "step": 72
+    },
+    {
+      "epoch": 1.0017421602787457,
+      "grad_norm": 3.021101713180542,
+      "learning_rate": 8.345357977977113e-06,
+      "loss": 1.0164,
+      "step": 73
+    },
+    {
+      "epoch": 1.0156794425087108,
+      "grad_norm": 3.0675883293151855,
+      "learning_rate": 8.273945566761604e-06,
+      "loss": 0.9739,
+      "step": 74
+    },
+    {
+      "epoch": 1.029616724738676,
+      "grad_norm": 2.925316095352173,
+      "learning_rate": 8.201900360961325e-06,
+      "loss": 0.9607,
+      "step": 75
+    },
+    {
+      "epoch": 1.043554006968641,
+      "grad_norm": 3.2823657989501953,
+      "learning_rate": 8.12923879558374e-06,
+      "loss": 0.9313,
+      "step": 76
+    },
+    {
+      "epoch": 1.0574912891986064,
+      "grad_norm": 2.809762477874756,
+      "learning_rate": 8.055977446240727e-06,
+      "loss": 0.9682,
+      "step": 77
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 3.0586483478546143,
+      "learning_rate": 7.982133025367346e-06,
+      "loss": 0.9674,
+      "step": 78
+    },
+    {
+      "epoch": 1.0853658536585367,
+      "grad_norm": 2.9541120529174805,
+      "learning_rate": 7.907722378409371e-06,
+      "loss": 0.9691,
+      "step": 79
+    },
+    {
+      "epoch": 1.0993031358885017,
+      "grad_norm": 2.965197801589966,
+      "learning_rate": 7.83276247998052e-06,
+      "loss": 0.9537,
+      "step": 80
+    },
+    {
+      "epoch": 1.113240418118467,
+      "grad_norm": 3.096423625946045,
+      "learning_rate": 7.757270429990162e-06,
+      "loss": 0.9631,
+      "step": 81
+    },
+    {
+      "epoch": 1.127177700348432,
+      "grad_norm": 3.0303800106048584,
+      "learning_rate": 7.681263449742493e-06,
+      "loss": 0.9774,
+      "step": 82
+    },
+    {
+      "epoch": 1.1411149825783973,
+      "grad_norm": 3.2755138874053955,
+      "learning_rate": 7.604758878007994e-06,
+      "loss": 0.9589,
+      "step": 83
+    },
+    {
+      "epoch": 1.1550522648083623,
+      "grad_norm": 3.0583481788635254,
+      "learning_rate": 7.527774167068094e-06,
+      "loss": 0.9313,
+      "step": 84
+    },
+    {
+      "epoch": 1.1689895470383276,
+      "grad_norm": 2.8140718936920166,
+      "learning_rate": 7.4503268787339455e-06,
+      "loss": 0.9137,
+      "step": 85
+    },
+    {
+      "epoch": 1.1829268292682926,
+      "grad_norm": 3.0150392055511475,
+      "learning_rate": 7.372434680340213e-06,
+      "loss": 0.9324,
+      "step": 86
+    },
+    {
+      "epoch": 1.1968641114982579,
+      "grad_norm": 3.1816203594207764,
+      "learning_rate": 7.294115340714782e-06,
+      "loss": 0.9835,
+      "step": 87
+    },
+    {
+      "epoch": 1.210801393728223,
+      "grad_norm": 3.011570930480957,
+      "learning_rate": 7.215386726125319e-06,
+      "loss": 0.9395,
+      "step": 88
+    },
+    {
+      "epoch": 1.2247386759581882,
+      "grad_norm": 4.090625286102295,
+      "learning_rate": 7.1362667962036166e-06,
+      "loss": 0.9682,
+      "step": 89
+    },
+    {
+      "epoch": 1.2386759581881532,
+      "grad_norm": 3.290282964706421,
+      "learning_rate": 7.056773599848612e-06,
+      "loss": 0.9487,
+      "step": 90
+    },
+    {
+      "epoch": 1.2526132404181185,
+      "grad_norm": 3.567591667175293,
+      "learning_rate": 6.976925271109072e-06,
+      "loss": 0.9459,
+      "step": 91
+    },
+    {
+      "epoch": 1.2665505226480835,
+      "grad_norm": 2.817159414291382,
+      "learning_rate": 6.8967400250468335e-06,
+      "loss": 0.968,
+      "step": 92
+    },
+    {
+      "epoch": 1.2804878048780488,
+      "grad_norm": 3.8883535861968994,
+      "learning_rate": 6.816236153581568e-06,
+      "loss": 0.938,
+      "step": 93
+    },
+    {
+      "epoch": 1.294425087108014,
+      "grad_norm": 2.920037269592285,
+      "learning_rate": 6.735432021318023e-06,
+      "loss": 0.9401,
+      "step": 94
+    },
+    {
+      "epoch": 1.3083623693379791,
+      "grad_norm": 2.851327896118164,
+      "learning_rate": 6.654346061356661e-06,
+      "loss": 0.9636,
+      "step": 95
+    },
+    {
+      "epoch": 1.3222996515679442,
+      "grad_norm": 3.1404778957366943,
+      "learning_rate": 6.572996771088706e-06,
+      "loss": 0.9665,
+      "step": 96
+    },
+    {
+      "epoch": 1.3362369337979094,
+      "grad_norm": 4.205505847930908,
+      "learning_rate": 6.491402707976482e-06,
+      "loss": 0.945,
+      "step": 97
+    },
+    {
+      "epoch": 1.3501742160278747,
+      "grad_norm": 2.9891207218170166,
+      "learning_rate": 6.409582485320087e-06,
+      "loss": 0.9554,
+      "step": 98
+    },
+    {
+      "epoch": 1.3641114982578397,
+      "grad_norm": 2.9016053676605225,
+      "learning_rate": 6.327554768011307e-06,
+      "loss": 0.9613,
+      "step": 99
+    },
+    {
+      "epoch": 1.3780487804878048,
+      "grad_norm": 2.954751968383789,
+      "learning_rate": 6.245338268275765e-06,
+      "loss": 0.9358,
+      "step": 100
+    },
+    {
+      "epoch": 1.39198606271777,
+      "grad_norm": 3.2333548069000244,
+      "learning_rate": 6.162951741404276e-06,
+      "loss": 0.9573,
+      "step": 101
+    },
+    {
+      "epoch": 1.4059233449477353,
+      "grad_norm": 3.4226996898651123,
+      "learning_rate": 6.080413981474379e-06,
+      "loss": 0.9294,
+      "step": 102
+    },
+    {
+      "epoch": 1.4198606271777003,
+      "grad_norm": 3.169379711151123,
+      "learning_rate": 5.9977438170630085e-06,
+      "loss": 0.9195,
+      "step": 103
+    },
+    {
+      "epoch": 1.4337979094076654,
+      "grad_norm": 3.147132396697998,
+      "learning_rate": 5.914960106951313e-06,
+      "loss": 0.9524,
+      "step": 104
+    },
+    {
+      "epoch": 1.4477351916376306,
+      "grad_norm": 2.7678744792938232,
+      "learning_rate": 5.832081735822573e-06,
+      "loss": 0.9234,
+      "step": 105
+    },
+    {
+      "epoch": 1.461672473867596,
+      "grad_norm": 2.8116793632507324,
+      "learning_rate": 5.749127609954215e-06,
+      "loss": 0.9619,
+      "step": 106
+    },
+    {
+      "epoch": 1.475609756097561,
+      "grad_norm": 3.6426944732666016,
+      "learning_rate": 5.666116652904889e-06,
+      "loss": 0.9435,
+      "step": 107
+    },
+    {
+      "epoch": 1.489547038327526,
+      "grad_norm": 4.532324314117432,
+      "learning_rate": 5.5830678011976225e-06,
+      "loss": 0.9538,
+      "step": 108
+    },
+    {
+      "epoch": 1.5034843205574913,
+      "grad_norm": 3.7293591499328613,
+      "learning_rate": 5.5e-06,
+      "loss": 0.9595,
+      "step": 109
+    },
+    {
+      "epoch": 1.5174216027874565,
+      "grad_norm": 2.8792057037353516,
+      "learning_rate": 5.416932198802378e-06,
+      "loss": 0.9498,
+      "step": 110
+    },
+    {
+      "epoch": 1.5313588850174216,
+      "grad_norm": 2.9074580669403076,
+      "learning_rate": 5.333883347095112e-06,
+      "loss": 0.9572,
+      "step": 111
+    },
+    {
+      "epoch": 1.5452961672473866,
+      "grad_norm": 4.807355880737305,
+      "learning_rate": 5.250872390045787e-06,
+      "loss": 0.9527,
+      "step": 112
+    },
+    {
+      "epoch": 1.5592334494773519,
+      "grad_norm": 4.229637622833252,
+      "learning_rate": 5.167918264177426e-06,
+      "loss": 0.9275,
+      "step": 113
+    },
+    {
+      "epoch": 1.5731707317073171,
+      "grad_norm": 3.07944393157959,
+      "learning_rate": 5.085039893048687e-06,
+      "loss": 0.9565,
+      "step": 114
+    },
+    {
+      "epoch": 1.5871080139372822,
+      "grad_norm": 2.8650782108306885,
+      "learning_rate": 5.002256182936992e-06,
+      "loss": 0.9493,
+      "step": 115
+    },
+    {
+      "epoch": 1.6010452961672472,
+      "grad_norm": 2.928194284439087,
+      "learning_rate": 4.919586018525621e-06,
+      "loss": 0.9513,
+      "step": 116
+    },
+    {
+      "epoch": 1.6149825783972127,
+      "grad_norm": 3.433330535888672,
+      "learning_rate": 4.837048258595723e-06,
+      "loss": 0.978,
+      "step": 117
+    },
+    {
+      "epoch": 1.6289198606271778,
+      "grad_norm": 2.8581085205078125,
+      "learning_rate": 4.754661731724237e-06,
+      "loss": 0.9366,
+      "step": 118
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 2.897559404373169,
+      "learning_rate": 4.672445231988693e-06,
+      "loss": 0.9641,
+      "step": 119
+    },
+    {
+      "epoch": 1.656794425087108,
+      "grad_norm": 2.8979365825653076,
+      "learning_rate": 4.590417514679912e-06,
+      "loss": 0.9316,
+      "step": 120
+    },
+    {
+      "epoch": 1.6707317073170733,
+      "grad_norm": 3.090183734893799,
+      "learning_rate": 4.508597292023518e-06,
+      "loss": 0.9545,
+      "step": 121
+    },
+    {
+      "epoch": 1.6846689895470384,
+      "grad_norm": 2.9215645790100098,
+      "learning_rate": 4.427003228911295e-06,
+      "loss": 0.9169,
+      "step": 122
+    },
+    {
+      "epoch": 1.6986062717770034,
+      "grad_norm": 4.066997528076172,
+      "learning_rate": 4.345653938643339e-06,
+      "loss": 0.9357,
+      "step": 123
+    },
+    {
+      "epoch": 1.7125435540069687,
+      "grad_norm": 3.2360036373138428,
+      "learning_rate": 4.2645679786819796e-06,
+      "loss": 0.9205,
+      "step": 124
+    },
+    {
+      "epoch": 1.726480836236934,
+      "grad_norm": 2.890538215637207,
+      "learning_rate": 4.1837638464184334e-06,
+      "loss": 0.9355,
+      "step": 125
+    },
+    {
+      "epoch": 1.740418118466899,
+      "grad_norm": 3.4630892276763916,
+      "learning_rate": 4.103259974953166e-06,
+      "loss": 0.9263,
+      "step": 126
+    },
+    {
+      "epoch": 1.754355400696864,
+      "grad_norm": 3.326503276824951,
+      "learning_rate": 4.023074728890927e-06,
+      "loss": 0.9154,
+      "step": 127
+    },
+    {
+      "epoch": 1.7682926829268293,
+      "grad_norm": 3.6348044872283936,
+      "learning_rate": 3.943226400151388e-06,
+      "loss": 0.944,
+      "step": 128
+    },
+    {
+      "epoch": 1.7822299651567945,
+      "grad_norm": 3.0831995010375977,
+      "learning_rate": 3.863733203796385e-06,
+      "loss": 0.9457,
+      "step": 129
+    },
+    {
+      "epoch": 1.7961672473867596,
+      "grad_norm": 3.1765310764312744,
+      "learning_rate": 3.784613273874681e-06,
+      "loss": 0.9329,
+      "step": 130
+    },
+    {
+      "epoch": 1.8101045296167246,
+      "grad_norm": 2.767540693283081,
+      "learning_rate": 3.70588465928522e-06,
+      "loss": 0.9285,
+      "step": 131
+    },
+    {
+      "epoch": 1.82404181184669,
+      "grad_norm": 2.718041181564331,
+      "learning_rate": 3.6275653196597856e-06,
+      "loss": 0.9767,
+      "step": 132
+    },
+    {
+      "epoch": 1.8379790940766552,
+      "grad_norm": 4.337693691253662,
+      "learning_rate": 3.5496731212660538e-06,
+      "loss": 0.9351,
+      "step": 133
+    },
+    {
+      "epoch": 1.8519163763066202,
+      "grad_norm": 3.106288194656372,
+      "learning_rate": 3.472225832931907e-06,
+      "loss": 0.9554,
+      "step": 134
+    },
+    {
+      "epoch": 1.8658536585365852,
+      "grad_norm": 3.2049343585968018,
+      "learning_rate": 3.3952411219920066e-06,
+      "loss": 0.9601,
+      "step": 135
+    },
+    {
+      "epoch": 1.8797909407665505,
+      "grad_norm": 4.705850601196289,
+      "learning_rate": 3.318736550257507e-06,
+      "loss": 0.9595,
+      "step": 136
+    },
+    {
+      "epoch": 1.8937282229965158,
+      "grad_norm": 3.335909128189087,
+      "learning_rate": 3.2427295700098385e-06,
+      "loss": 0.9889,
+      "step": 137
+    },
+    {
+      "epoch": 1.9076655052264808,
+      "grad_norm": 2.938302993774414,
+      "learning_rate": 3.1672375200194797e-06,
+      "loss": 0.9306,
+      "step": 138
+    },
+    {
+      "epoch": 1.9216027874564459,
+      "grad_norm": 3.15813946723938,
+      "learning_rate": 3.092277621590627e-06,
+      "loss": 0.9332,
+      "step": 139
+    },
+    {
+      "epoch": 1.9355400696864111,
+      "grad_norm": 2.869309902191162,
+      "learning_rate": 3.0178669746326567e-06,
+      "loss": 0.9496,
+      "step": 140
+    },
+    {
+      "epoch": 1.9494773519163764,
+      "grad_norm": 2.8482539653778076,
+      "learning_rate": 2.9440225537592728e-06,
+      "loss": 0.9406,
+      "step": 141
+    },
+    {
+      "epoch": 1.9634146341463414,
+      "grad_norm": 3.2523257732391357,
+      "learning_rate": 2.8707612044162595e-06,
+      "loss": 0.9377,
+      "step": 142
+    },
+    {
+      "epoch": 1.9773519163763065,
+      "grad_norm": 3.42722487449646,
+      "learning_rate": 2.7980996390386755e-06,
+      "loss": 0.9622,
+      "step": 143
+    },
+    {
+      "epoch": 1.9912891986062717,
+      "grad_norm": 3.1534297466278076,
+      "learning_rate": 2.7260544332383964e-06,
+      "loss": 0.9219,
+      "step": 144
+    },
+    {
+      "epoch": 2.005226480836237,
+      "grad_norm": 2.9020955562591553,
+      "learning_rate": 2.654642022022887e-06,
+      "loss": 0.9233,
+      "step": 145
+    },
+    {
+      "epoch": 2.0034843205574915,
+      "grad_norm": 6.1046247482299805,
+      "learning_rate": 2.5838786960460267e-06,
+      "loss": 0.9226,
+      "step": 146
+    },
+    {
+      "epoch": 2.0174216027874565,
+      "grad_norm": 2.791771411895752,
+      "learning_rate": 2.513780597891867e-06,
+      "loss": 0.8854,
+      "step": 147
+    },
+    {
+      "epoch": 2.0313588850174216,
+      "grad_norm": 4.039772033691406,
+      "learning_rate": 2.444363718392189e-06,
+      "loss": 0.9067,
+      "step": 148
+    },
+    {
+      "epoch": 2.0452961672473866,
+      "grad_norm": 3.059945821762085,
+      "learning_rate": 2.3756438929786434e-06,
+      "loss": 0.872,
+      "step": 149
+    },
+    {
+      "epoch": 2.059233449477352,
+      "grad_norm": 3.355379819869995,
+      "learning_rate": 2.3076367980703774e-06,
+      "loss": 0.8897,
+      "step": 150
+    },
+    {
+      "epoch": 2.073170731707317,
+      "grad_norm": 3.4992244243621826,
+      "learning_rate": 2.240357947497908e-06,
+      "loss": 0.9425,
+      "step": 151
+    },
+    {
+      "epoch": 2.087108013937282,
+      "grad_norm": 3.829111099243164,
+      "learning_rate": 2.173822688964094e-06,
+      "loss": 0.9141,
+      "step": 152
+    },
+    {
+      "epoch": 2.1010452961672472,
+      "grad_norm": 2.9267561435699463,
+      "learning_rate": 2.108046200543013e-06,
+      "loss": 0.9238,
+      "step": 153
+    },
+    {
+      "epoch": 2.1149825783972127,
+      "grad_norm": 3.307797908782959,
+      "learning_rate": 2.0430434872175245e-06,
+      "loss": 0.9014,
+      "step": 154
+    },
+    {
+      "epoch": 2.1289198606271778,
+      "grad_norm": 3.0536694526672363,
+      "learning_rate": 1.9788293774563163e-06,
+      "loss": 0.8967,
+      "step": 155
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 3.2300519943237305,
+      "learning_rate": 1.9154185198312327e-06,
+      "loss": 0.8817,
+      "step": 156
+    },
+    {
+      "epoch": 2.156794425087108,
+      "grad_norm": 3.410097599029541,
+      "learning_rate": 1.8528253796756277e-06,
+      "loss": 0.9151,
+      "step": 157
+    },
+    {
+      "epoch": 2.1707317073170733,
+      "grad_norm": 3.1198341846466064,
+      "learning_rate": 1.7910642357845122e-06,
+      "loss": 0.9359,
+      "step": 158
+    },
+    {
+      "epoch": 2.1846689895470384,
+      "grad_norm": 3.0908079147338867,
+      "learning_rate": 1.7301491771572808e-06,
+      "loss": 0.8697,
+      "step": 159
+    },
+    {
+      "epoch": 2.1986062717770034,
+      "grad_norm": 45.06842803955078,
+      "learning_rate": 1.67009409978371e-06,
+      "loss": 0.8753,
+      "step": 160
+    },
+    {
+      "epoch": 2.2125435540069684,
+      "grad_norm": 3.0929031372070312,
+      "learning_rate": 1.610912703473989e-06,
+      "loss": 0.9032,
+      "step": 161
+    },
+    {
+      "epoch": 2.226480836236934,
+      "grad_norm": 3.174290180206299,
+      "learning_rate": 1.5526184887335188e-06,
+      "loss": 0.9066,
+      "step": 162
+    },
+    {
+      "epoch": 2.240418118466899,
+      "grad_norm": 3.2078001499176025,
+      "learning_rate": 1.4952247536831645e-06,
+      "loss": 0.8793,
+      "step": 163
+    },
+    {
+      "epoch": 2.254355400696864,
+      "grad_norm": 3.8318631649017334,
+      "learning_rate": 1.438744591025668e-06,
+      "loss": 0.8881,
+      "step": 164
+    },
+    {
+      "epoch": 2.2682926829268295,
+      "grad_norm": 3.460146188735962,
+      "learning_rate": 1.3831908850589433e-06,
+      "loss": 0.9087,
+      "step": 165
+    },
+    {
+      "epoch": 2.2822299651567945,
+      "grad_norm": 3.1915969848632812,
+      "learning_rate": 1.3285763087368974e-06,
+      "loss": 0.9007,
+      "step": 166
+    },
+    {
+      "epoch": 2.2961672473867596,
+      "grad_norm": 3.0315561294555664,
+      "learning_rate": 1.2749133207784575e-06,
+      "loss": 0.879,
+      "step": 167
+    },
+    {
+      "epoch": 2.3101045296167246,
+      "grad_norm": 4.681447505950928,
+      "learning_rate": 1.2222141628254902e-06,
+      "loss": 0.9268,
+      "step": 168
+    },
+    {
+      "epoch": 2.3240418118466897,
+      "grad_norm": 2.946652889251709,
+      "learning_rate": 1.1704908566502246e-06,
+      "loss": 0.8952,
+      "step": 169
+    },
+    {
+      "epoch": 2.337979094076655,
+      "grad_norm": 2.944952964782715,
+      "learning_rate": 1.1197552014128314e-06,
+      "loss": 0.8807,
+      "step": 170
+    },
+    {
+      "epoch": 2.35191637630662,
+      "grad_norm": 3.2808735370635986,
+      "learning_rate": 1.0700187709697969e-06,
+      "loss": 0.8722,
+      "step": 171
+    },
+    {
+      "epoch": 2.3658536585365852,
+      "grad_norm": 3.887355327606201,
+      "learning_rate": 1.0212929112336848e-06,
+      "loss": 0.8863,
+      "step": 172
+    },
+    {
+      "epoch": 2.3797909407665507,
+      "grad_norm": 3.0687787532806396,
+      "learning_rate": 9.7358873758489e-07,
+      "loss": 0.9093,
+      "step": 173
+    },
+    {
+      "epoch": 2.3937282229965158,
+      "grad_norm": 2.890662431716919,
+      "learning_rate": 9.269171323360006e-07,
+      "loss": 0.8987,
+      "step": 174
+    },
+    {
+      "epoch": 2.407665505226481,
+      "grad_norm": 3.5224292278289795,
+      "learning_rate": 8.812887422493117e-07,
+      "loss": 0.9008,
+      "step": 175
+    },
+    {
+      "epoch": 2.421602787456446,
+      "grad_norm": 7.938294410705566,
+      "learning_rate": 8.367139761080734e-07,
+      "loss": 0.8774,
+      "step": 176
+    },
+    {
+      "epoch": 2.435540069686411,
+      "grad_norm": 3.240544557571411,
+      "learning_rate": 7.932030023420393e-07,
+      "loss": 0.9178,
+      "step": 177
+    },
+    {
+      "epoch": 2.4494773519163764,
+      "grad_norm": 3.17809796333313,
+      "learning_rate": 7.507657467078292e-07,
+      "loss": 0.8881,
+      "step": 178
+    },
+    {
+      "epoch": 2.4634146341463414,
+      "grad_norm": 3.075671911239624,
+      "learning_rate": 7.094118900246642e-07,
+      "loss": 0.94,
+      "step": 179
+    },
+    {
+      "epoch": 2.4773519163763065,
+      "grad_norm": 3.6002347469329834,
+      "learning_rate": 6.691508659659682e-07,
+      "loss": 0.8895,
+      "step": 180
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 213,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 36,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.164757741828047e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb5fabea60250d3a42d140aaad6152879cade63f57e1ddc910fe971895effcd
+size 7416

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)