Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/root/autodl-tmp/out/checkpoint-1902",
+  "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": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.3"
+}

latest

@@ -0,0 +1 @@
+global_step225

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89af8efae13b10e91766f41f0ae0e52f450126f73b6764e2879e9fd4879842f0
+size 4865522496

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a394bc09723b10ca630fbb380c29a1cd49c53e41032562420b1fb07729ee7a
+size 4907529424

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f68e7a2c6e6108d2cbba16f0fec7da3b679684e79f0713869c6caae33c07d9
+size 4907529456

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a90dbce4fb115fd8a2ec997f5f6515fd0a3c9e1a11cd7c17e92d3a7839909b83
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea3f4d529567fbe12cf12bb9c2da3246ccd23f997e71c0d1efb068affbd6e13
+size 4907496272

model.safetensors.index.json

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

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5670d88ebc88a22600882bf1d00cfe253f1c92a0e61c826395faa3de3b2ce196
+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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:868ad0021d8fcb7c1da1debcabd7443fccd21697a51abc03b3c1abb52c64b91e
+size 17078592

trainer_state.json

@@ -0,0 +1,1608 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0044444444444444444,
+      "grad_norm": 7.197563171386719,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 1.3915,
+      "step": 1
+    },
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 7.682923793792725,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.3854,
+      "step": 2
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 9.152216911315918,
+      "learning_rate": 7.5e-07,
+      "loss": 1.3159,
+      "step": 3
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 9.388493537902832,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.3236,
+      "step": 4
+    },
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 12.188794136047363,
+      "learning_rate": 1.25e-06,
+      "loss": 1.3502,
+      "step": 5
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 12.245216369628906,
+      "learning_rate": 1.5e-06,
+      "loss": 1.404,
+      "step": 6
+    },
+    {
+      "epoch": 0.03111111111111111,
+      "grad_norm": 19.210506439208984,
+      "learning_rate": 1.75e-06,
+      "loss": 1.4199,
+      "step": 7
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 9.991368293762207,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.3316,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.724348545074463,
+      "learning_rate": 2.25e-06,
+      "loss": 1.4482,
+      "step": 9
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 8.962543487548828,
+      "learning_rate": 2.5e-06,
+      "loss": 1.29,
+      "step": 10
+    },
+    {
+      "epoch": 0.04888888888888889,
+      "grad_norm": 7.128359317779541,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 1.3139,
+      "step": 11
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 11.580962181091309,
+      "learning_rate": 3e-06,
+      "loss": 1.3238,
+      "step": 12
+    },
+    {
+      "epoch": 0.057777777777777775,
+      "grad_norm": 8.380171775817871,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 1.3434,
+      "step": 13
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 5.92144250869751,
+      "learning_rate": 3.5e-06,
+      "loss": 1.2896,
+      "step": 14
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 8.112162590026855,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.2117,
+      "step": 15
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 3.5406394004821777,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2094,
+      "step": 16
+    },
+    {
+      "epoch": 0.07555555555555556,
+      "grad_norm": 22.047605514526367,
+      "learning_rate": 4.25e-06,
+      "loss": 1.2027,
+      "step": 17
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.793862819671631,
+      "learning_rate": 4.5e-06,
+      "loss": 1.2434,
+      "step": 18
+    },
+    {
+      "epoch": 0.08444444444444445,
+      "grad_norm": 9.382174491882324,
+      "learning_rate": 4.75e-06,
+      "loss": 1.3183,
+      "step": 19
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 5.871135234832764,
+      "learning_rate": 5e-06,
+      "loss": 1.2432,
+      "step": 20
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 17.656475067138672,
+      "learning_rate": 5.2500000000000006e-06,
+      "loss": 1.1843,
+      "step": 21
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 10.098402976989746,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 1.3401,
+      "step": 22
+    },
+    {
+      "epoch": 0.10222222222222223,
+      "grad_norm": 23.264266967773438,
+      "learning_rate": 5.75e-06,
+      "loss": 1.3025,
+      "step": 23
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 4.140642166137695,
+      "learning_rate": 6e-06,
+      "loss": 1.2141,
+      "step": 24
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 6.262714862823486,
+      "learning_rate": 6.25e-06,
+      "loss": 1.2665,
+      "step": 25
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 6.946407794952393,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 1.1989,
+      "step": 26
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.5363879203796387,
+      "learning_rate": 6.750000000000001e-06,
+      "loss": 1.1771,
+      "step": 27
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 3.964658737182617,
+      "learning_rate": 7e-06,
+      "loss": 1.2362,
+      "step": 28
+    },
+    {
+      "epoch": 0.1288888888888889,
+      "grad_norm": 2.513711452484131,
+      "learning_rate": 7.25e-06,
+      "loss": 1.2203,
+      "step": 29
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 2.6071319580078125,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.167,
+      "step": 30
+    },
+    {
+      "epoch": 0.13777777777777778,
+      "grad_norm": 3.0134849548339844,
+      "learning_rate": 7.75e-06,
+      "loss": 1.2139,
+      "step": 31
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 2.4809670448303223,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.1603,
+      "step": 32
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 3.1294925212860107,
+      "learning_rate": 8.25e-06,
+      "loss": 1.1922,
+      "step": 33
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 2.703998565673828,
+      "learning_rate": 8.5e-06,
+      "loss": 1.1858,
+      "step": 34
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 4.653899192810059,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.2678,
+      "step": 35
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.976705312728882,
+      "learning_rate": 9e-06,
+      "loss": 1.2004,
+      "step": 36
+    },
+    {
+      "epoch": 0.16444444444444445,
+      "grad_norm": 3.332261323928833,
+      "learning_rate": 9.250000000000001e-06,
+      "loss": 1.2128,
+      "step": 37
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 2.7455172538757324,
+      "learning_rate": 9.5e-06,
+      "loss": 1.2348,
+      "step": 38
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 2.5534517765045166,
+      "learning_rate": 9.75e-06,
+      "loss": 1.1752,
+      "step": 39
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 2.2505180835723877,
+      "learning_rate": 1e-05,
+      "loss": 1.1248,
+      "step": 40
+    },
+    {
+      "epoch": 0.18222222222222223,
+      "grad_norm": 3.083693265914917,
+      "learning_rate": 9.999853218975136e-06,
+      "loss": 1.1466,
+      "step": 41
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 2.871704339981079,
+      "learning_rate": 9.99941288451841e-06,
+      "loss": 1.1622,
+      "step": 42
+    },
+    {
+      "epoch": 0.19111111111111112,
+      "grad_norm": 2.9086086750030518,
+      "learning_rate": 9.998679022482916e-06,
+      "loss": 1.1584,
+      "step": 43
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 2.8458251953125,
+      "learning_rate": 9.997651675955467e-06,
+      "loss": 1.1556,
+      "step": 44
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.2609152793884277,
+      "learning_rate": 9.99633090525405e-06,
+      "loss": 1.1991,
+      "step": 45
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 14.039426803588867,
+      "learning_rate": 9.9947167879243e-06,
+      "loss": 1.1318,
+      "step": 46
+    },
+    {
+      "epoch": 0.2088888888888889,
+      "grad_norm": 3.4546499252319336,
+      "learning_rate": 9.992809418734932e-06,
+      "loss": 1.1987,
+      "step": 47
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 3.3863046169281006,
+      "learning_rate": 9.99060890967219e-06,
+      "loss": 1.171,
+      "step": 48
+    },
+    {
+      "epoch": 0.21777777777777776,
+      "grad_norm": 2.217785596847534,
+      "learning_rate": 9.988115389933263e-06,
+      "loss": 1.124,
+      "step": 49
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 3.8226356506347656,
+      "learning_rate": 9.985329005918702e-06,
+      "loss": 1.2048,
+      "step": 50
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 4.5612688064575195,
+      "learning_rate": 9.982249921223833e-06,
+      "loss": 1.1899,
+      "step": 51
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 3.4833076000213623,
+      "learning_rate": 9.978878316629132e-06,
+      "loss": 1.1745,
+      "step": 52
+    },
+    {
+      "epoch": 0.23555555555555555,
+      "grad_norm": 2.259718894958496,
+      "learning_rate": 9.975214390089637e-06,
+      "loss": 1.1016,
+      "step": 53
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.242814779281616,
+      "learning_rate": 9.9712583567233e-06,
+      "loss": 1.1984,
+      "step": 54
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 4.208090305328369,
+      "learning_rate": 9.967010448798376e-06,
+      "loss": 1.1899,
+      "step": 55
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 2.8487319946289062,
+      "learning_rate": 9.962470915719775e-06,
+      "loss": 1.1735,
+      "step": 56
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 2.4001946449279785,
+      "learning_rate": 9.957640024014426e-06,
+      "loss": 1.1199,
+      "step": 57
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 4.717513561248779,
+      "learning_rate": 9.952518057315624e-06,
+      "loss": 1.1234,
+      "step": 58
+    },
+    {
+      "epoch": 0.26222222222222225,
+      "grad_norm": 2.7141494750976562,
+      "learning_rate": 9.947105316346372e-06,
+      "loss": 1.1619,
+      "step": 59
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 2.610142946243286,
+      "learning_rate": 9.941402118901743e-06,
+      "loss": 1.2141,
+      "step": 60
+    },
+    {
+      "epoch": 0.27111111111111114,
+      "grad_norm": 3.9055914878845215,
+      "learning_rate": 9.9354087998302e-06,
+      "loss": 1.1778,
+      "step": 61
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 3.3144619464874268,
+      "learning_rate": 9.929125711013952e-06,
+      "loss": 1.1574,
+      "step": 62
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.429931640625,
+      "learning_rate": 9.922553221348281e-06,
+      "loss": 1.1524,
+      "step": 63
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 2.495755195617676,
+      "learning_rate": 9.915691716719899e-06,
+      "loss": 1.1692,
+      "step": 64
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 1.96566903591156,
+      "learning_rate": 9.908541599984276e-06,
+      "loss": 1.0634,
+      "step": 65
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 2.161886215209961,
+      "learning_rate": 9.901103290941996e-06,
+      "loss": 1.1318,
+      "step": 66
+    },
+    {
+      "epoch": 0.29777777777777775,
+      "grad_norm": 2.408609390258789,
+      "learning_rate": 9.893377226314113e-06,
+      "loss": 1.118,
+      "step": 67
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 2.3472368717193604,
+      "learning_rate": 9.885363859716497e-06,
+      "loss": 1.1064,
+      "step": 68
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 4.991092681884766,
+      "learning_rate": 9.877063661633213e-06,
+      "loss": 1.1629,
+      "step": 69
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 2.2165753841400146,
+      "learning_rate": 9.868477119388897e-06,
+      "loss": 1.0692,
+      "step": 70
+    },
+    {
+      "epoch": 0.31555555555555553,
+      "grad_norm": 3.0987343788146973,
+      "learning_rate": 9.859604737120131e-06,
+      "loss": 1.1878,
+      "step": 71
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.5139403343200684,
+      "learning_rate": 9.850447035745868e-06,
+      "loss": 1.1443,
+      "step": 72
+    },
+    {
+      "epoch": 0.3244444444444444,
+      "grad_norm": 2.9309511184692383,
+      "learning_rate": 9.841004552936817e-06,
+      "loss": 1.1986,
+      "step": 73
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 2.642705202102661,
+      "learning_rate": 9.831277843083904e-06,
+      "loss": 1.1076,
+      "step": 74
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.53140926361084,
+      "learning_rate": 9.821267477265705e-06,
+      "loss": 1.1432,
+      "step": 75
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 3.0417535305023193,
+      "learning_rate": 9.810974043214923e-06,
+      "loss": 1.1889,
+      "step": 76
+    },
+    {
+      "epoch": 0.3422222222222222,
+      "grad_norm": 2.1667232513427734,
+      "learning_rate": 9.800398145283874e-06,
+      "loss": 1.1088,
+      "step": 77
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 2.451881170272827,
+      "learning_rate": 9.789540404409017e-06,
+      "loss": 1.125,
+      "step": 78
+    },
+    {
+      "epoch": 0.3511111111111111,
+      "grad_norm": 5.966605186462402,
+      "learning_rate": 9.778401458074482e-06,
+      "loss": 1.2031,
+      "step": 79
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 2.767612934112549,
+      "learning_rate": 9.766981960274653e-06,
+      "loss": 1.1299,
+      "step": 80
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.8305821418762207,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 1.106,
+      "step": 81
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 2.256387710571289,
+      "learning_rate": 9.74330400857655e-06,
+      "loss": 1.1994,
+      "step": 82
+    },
+    {
+      "epoch": 0.3688888888888889,
+      "grad_norm": 2.9722063541412354,
+      "learning_rate": 9.731046944867883e-06,
+      "loss": 1.1182,
+      "step": 83
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 3.528620958328247,
+      "learning_rate": 9.718512109991516e-06,
+      "loss": 1.2216,
+      "step": 84
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 2.0519301891326904,
+      "learning_rate": 9.705700239897809e-06,
+      "loss": 1.1228,
+      "step": 85
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 2.4317550659179688,
+      "learning_rate": 9.692612086802536e-06,
+      "loss": 1.164,
+      "step": 86
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 3.0390419960021973,
+      "learning_rate": 9.679248419142704e-06,
+      "loss": 1.2052,
+      "step": 87
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 2.4871633052825928,
+      "learning_rate": 9.665610021531447e-06,
+      "loss": 1.1605,
+      "step": 88
+    },
+    {
+      "epoch": 0.39555555555555555,
+      "grad_norm": 3.762112617492676,
+      "learning_rate": 9.651697694711959e-06,
+      "loss": 1.1504,
+      "step": 89
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 18.623851776123047,
+      "learning_rate": 9.637512255510475e-06,
+      "loss": 1.173,
+      "step": 90
+    },
+    {
+      "epoch": 0.40444444444444444,
+      "grad_norm": 2.8003592491149902,
+      "learning_rate": 9.623054536788315e-06,
+      "loss": 1.1239,
+      "step": 91
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 2.560473918914795,
+      "learning_rate": 9.608325387392988e-06,
+      "loss": 1.1203,
+      "step": 92
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 1.885018229484558,
+      "learning_rate": 9.593325672108352e-06,
+      "loss": 1.142,
+      "step": 93
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 4.514256000518799,
+      "learning_rate": 9.578056271603837e-06,
+      "loss": 1.1398,
+      "step": 94
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 2.7508609294891357,
+      "learning_rate": 9.562518082382751e-06,
+      "loss": 1.1355,
+      "step": 95
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 2.800530433654785,
+      "learning_rate": 9.546712016729625e-06,
+      "loss": 1.1512,
+      "step": 96
+    },
+    {
+      "epoch": 0.4311111111111111,
+      "grad_norm": 3.151304006576538,
+      "learning_rate": 9.530639002656665e-06,
+      "loss": 1.1215,
+      "step": 97
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 2.7462916374206543,
+      "learning_rate": 9.514299983849267e-06,
+      "loss": 1.1412,
+      "step": 98
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.8580820560455322,
+      "learning_rate": 9.497695919610595e-06,
+      "loss": 1.088,
+      "step": 99
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 2.2820510864257812,
+      "learning_rate": 9.480827784805278e-06,
+      "loss": 1.1844,
+      "step": 100
+    },
+    {
+      "epoch": 0.4488888888888889,
+      "grad_norm": 1.8663792610168457,
+      "learning_rate": 9.463696569802163e-06,
+      "loss": 1.1218,
+      "step": 101
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 2.3818678855895996,
+      "learning_rate": 9.446303280416167e-06,
+      "loss": 1.186,
+      "step": 102
+    },
+    {
+      "epoch": 0.4577777777777778,
+      "grad_norm": 1.8850212097167969,
+      "learning_rate": 9.428648937849227e-06,
+      "loss": 1.0865,
+      "step": 103
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 2.012317419052124,
+      "learning_rate": 9.410734578630344e-06,
+      "loss": 1.0468,
+      "step": 104
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 2.9131033420562744,
+      "learning_rate": 9.392561254554712e-06,
+      "loss": 1.1631,
+      "step": 105
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 3.2192587852478027,
+      "learning_rate": 9.374130032621993e-06,
+      "loss": 1.1361,
+      "step": 106
+    },
+    {
+      "epoch": 0.47555555555555556,
+      "grad_norm": 2.818880319595337,
+      "learning_rate": 9.355441994973639e-06,
+      "loss": 1.1578,
+      "step": 107
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.6746394634246826,
+      "learning_rate": 9.336498238829383e-06,
+      "loss": 1.1542,
+      "step": 108
+    },
+    {
+      "epoch": 0.48444444444444446,
+      "grad_norm": 3.4095306396484375,
+      "learning_rate": 9.317299876422797e-06,
+      "loss": 1.142,
+      "step": 109
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 2.7571191787719727,
+      "learning_rate": 9.297848034936007e-06,
+      "loss": 1.1133,
+      "step": 110
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 2.1086196899414062,
+      "learning_rate": 9.278143856433503e-06,
+      "loss": 1.1164,
+      "step": 111
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 2.419229507446289,
+      "learning_rate": 9.258188497795093e-06,
+      "loss": 1.1713,
+      "step": 112
+    },
+    {
+      "epoch": 0.5022222222222222,
+      "grad_norm": 2.4053385257720947,
+      "learning_rate": 9.237983130647973e-06,
+      "loss": 1.1185,
+      "step": 113
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 2.489058017730713,
+      "learning_rate": 9.217528941297942e-06,
+      "loss": 1.168,
+      "step": 114
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 2.2254421710968018,
+      "learning_rate": 9.196827130659752e-06,
+      "loss": 1.1715,
+      "step": 115
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 2.17338228225708,
+      "learning_rate": 9.175878914186591e-06,
+      "loss": 1.1486,
+      "step": 116
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.704568386077881,
+      "learning_rate": 9.154685521798736e-06,
+      "loss": 1.2477,
+      "step": 117
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 2.340566396713257,
+      "learning_rate": 9.13324819781133e-06,
+      "loss": 1.1748,
+      "step": 118
+    },
+    {
+      "epoch": 0.5288888888888889,
+      "grad_norm": 2.876037359237671,
+      "learning_rate": 9.111568200861324e-06,
+      "loss": 1.1003,
+      "step": 119
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.6906325817108154,
+      "learning_rate": 9.089646803833589e-06,
+      "loss": 1.0845,
+      "step": 120
+    },
+    {
+      "epoch": 0.5377777777777778,
+      "grad_norm": 2.1755309104919434,
+      "learning_rate": 9.067485293786173e-06,
+      "loss": 1.2046,
+      "step": 121
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 2.471137046813965,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 1.1749,
+      "step": 122
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 2.135450839996338,
+      "learning_rate": 9.022447153276169e-06,
+      "loss": 1.1702,
+      "step": 123
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 2.0650486946105957,
+      "learning_rate": 8.99957316711135e-06,
+      "loss": 1.1009,
+      "step": 124
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 2.5196189880371094,
+      "learning_rate": 8.976464356367133e-06,
+      "loss": 1.1063,
+      "step": 125
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.1774826049804688,
+      "learning_rate": 8.95312207781749e-06,
+      "loss": 1.1902,
+      "step": 126
+    },
+    {
+      "epoch": 0.5644444444444444,
+      "grad_norm": 2.327805757522583,
+      "learning_rate": 8.929547701943849e-06,
+      "loss": 1.1152,
+      "step": 127
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 3.271408796310425,
+      "learning_rate": 8.905742612854628e-06,
+      "loss": 1.1846,
+      "step": 128
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 2.898059844970703,
+      "learning_rate": 8.881708208203977e-06,
+      "loss": 1.16,
+      "step": 129
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 2.6147210597991943,
+      "learning_rate": 8.857445899109716e-06,
+      "loss": 1.12,
+      "step": 130
+    },
+    {
+      "epoch": 0.5822222222222222,
+      "grad_norm": 3.8312957286834717,
+      "learning_rate": 8.832957110070482e-06,
+      "loss": 1.1535,
+      "step": 131
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 3.3056952953338623,
+      "learning_rate": 8.808243278882094e-06,
+      "loss": 1.0797,
+      "step": 132
+    },
+    {
+      "epoch": 0.5911111111111111,
+      "grad_norm": 3.1664161682128906,
+      "learning_rate": 8.783305856553143e-06,
+      "loss": 1.1774,
+      "step": 133
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 2.9546732902526855,
+      "learning_rate": 8.758146307219793e-06,
+      "loss": 1.213,
+      "step": 134
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.9610460996627808,
+      "learning_rate": 8.732766108059814e-06,
+      "loss": 1.167,
+      "step": 135
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 2.216212749481201,
+      "learning_rate": 8.707166749205867e-06,
+      "loss": 1.0953,
+      "step": 136
+    },
+    {
+      "epoch": 0.6088888888888889,
+      "grad_norm": 5.400648593902588,
+      "learning_rate": 8.681349733658002e-06,
+      "loss": 1.085,
+      "step": 137
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 2.8066205978393555,
+      "learning_rate": 8.65531657719542e-06,
+      "loss": 1.1447,
+      "step": 138
+    },
+    {
+      "epoch": 0.6177777777777778,
+      "grad_norm": 3.9573774337768555,
+      "learning_rate": 8.629068808287476e-06,
+      "loss": 1.1372,
+      "step": 139
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 2.352977991104126,
+      "learning_rate": 8.602607968003935e-06,
+      "loss": 1.1005,
+      "step": 140
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 3.9835476875305176,
+      "learning_rate": 8.575935609924505e-06,
+      "loss": 1.1974,
+      "step": 141
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 2.4645981788635254,
+      "learning_rate": 8.549053300047602e-06,
+      "loss": 1.0944,
+      "step": 142
+    },
+    {
+      "epoch": 0.6355555555555555,
+      "grad_norm": 1.7835776805877686,
+      "learning_rate": 8.521962616698428e-06,
+      "loss": 1.1516,
+      "step": 143
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.5801022052764893,
+      "learning_rate": 8.494665150436288e-06,
+      "loss": 1.1421,
+      "step": 144
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 2.424285650253296,
+      "learning_rate": 8.467162503961209e-06,
+      "loss": 1.147,
+      "step": 145
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 2.7262933254241943,
+      "learning_rate": 8.439456292019849e-06,
+      "loss": 1.1269,
+      "step": 146
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 1.9822264909744263,
+      "learning_rate": 8.411548141310683e-06,
+      "loss": 1.1161,
+      "step": 147
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 1.773859977722168,
+      "learning_rate": 8.383439690388491e-06,
+      "loss": 1.0834,
+      "step": 148
+    },
+    {
+      "epoch": 0.6622222222222223,
+      "grad_norm": 2.605008363723755,
+      "learning_rate": 8.35513258956817e-06,
+      "loss": 1.1789,
+      "step": 149
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.594944477081299,
+      "learning_rate": 8.326628500827826e-06,
+      "loss": 1.1489,
+      "step": 150
+    },
+    {
+      "epoch": 0.6711111111111111,
+      "grad_norm": 2.652006149291992,
+      "learning_rate": 8.297929097711207e-06,
+      "loss": 1.1225,
+      "step": 151
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 3.7691638469696045,
+      "learning_rate": 8.269036065229426e-06,
+      "loss": 1.2454,
+      "step": 152
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.865312337875366,
+      "learning_rate": 8.239951099762058e-06,
+      "loss": 1.1437,
+      "step": 153
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 2.1165366172790527,
+      "learning_rate": 8.210675908957513e-06,
+      "loss": 1.1353,
+      "step": 154
+    },
+    {
+      "epoch": 0.6888888888888889,
+      "grad_norm": 2.63763427734375,
+      "learning_rate": 8.1812122116328e-06,
+      "loss": 1.1393,
+      "step": 155
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 3.102932929992676,
+      "learning_rate": 8.151561737672591e-06,
+      "loss": 1.1366,
+      "step": 156
+    },
+    {
+      "epoch": 0.6977777777777778,
+      "grad_norm": 3.0296387672424316,
+      "learning_rate": 8.12172622792767e-06,
+      "loss": 1.0632,
+      "step": 157
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 2.647352933883667,
+      "learning_rate": 8.091707434112717e-06,
+      "loss": 1.0779,
+      "step": 158
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 3.4690728187561035,
+      "learning_rate": 8.061507118703456e-06,
+      "loss": 1.187,
+      "step": 159
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 2.914712905883789,
+      "learning_rate": 8.031127054833192e-06,
+      "loss": 1.1118,
+      "step": 160
+    },
+    {
+      "epoch": 0.7155555555555555,
+      "grad_norm": 2.348532199859619,
+      "learning_rate": 8.000569026188684e-06,
+      "loss": 1.1566,
+      "step": 161
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.2149953842163086,
+      "learning_rate": 7.969834826905441e-06,
+      "loss": 1.1446,
+      "step": 162
+    },
+    {
+      "epoch": 0.7244444444444444,
+      "grad_norm": 1.8673402070999146,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 1.1512,
+      "step": 163
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 2.2096667289733887,
+      "learning_rate": 7.90784514457583e-06,
+      "loss": 1.0488,
+      "step": 164
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 2.886953592300415,
+      "learning_rate": 7.876593301093104e-06,
+      "loss": 1.1158,
+      "step": 165
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 3.801467180252075,
+      "learning_rate": 7.845172565885237e-06,
+      "loss": 1.1106,
+      "step": 166
+    },
+    {
+      "epoch": 0.7422222222222222,
+      "grad_norm": 2.3027687072753906,
+      "learning_rate": 7.813584783739314e-06,
+      "loss": 1.1146,
+      "step": 167
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 3.938884973526001,
+      "learning_rate": 7.78183180925015e-06,
+      "loss": 1.1328,
+      "step": 168
+    },
+    {
+      "epoch": 0.7511111111111111,
+      "grad_norm": 2.19864821434021,
+      "learning_rate": 7.749915506711402e-06,
+      "loss": 1.1701,
+      "step": 169
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 4.781134128570557,
+      "learning_rate": 7.717837750006106e-06,
+      "loss": 1.1709,
+      "step": 170
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.3147037029266357,
+      "learning_rate": 7.685600422496666e-06,
+      "loss": 1.0917,
+      "step": 171
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 3.0294220447540283,
+      "learning_rate": 7.653205416914267e-06,
+      "loss": 1.1209,
+      "step": 172
+    },
+    {
+      "epoch": 0.7688888888888888,
+      "grad_norm": 1.97251296043396,
+      "learning_rate": 7.620654635247762e-06,
+      "loss": 1.0584,
+      "step": 173
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 4.131389141082764,
+      "learning_rate": 7.587949988631982e-06,
+      "loss": 1.171,
+      "step": 174
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 2.2693028450012207,
+      "learning_rate": 7.555093397235553e-06,
+      "loss": 1.1358,
+      "step": 175
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 2.0202383995056152,
+      "learning_rate": 7.5220867901481335e-06,
+      "loss": 1.1823,
+      "step": 176
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 2.4606690406799316,
+      "learning_rate": 7.488932105267171e-06,
+      "loss": 1.0837,
+      "step": 177
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 1.997691035270691,
+      "learning_rate": 7.455631289184117e-06,
+      "loss": 1.1091,
+      "step": 178
+    },
+    {
+      "epoch": 0.7955555555555556,
+      "grad_norm": 2.143990993499756,
+      "learning_rate": 7.422186297070136e-06,
+      "loss": 1.1174,
+      "step": 179
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.189858913421631,
+      "learning_rate": 7.388599092561315e-06,
+      "loss": 1.1757,
+      "step": 180
+    },
+    {
+      "epoch": 0.8044444444444444,
+      "grad_norm": 1.796143889427185,
+      "learning_rate": 7.3548716476433756e-06,
+      "loss": 1.1114,
+      "step": 181
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 1.725069284439087,
+      "learning_rate": 7.32100594253589e-06,
+      "loss": 1.0613,
+      "step": 182
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 2.555976152420044,
+      "learning_rate": 7.2870039655760186e-06,
+      "loss": 1.0673,
+      "step": 183
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 2.573438882827759,
+      "learning_rate": 7.252867713101772e-06,
+      "loss": 1.1355,
+      "step": 184
+    },
+    {
+      "epoch": 0.8222222222222222,
+      "grad_norm": 2.54061222076416,
+      "learning_rate": 7.218599189334799e-06,
+      "loss": 1.1363,
+      "step": 185
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 2.8169195652008057,
+      "learning_rate": 7.184200406262717e-06,
+      "loss": 1.0974,
+      "step": 186
+    },
+    {
+      "epoch": 0.8311111111111111,
+      "grad_norm": 10.035176277160645,
+      "learning_rate": 7.149673383520978e-06,
+      "loss": 1.1138,
+      "step": 187
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 3.066096544265747,
+      "learning_rate": 7.115020148274294e-06,
+      "loss": 1.1197,
+      "step": 188
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.641267776489258,
+      "learning_rate": 7.080242735097622e-06,
+      "loss": 1.1566,
+      "step": 189
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 3.2539026737213135,
+      "learning_rate": 7.045343185856701e-06,
+      "loss": 1.0788,
+      "step": 190
+    },
+    {
+      "epoch": 0.8488888888888889,
+      "grad_norm": 3.5505993366241455,
+      "learning_rate": 7.01032354958817e-06,
+      "loss": 1.1023,
+      "step": 191
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 2.408964157104492,
+      "learning_rate": 6.975185882379272e-06,
+      "loss": 1.1087,
+      "step": 192
+    },
+    {
+      "epoch": 0.8577777777777778,
+      "grad_norm": 2.967325210571289,
+      "learning_rate": 6.939932247247126e-06,
+      "loss": 1.0942,
+      "step": 193
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 1.98670494556427,
+      "learning_rate": 6.9045647140176145e-06,
+      "loss": 1.1288,
+      "step": 194
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 2.2912962436676025,
+      "learning_rate": 6.869085359203844e-06,
+      "loss": 1.1148,
+      "step": 195
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 2.9244866371154785,
+      "learning_rate": 6.833496265884241e-06,
+      "loss": 1.1047,
+      "step": 196
+    },
+    {
+      "epoch": 0.8755555555555555,
+      "grad_norm": 3.550187349319458,
+      "learning_rate": 6.79779952358024e-06,
+      "loss": 1.1299,
+      "step": 197
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.448188066482544,
+      "learning_rate": 6.76199722813361e-06,
+      "loss": 1.0937,
+      "step": 198
+    },
+    {
+      "epoch": 0.8844444444444445,
+      "grad_norm": 2.392951488494873,
+      "learning_rate": 6.726091481583396e-06,
+      "loss": 1.1075,
+      "step": 199
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.764351487159729,
+      "learning_rate": 6.690084392042514e-06,
+      "loss": 1.0864,
+      "step": 200
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 2.1497156620025635,
+      "learning_rate": 6.653978073573962e-06,
+      "loss": 1.0698,
+      "step": 201
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 2.4440653324127197,
+      "learning_rate": 6.6177746460667124e-06,
+      "loss": 1.1207,
+      "step": 202
+    },
+    {
+      "epoch": 0.9022222222222223,
+      "grad_norm": 5.237727165222168,
+      "learning_rate": 6.581476235111244e-06,
+      "loss": 1.2957,
+      "step": 203
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 2.54868745803833,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 1.1072,
+      "step": 204
+    },
+    {
+      "epoch": 0.9111111111111111,
+      "grad_norm": 2.269233465194702,
+      "learning_rate": 6.508602992975963e-06,
+      "loss": 1.096,
+      "step": 205
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 1.835715413093567,
+      "learning_rate": 6.472032440359817e-06,
+      "loss": 1.0722,
+      "step": 206
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.5577235221862793,
+      "learning_rate": 6.43537546117158e-06,
+      "loss": 1.1194,
+      "step": 207
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 2.0571846961975098,
+      "learning_rate": 6.398634207630841e-06,
+      "loss": 1.1089,
+      "step": 208
+    },
+    {
+      "epoch": 0.9288888888888889,
+      "grad_norm": 3.0140180587768555,
+      "learning_rate": 6.361810836905138e-06,
+      "loss": 1.2144,
+      "step": 209
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 2.731870412826538,
+      "learning_rate": 6.32490751098331e-06,
+      "loss": 1.1493,
+      "step": 210
+    },
+    {
+      "epoch": 0.9377777777777778,
+      "grad_norm": 2.427889347076416,
+      "learning_rate": 6.287926396548556e-06,
+      "loss": 1.0504,
+      "step": 211
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 2.487750291824341,
+      "learning_rate": 6.250869664851226e-06,
+      "loss": 1.0908,
+      "step": 212
+    },
+    {
+      "epoch": 0.9466666666666667,
+      "grad_norm": 2.3912594318389893,
+      "learning_rate": 6.213739491581347e-06,
+      "loss": 1.1216,
+      "step": 213
+    },
+    {
+      "epoch": 0.9511111111111111,
+      "grad_norm": 3.4675991535186768,
+      "learning_rate": 6.176538056740871e-06,
+      "loss": 1.0171,
+      "step": 214
+    },
+    {
+      "epoch": 0.9555555555555556,
+      "grad_norm": 1.81716787815094,
+      "learning_rate": 6.139267544515689e-06,
+      "loss": 1.044,
+      "step": 215
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.6640546321868896,
+      "learning_rate": 6.101930143147395e-06,
+      "loss": 1.1029,
+      "step": 216
+    },
+    {
+      "epoch": 0.9644444444444444,
+      "grad_norm": 2.501460313796997,
+      "learning_rate": 6.064528044804805e-06,
+      "loss": 1.1141,
+      "step": 217
+    },
+    {
+      "epoch": 0.9688888888888889,
+      "grad_norm": 2.3960464000701904,
+      "learning_rate": 6.0270634454552494e-06,
+      "loss": 1.0526,
+      "step": 218
+    },
+    {
+      "epoch": 0.9733333333333334,
+      "grad_norm": 2.989225387573242,
+      "learning_rate": 5.989538544735644e-06,
+      "loss": 1.1437,
+      "step": 219
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.963538646697998,
+      "learning_rate": 5.951955545823342e-06,
+      "loss": 1.0998,
+      "step": 220
+    },
+    {
+      "epoch": 0.9822222222222222,
+      "grad_norm": 2.2665040493011475,
+      "learning_rate": 5.9143166553067846e-06,
+      "loss": 1.1062,
+      "step": 221
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 2.201535701751709,
+      "learning_rate": 5.87662408305594e-06,
+      "loss": 1.042,
+      "step": 222
+    },
+    {
+      "epoch": 0.9911111111111112,
+      "grad_norm": 2.513442039489746,
+      "learning_rate": 5.8388800420925616e-06,
+      "loss": 1.0733,
+      "step": 223
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 2.0468199253082275,
+      "learning_rate": 5.801086748460255e-06,
+      "loss": 1.1171,
+      "step": 224
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.2198939323425293,
+      "learning_rate": 5.763246421094373e-06,
+      "loss": 1.1027,
+      "step": 225
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 225,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.193854425949798e+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:a3207917e04aabf6853d89ab3b2aeca98a0b9185a3edbbbfdb5d657f1c5252af
+size 8568

zero_to_fp32.py

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