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 +1,26 @@
+{
+  "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": 32768,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "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": "4.51.3"
+}

latest

@@ -0,0 +1 @@
+global_step229

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2932c6ca76193bb2cb1ba5909551091e22e4e20c2fa2c36cca3cd77c054a8263
+size 4781571736

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9415df40b10227fea2e12091ed9f38120b074d349c1f6bfd4d6b9adb6e3fb5
+size 4781592784

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af053515fb7a368798be753a823b71a731ccefa442cfbe8de37d2d17d0ffc505
+size 4781592800

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fb54f34865ce4d04275096a9896b0d0726d6e0e96e7a42d1c2ea127a81cc69
+size 4886471600

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95cc51fba7765b840a057355427d4079b6b1735f2b81212a3ac138c3dcc03a93
+size 4781592824

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8068b6f2e09e4efedcd8475fad5b919b73c3ea2b82b72b9f36afd263b942ff97
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d462646ab870d0d28c78e0a06034b8a5b84c6fe59a4899a20604f8639d16deed
+size 4886471600

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b3104bbe969a741bc5872de72a09f1aa0c12cd1ae12336110234541cfd62ee
+size 4781592824

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3885a22e297056b12307f3dfe905b2cc73433faecc7134b828279bfe5cdd227
+size 4781592816

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1abc985dff36d45cf513a47fd3a165a9487f5ecc5e81aa47536a6a94a86584
+size 3900777072

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 47144806400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00010-of-00010.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.norm.weight": "model-00010-of-00010.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f469fb6a869fe76761e1194ed0a7948ca397689bbc8ac0a9ea85a077fd50929
+size 16389

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e31efd49e7c2510fff79f966c879db58740a4187714c13003ffa53d0d441c5
+size 16389

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755aba68d004de8b7239e4451f96d8aaad4274ed7f03ec57d204f73d7b768a54
+size 16389

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e57948798e97ec4bd65e4f2bab0090fd58ab95e9d421be20702021446d2636
+size 16389

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7930f1c6dd64fe161f166b710675bea007029bf2a54e835287c8517c8d61b7e
+size 16389

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c098b3d19df4c6a4261105183eb9357e2715d784d681c1426e4bb88c847c317
+size 16389

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c914eacfcdfa6cf1a18175490235b8bf14f4521cc8ebda28a827fb8611e2958d
+size 16389

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad02907448ab52a0de6407d8cc85b4523850947654c14a8ca1a3772f6c8c9cf8
+size 16389

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295bdcf639363dd785518768a76e7a8e159d706da63702bed87e48e057b7a525
+size 1465

special_tokens_map.json

@@ -0,0 +1,1032 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "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:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

trainer_state.json

@@ -0,0 +1,1682 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.944206008583691,
+  "eval_steps": 500,
+  "global_step": 232,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017167381974248927,
+      "grad_norm": 24.894664359139377,
+      "learning_rate": 0.0,
+      "loss": 2.0734,
+      "step": 1
+    },
+    {
+      "epoch": 0.034334763948497854,
+      "grad_norm": 24.00031672844471,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.0836,
+      "step": 2
+    },
+    {
+      "epoch": 0.05150214592274678,
+      "grad_norm": 29.716249933336616,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.1693,
+      "step": 3
+    },
+    {
+      "epoch": 0.06866952789699571,
+      "grad_norm": 24.37331054435917,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.0201,
+      "step": 4
+    },
+    {
+      "epoch": 0.08583690987124463,
+      "grad_norm": 19.789582138660975,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.9014,
+      "step": 5
+    },
+    {
+      "epoch": 0.10300429184549356,
+      "grad_norm": 18.92438805672366,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.0578,
+      "step": 6
+    },
+    {
+      "epoch": 0.12017167381974249,
+      "grad_norm": 13.872256454769323,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.9303,
+      "step": 7
+    },
+    {
+      "epoch": 0.13733905579399142,
+      "grad_norm": 17.41216169856372,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 1.9427,
+      "step": 8
+    },
+    {
+      "epoch": 0.15450643776824036,
+      "grad_norm": 13.884818846193818,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.7924,
+      "step": 9
+    },
+    {
+      "epoch": 0.17167381974248927,
+      "grad_norm": 10.563149359389286,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 1.8341,
+      "step": 10
+    },
+    {
+      "epoch": 0.1888412017167382,
+      "grad_norm": 17.065510513137394,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.8003,
+      "step": 11
+    },
+    {
+      "epoch": 0.20600858369098712,
+      "grad_norm": 13.365031970331449,
+      "learning_rate": 2.2e-06,
+      "loss": 1.7405,
+      "step": 12
+    },
+    {
+      "epoch": 0.22317596566523606,
+      "grad_norm": 10.184190757772281,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.7369,
+      "step": 13
+    },
+    {
+      "epoch": 0.24034334763948498,
+      "grad_norm": 8.522394959606002,
+      "learning_rate": 2.6e-06,
+      "loss": 1.7161,
+      "step": 14
+    },
+    {
+      "epoch": 0.2575107296137339,
+      "grad_norm": 7.4639532795389885,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.7516,
+      "step": 15
+    },
+    {
+      "epoch": 0.27467811158798283,
+      "grad_norm": 6.885531173304724,
+      "learning_rate": 3e-06,
+      "loss": 1.7291,
+      "step": 16
+    },
+    {
+      "epoch": 0.2918454935622318,
+      "grad_norm": 8.124663030531377,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.8113,
+      "step": 17
+    },
+    {
+      "epoch": 0.3090128755364807,
+      "grad_norm": 7.505534742466626,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 1.7011,
+      "step": 18
+    },
+    {
+      "epoch": 0.3261802575107296,
+      "grad_norm": 6.546353703058948,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.679,
+      "step": 19
+    },
+    {
+      "epoch": 0.34334763948497854,
+      "grad_norm": 8.084166970057376,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 1.7672,
+      "step": 20
+    },
+    {
+      "epoch": 0.3605150214592275,
+      "grad_norm": 7.39493724533185,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.7273,
+      "step": 21
+    },
+    {
+      "epoch": 0.3776824034334764,
+      "grad_norm": 7.897097334092764,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 1.723,
+      "step": 22
+    },
+    {
+      "epoch": 0.3948497854077253,
+      "grad_norm": 6.969310652434427,
+      "learning_rate": 4.4e-06,
+      "loss": 1.6652,
+      "step": 23
+    },
+    {
+      "epoch": 0.41201716738197425,
+      "grad_norm": 6.593881510049774,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 1.6471,
+      "step": 24
+    },
+    {
+      "epoch": 0.4291845493562232,
+      "grad_norm": 7.447075197928159,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.7447,
+      "step": 25
+    },
+    {
+      "epoch": 0.44635193133047213,
+      "grad_norm": 7.593703083280446,
+      "learning_rate": 5e-06,
+      "loss": 1.7199,
+      "step": 26
+    },
+    {
+      "epoch": 0.463519313304721,
+      "grad_norm": 7.670358465509374,
+      "learning_rate": 5.2e-06,
+      "loss": 1.7528,
+      "step": 27
+    },
+    {
+      "epoch": 0.48068669527896996,
+      "grad_norm": 6.816789703879088,
+      "learning_rate": 5.400000000000001e-06,
+      "loss": 1.69,
+      "step": 28
+    },
+    {
+      "epoch": 0.4978540772532189,
+      "grad_norm": 6.703285346233008,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 1.6589,
+      "step": 29
+    },
+    {
+      "epoch": 0.5150214592274678,
+      "grad_norm": 6.319351833531301,
+      "learning_rate": 5.8e-06,
+      "loss": 1.6783,
+      "step": 30
+    },
+    {
+      "epoch": 0.5321888412017167,
+      "grad_norm": 7.668634230120905,
+      "learning_rate": 6e-06,
+      "loss": 1.7307,
+      "step": 31
+    },
+    {
+      "epoch": 0.5493562231759657,
+      "grad_norm": 7.216605386564187,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 1.6241,
+      "step": 32
+    },
+    {
+      "epoch": 0.5665236051502146,
+      "grad_norm": 7.95986167238638,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 1.7027,
+      "step": 33
+    },
+    {
+      "epoch": 0.5836909871244635,
+      "grad_norm": 7.567869929265614,
+      "learning_rate": 6.600000000000001e-06,
+      "loss": 1.6541,
+      "step": 34
+    },
+    {
+      "epoch": 0.6008583690987125,
+      "grad_norm": 7.583204324051831,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.6605,
+      "step": 35
+    },
+    {
+      "epoch": 0.6180257510729614,
+      "grad_norm": 7.927092569421214,
+      "learning_rate": 7e-06,
+      "loss": 1.6376,
+      "step": 36
+    },
+    {
+      "epoch": 0.6351931330472103,
+      "grad_norm": 6.777169937117983,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 1.6076,
+      "step": 37
+    },
+    {
+      "epoch": 0.6523605150214592,
+      "grad_norm": 7.376746584211704,
+      "learning_rate": 7.4e-06,
+      "loss": 1.6631,
+      "step": 38
+    },
+    {
+      "epoch": 0.6695278969957081,
+      "grad_norm": 5.931441717917702,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 1.6105,
+      "step": 39
+    },
+    {
+      "epoch": 0.6866952789699571,
+      "grad_norm": 7.788470294493901,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.6777,
+      "step": 40
+    },
+    {
+      "epoch": 0.703862660944206,
+      "grad_norm": 7.201871110419962,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.6622,
+      "step": 41
+    },
+    {
+      "epoch": 0.721030042918455,
+      "grad_norm": 7.351004222204919,
+      "learning_rate": 8.2e-06,
+      "loss": 1.6343,
+      "step": 42
+    },
+    {
+      "epoch": 0.7381974248927039,
+      "grad_norm": 7.116370756646885,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 1.6713,
+      "step": 43
+    },
+    {
+      "epoch": 0.7553648068669528,
+      "grad_norm": 6.804638326754223,
+      "learning_rate": 8.6e-06,
+      "loss": 1.5942,
+      "step": 44
+    },
+    {
+      "epoch": 0.7725321888412017,
+      "grad_norm": 7.1784709545283025,
+      "learning_rate": 8.8e-06,
+      "loss": 1.6453,
+      "step": 45
+    },
+    {
+      "epoch": 0.7896995708154506,
+      "grad_norm": 6.578248052500373,
+      "learning_rate": 9e-06,
+      "loss": 1.6493,
+      "step": 46
+    },
+    {
+      "epoch": 0.8068669527896996,
+      "grad_norm": 5.835458640344457,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 1.5686,
+      "step": 47
+    },
+    {
+      "epoch": 0.8240343347639485,
+      "grad_norm": 6.024182879280123,
+      "learning_rate": 9.4e-06,
+      "loss": 1.5686,
+      "step": 48
+    },
+    {
+      "epoch": 0.8412017167381974,
+      "grad_norm": 5.931203630890797,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.5948,
+      "step": 49
+    },
+    {
+      "epoch": 0.8583690987124464,
+      "grad_norm": 5.741506735885901,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.6167,
+      "step": 50
+    },
+    {
+      "epoch": 0.8755364806866953,
+      "grad_norm": 6.248428015586314,
+      "learning_rate": 1e-05,
+      "loss": 1.6021,
+      "step": 51
+    },
+    {
+      "epoch": 0.8927038626609443,
+      "grad_norm": 5.523348714272916,
+      "learning_rate": 9.999255120204248e-06,
+      "loss": 1.6021,
+      "step": 52
+    },
+    {
+      "epoch": 0.9098712446351931,
+      "grad_norm": 5.486958421466518,
+      "learning_rate": 9.997020702755353e-06,
+      "loss": 1.5414,
+      "step": 53
+    },
+    {
+      "epoch": 0.927038626609442,
+      "grad_norm": 4.906442579745384,
+      "learning_rate": 9.993297413402282e-06,
+      "loss": 1.6355,
+      "step": 54
+    },
+    {
+      "epoch": 0.944206008583691,
+      "grad_norm": 3.4477648478182217,
+      "learning_rate": 9.98808636150624e-06,
+      "loss": 1.5204,
+      "step": 55
+    },
+    {
+      "epoch": 0.9613733905579399,
+      "grad_norm": 5.283485667760506,
+      "learning_rate": 9.981389099710132e-06,
+      "loss": 1.557,
+      "step": 56
+    },
+    {
+      "epoch": 0.9785407725321889,
+      "grad_norm": 4.864774414469769,
+      "learning_rate": 9.973207623475964e-06,
+      "loss": 1.5847,
+      "step": 57
+    },
+    {
+      "epoch": 0.9957081545064378,
+      "grad_norm": 4.99512035052619,
+      "learning_rate": 9.96354437049027e-06,
+      "loss": 1.4972,
+      "step": 58
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.99512035052619,
+      "learning_rate": 9.952402219937817e-06,
+      "loss": 1.6505,
+      "step": 59
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.425569772720337,
+      "eval_runtime": 55.3506,
+      "eval_samples_per_second": 6.504,
+      "eval_steps_per_second": 0.217,
+      "step": 59
+    },
+    {
+      "epoch": 1.0171673819742488,
+      "grad_norm": 3.9912629226494145,
+      "learning_rate": 9.939784491643734e-06,
+      "loss": 1.5689,
+      "step": 60
+    },
+    {
+      "epoch": 1.0343347639484979,
+      "grad_norm": 3.5037206814091273,
+      "learning_rate": 9.925694945084369e-06,
+      "loss": 1.5846,
+      "step": 61
+    },
+    {
+      "epoch": 1.0515021459227467,
+      "grad_norm": 3.096134013860231,
+      "learning_rate": 9.910137778267153e-06,
+      "loss": 1.561,
+      "step": 62
+    },
+    {
+      "epoch": 1.0686695278969958,
+      "grad_norm": 6.745525969869406,
+      "learning_rate": 9.893117626479778e-06,
+      "loss": 1.5086,
+      "step": 63
+    },
+    {
+      "epoch": 1.0858369098712446,
+      "grad_norm": 3.771654699845576,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 1.4463,
+      "step": 64
+    },
+    {
+      "epoch": 1.1030042918454936,
+      "grad_norm": 7.348146928107017,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 1.5732,
+      "step": 65
+    },
+    {
+      "epoch": 1.1201716738197425,
+      "grad_norm": 4.285886261726828,
+      "learning_rate": 9.833332143466099e-06,
+      "loss": 1.5634,
+      "step": 66
+    },
+    {
+      "epoch": 1.1373390557939915,
+      "grad_norm": 9.50651645737036,
+      "learning_rate": 9.810515099218004e-06,
+      "loss": 1.5832,
+      "step": 67
+    },
+    {
+      "epoch": 1.1545064377682404,
+      "grad_norm": 9.85903247254424,
+      "learning_rate": 9.78626475276808e-06,
+      "loss": 1.5158,
+      "step": 68
+    },
+    {
+      "epoch": 1.1716738197424892,
+      "grad_norm": 4.500325598034437,
+      "learning_rate": 9.76058832955357e-06,
+      "loss": 1.5577,
+      "step": 69
+    },
+    {
+      "epoch": 1.1888412017167382,
+      "grad_norm": 6.726627673373393,
+      "learning_rate": 9.733493479914031e-06,
+      "loss": 1.5402,
+      "step": 70
+    },
+    {
+      "epoch": 1.206008583690987,
+      "grad_norm": 5.992547800498691,
+      "learning_rate": 9.704988276811883e-06,
+      "loss": 1.4771,
+      "step": 71
+    },
+    {
+      "epoch": 1.2231759656652361,
+      "grad_norm": 3.966804454715501,
+      "learning_rate": 9.675081213427076e-06,
+      "loss": 1.4715,
+      "step": 72
+    },
+    {
+      "epoch": 1.240343347639485,
+      "grad_norm": 5.018712503166457,
+      "learning_rate": 9.643781200626512e-06,
+      "loss": 1.483,
+      "step": 73
+    },
+    {
+      "epoch": 1.2575107296137338,
+      "grad_norm": 5.147155410650178,
+      "learning_rate": 9.611097564309054e-06,
+      "loss": 1.529,
+      "step": 74
+    },
+    {
+      "epoch": 1.2746781115879828,
+      "grad_norm": 4.430249361377804,
+      "learning_rate": 9.577040042626832e-06,
+      "loss": 1.5055,
+      "step": 75
+    },
+    {
+      "epoch": 1.2918454935622319,
+      "grad_norm": 3.3331885191043824,
+      "learning_rate": 9.54161878308377e-06,
+      "loss": 1.5686,
+      "step": 76
+    },
+    {
+      "epoch": 1.3090128755364807,
+      "grad_norm": 3.3765624318373684,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 1.4806,
+      "step": 77
+    },
+    {
+      "epoch": 1.3261802575107295,
+      "grad_norm": 3.0122848173838146,
+      "learning_rate": 9.466727668927817e-06,
+      "loss": 1.483,
+      "step": 78
+    },
+    {
+      "epoch": 1.3433476394849786,
+      "grad_norm": 2.8374889256024325,
+      "learning_rate": 9.427280128266049e-06,
+      "loss": 1.5371,
+      "step": 79
+    },
+    {
+      "epoch": 1.3605150214592274,
+      "grad_norm": 3.8591143057415067,
+      "learning_rate": 9.38651347099721e-06,
+      "loss": 1.515,
+      "step": 80
+    },
+    {
+      "epoch": 1.3776824034334765,
+      "grad_norm": 2.702387816445196,
+      "learning_rate": 9.344439843625034e-06,
+      "loss": 1.5065,
+      "step": 81
+    },
+    {
+      "epoch": 1.3948497854077253,
+      "grad_norm": 3.231309074741847,
+      "learning_rate": 9.301071782067504e-06,
+      "loss": 1.4691,
+      "step": 82
+    },
+    {
+      "epoch": 1.4120171673819741,
+      "grad_norm": 2.569345186210359,
+      "learning_rate": 9.256422207921757e-06,
+      "loss": 1.4551,
+      "step": 83
+    },
+    {
+      "epoch": 1.4291845493562232,
+      "grad_norm": 2.6936841928298763,
+      "learning_rate": 9.21050442461406e-06,
+      "loss": 1.5342,
+      "step": 84
+    },
+    {
+      "epoch": 1.4463519313304722,
+      "grad_norm": 3.1643389084628923,
+      "learning_rate": 9.163332113436031e-06,
+      "loss": 1.5134,
+      "step": 85
+    },
+    {
+      "epoch": 1.463519313304721,
+      "grad_norm": 2.0547003373714317,
+      "learning_rate": 9.114919329468283e-06,
+      "loss": 1.543,
+      "step": 86
+    },
+    {
+      "epoch": 1.48068669527897,
+      "grad_norm": 3.4765227820159628,
+      "learning_rate": 9.065280497392663e-06,
+      "loss": 1.4952,
+      "step": 87
+    },
+    {
+      "epoch": 1.497854077253219,
+      "grad_norm": 2.3605853021000245,
+      "learning_rate": 9.014430407194413e-06,
+      "loss": 1.4706,
+      "step": 88
+    },
+    {
+      "epoch": 1.5150214592274678,
+      "grad_norm": 2.79040585245284,
+      "learning_rate": 8.962384209755453e-06,
+      "loss": 1.5038,
+      "step": 89
+    },
+    {
+      "epoch": 1.5321888412017168,
+      "grad_norm": 3.130637987619235,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 1.5331,
+      "step": 90
+    },
+    {
+      "epoch": 1.5493562231759657,
+      "grad_norm": 2.1702749562184036,
+      "learning_rate": 8.854765873974898e-06,
+      "loss": 1.4362,
+      "step": 91
+    },
+    {
+      "epoch": 1.5665236051502145,
+      "grad_norm": 3.529361540533676,
+      "learning_rate": 8.799225800722895e-06,
+      "loss": 1.5103,
+      "step": 92
+    },
+    {
+      "epoch": 1.5836909871244635,
+      "grad_norm": 2.1288633137671362,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 1.4735,
+      "step": 93
+    },
+    {
+      "epoch": 1.6008583690987126,
+      "grad_norm": 4.653595880593553,
+      "learning_rate": 8.684766579921684e-06,
+      "loss": 1.4837,
+      "step": 94
+    },
+    {
+      "epoch": 1.6180257510729614,
+      "grad_norm": 4.183036771208689,
+      "learning_rate": 8.625881535716883e-06,
+      "loss": 1.4616,
+      "step": 95
+    },
+    {
+      "epoch": 1.6351931330472103,
+      "grad_norm": 3.583624228870984,
+      "learning_rate": 8.565916153152982e-06,
+      "loss": 1.452,
+      "step": 96
+    },
+    {
+      "epoch": 1.652360515021459,
+      "grad_norm": 2.9353226938465538,
+      "learning_rate": 8.504888299030748e-06,
+      "loss": 1.5003,
+      "step": 97
+    },
+    {
+      "epoch": 1.6695278969957081,
+      "grad_norm": 3.9811908362996387,
+      "learning_rate": 8.442816156716386e-06,
+      "loss": 1.4712,
+      "step": 98
+    },
+    {
+      "epoch": 1.6866952789699572,
+      "grad_norm": 4.507840289564422,
+      "learning_rate": 8.379718220723772e-06,
+      "loss": 1.5154,
+      "step": 99
+    },
+    {
+      "epoch": 1.703862660944206,
+      "grad_norm": 1.7351061691281462,
+      "learning_rate": 8.315613291203977e-06,
+      "loss": 1.5071,
+      "step": 100
+    },
+    {
+      "epoch": 1.7210300429184548,
+      "grad_norm": 2.1548506371633476,
+      "learning_rate": 8.250520468343722e-06,
+      "loss": 1.4847,
+      "step": 101
+    },
+    {
+      "epoch": 1.738197424892704,
+      "grad_norm": 2.915800387932283,
+      "learning_rate": 8.184459146674447e-06,
+      "loss": 1.5255,
+      "step": 102
+    },
+    {
+      "epoch": 1.755364806866953,
+      "grad_norm": 1.8127751226762168,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 1.4585,
+      "step": 103
+    },
+    {
+      "epoch": 1.7725321888412018,
+      "grad_norm": 3.2104447847604884,
+      "learning_rate": 8.049510022000365e-06,
+      "loss": 1.5145,
+      "step": 104
+    },
+    {
+      "epoch": 1.7896995708154506,
+      "grad_norm": 1.7409586719583194,
+      "learning_rate": 7.980662427346127e-06,
+      "loss": 1.5268,
+      "step": 105
+    },
+    {
+      "epoch": 1.8068669527896994,
+      "grad_norm": 4.142279628383546,
+      "learning_rate": 7.910926738603855e-06,
+      "loss": 1.4615,
+      "step": 106
+    },
+    {
+      "epoch": 1.8240343347639485,
+      "grad_norm": 3.877668467895349,
+      "learning_rate": 7.84032373365578e-06,
+      "loss": 1.465,
+      "step": 107
+    },
+    {
+      "epoch": 1.8412017167381975,
+      "grad_norm": 2.656628633387025,
+      "learning_rate": 7.768874448802665e-06,
+      "loss": 1.4922,
+      "step": 108
+    },
+    {
+      "epoch": 1.8583690987124464,
+      "grad_norm": 2.584883160911178,
+      "learning_rate": 7.696600172495997e-06,
+      "loss": 1.5179,
+      "step": 109
+    },
+    {
+      "epoch": 1.8755364806866952,
+      "grad_norm": 2.587010532927385,
+      "learning_rate": 7.62352243899504e-06,
+      "loss": 1.5014,
+      "step": 110
+    },
+    {
+      "epoch": 1.8927038626609443,
+      "grad_norm": 2.5107207102352915,
+      "learning_rate": 7.5496630219506805e-06,
+      "loss": 1.5064,
+      "step": 111
+    },
+    {
+      "epoch": 1.909871244635193,
+      "grad_norm": 2.0882468780951915,
+      "learning_rate": 7.475043927917908e-06,
+      "loss": 1.4503,
+      "step": 112
+    },
+    {
+      "epoch": 1.9270386266094421,
+      "grad_norm": 2.1486369526322924,
+      "learning_rate": 7.399687389798933e-06,
+      "loss": 1.5461,
+      "step": 113
+    },
+    {
+      "epoch": 1.944206008583691,
+      "grad_norm": 1.8242630296650162,
+      "learning_rate": 7.323615860218844e-06,
+      "loss": 1.4363,
+      "step": 114
+    },
+    {
+      "epoch": 1.9613733905579398,
+      "grad_norm": 2.145842755842824,
+      "learning_rate": 7.246852004835807e-06,
+      "loss": 1.4766,
+      "step": 115
+    },
+    {
+      "epoch": 1.9785407725321889,
+      "grad_norm": 1.6691578334566337,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 1.499,
+      "step": 116
+    },
+    {
+      "epoch": 1.995708154506438,
+      "grad_norm": 2.2108584637006863,
+      "learning_rate": 7.091339003877826e-06,
+      "loss": 1.4225,
+      "step": 117
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.2108584637006863,
+      "learning_rate": 7.012636193699838e-06,
+      "loss": 1.5231,
+      "step": 118
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3721916675567627,
+      "eval_runtime": 55.5761,
+      "eval_samples_per_second": 6.478,
+      "eval_steps_per_second": 0.216,
+      "step": 118
+    },
+    {
+      "epoch": 2.017167381974249,
+      "grad_norm": 3.7388997063310248,
+      "learning_rate": 6.933333714707094e-06,
+      "loss": 1.4963,
+      "step": 119
+    },
+    {
+      "epoch": 2.0343347639484977,
+      "grad_norm": 1.9374219671850537,
+      "learning_rate": 6.8534551952253395e-06,
+      "loss": 1.511,
+      "step": 120
+    },
+    {
+      "epoch": 2.051502145922747,
+      "grad_norm": 2.137490994962777,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 1.4785,
+      "step": 121
+    },
+    {
+      "epoch": 2.0686695278969958,
+      "grad_norm": 1.5840707110043721,
+      "learning_rate": 6.692065399168352e-06,
+      "loss": 1.4386,
+      "step": 122
+    },
+    {
+      "epoch": 2.0858369098712446,
+      "grad_norm": 2.0353319612062175,
+      "learning_rate": 6.6106022089924535e-06,
+      "loss": 1.3749,
+      "step": 123
+    },
+    {
+      "epoch": 2.1030042918454934,
+      "grad_norm": 1.8137709307149847,
+      "learning_rate": 6.5286591367987655e-06,
+      "loss": 1.4849,
+      "step": 124
+    },
+    {
+      "epoch": 2.1201716738197427,
+      "grad_norm": 2.7161222343926212,
+      "learning_rate": 6.4462605976828395e-06,
+      "loss": 1.4845,
+      "step": 125
+    },
+    {
+      "epoch": 2.1373390557939915,
+      "grad_norm": 1.3620483576209157,
+      "learning_rate": 6.363431142447469e-06,
+      "loss": 1.4977,
+      "step": 126
+    },
+    {
+      "epoch": 2.1545064377682404,
+      "grad_norm": 1.8781921403392814,
+      "learning_rate": 6.280195450287736e-06,
+      "loss": 1.4339,
+      "step": 127
+    },
+    {
+      "epoch": 2.171673819742489,
+      "grad_norm": 1.8249006642987649,
+      "learning_rate": 6.1965783214377895e-06,
+      "loss": 1.4837,
+      "step": 128
+    },
+    {
+      "epoch": 2.188841201716738,
+      "grad_norm": 1.4576334521913883,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 1.4642,
+      "step": 129
+    },
+    {
+      "epoch": 2.2060085836909873,
+      "grad_norm": 1.8699628551915364,
+      "learning_rate": 6.028299515429683e-06,
+      "loss": 1.3993,
+      "step": 130
+    },
+    {
+      "epoch": 2.223175965665236,
+      "grad_norm": 1.1893820742085242,
+      "learning_rate": 5.943687977264584e-06,
+      "loss": 1.3989,
+      "step": 131
+    },
+    {
+      "epoch": 2.240343347639485,
+      "grad_norm": 1.7116247132028521,
+      "learning_rate": 5.858795265456382e-06,
+      "loss": 1.4183,
+      "step": 132
+    },
+    {
+      "epoch": 2.257510729613734,
+      "grad_norm": 1.5102064250019567,
+      "learning_rate": 5.773646673951406e-06,
+      "loss": 1.457,
+      "step": 133
+    },
+    {
+      "epoch": 2.274678111587983,
+      "grad_norm": 1.2667706935607246,
+      "learning_rate": 5.688267572935843e-06,
+      "loss": 1.436,
+      "step": 134
+    },
+    {
+      "epoch": 2.291845493562232,
+      "grad_norm": 1.6963247346173285,
+      "learning_rate": 5.6026834012766155e-06,
+      "loss": 1.4965,
+      "step": 135
+    },
+    {
+      "epoch": 2.3090128755364807,
+      "grad_norm": 1.2569488026568798,
+      "learning_rate": 5.51691965894185e-06,
+      "loss": 1.4098,
+      "step": 136
+    },
+    {
+      "epoch": 2.3261802575107295,
+      "grad_norm": 1.1272036077401364,
+      "learning_rate": 5.4310018994030974e-06,
+      "loss": 1.4119,
+      "step": 137
+    },
+    {
+      "epoch": 2.3433476394849784,
+      "grad_norm": 1.673271865613411,
+      "learning_rate": 5.3449557220216245e-06,
+      "loss": 1.4661,
+      "step": 138
+    },
+    {
+      "epoch": 2.3605150214592276,
+      "grad_norm": 1.2078563404488671,
+      "learning_rate": 5.258806764421048e-06,
+      "loss": 1.4497,
+      "step": 139
+    },
+    {
+      "epoch": 2.3776824034334765,
+      "grad_norm": 1.308716503746094,
+      "learning_rate": 5.172580694848541e-06,
+      "loss": 1.4351,
+      "step": 140
+    },
+    {
+      "epoch": 2.3948497854077253,
+      "grad_norm": 1.6067743882863361,
+      "learning_rate": 5.0863032045269435e-06,
+      "loss": 1.4017,
+      "step": 141
+    },
+    {
+      "epoch": 2.412017167381974,
+      "grad_norm": 1.15329126746228,
+      "learning_rate": 5e-06,
+      "loss": 1.3885,
+      "step": 142
+    },
+    {
+      "epoch": 2.429184549356223,
+      "grad_norm": 1.3029425990628287,
+      "learning_rate": 4.913696795473058e-06,
+      "loss": 1.4686,
+      "step": 143
+    },
+    {
+      "epoch": 2.4463519313304722,
+      "grad_norm": 1.3782312780671255,
+      "learning_rate": 4.827419305151461e-06,
+      "loss": 1.4472,
+      "step": 144
+    },
+    {
+      "epoch": 2.463519313304721,
+      "grad_norm": 1.1387922784921702,
+      "learning_rate": 4.741193235578953e-06,
+      "loss": 1.4717,
+      "step": 145
+    },
+    {
+      "epoch": 2.48068669527897,
+      "grad_norm": 1.4489271450805266,
+      "learning_rate": 4.6550442779783755e-06,
+      "loss": 1.4325,
+      "step": 146
+    },
+    {
+      "epoch": 2.4978540772532187,
+      "grad_norm": 1.3782527667091915,
+      "learning_rate": 4.568998100596903e-06,
+      "loss": 1.405,
+      "step": 147
+    },
+    {
+      "epoch": 2.5150214592274676,
+      "grad_norm": 1.2668976356990511,
+      "learning_rate": 4.4830803410581506e-06,
+      "loss": 1.4427,
+      "step": 148
+    },
+    {
+      "epoch": 2.532188841201717,
+      "grad_norm": 1.4950710057650962,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 1.4714,
+      "step": 149
+    },
+    {
+      "epoch": 2.5493562231759657,
+      "grad_norm": 1.0576970824111924,
+      "learning_rate": 4.31173242706416e-06,
+      "loss": 1.3698,
+      "step": 150
+    },
+    {
+      "epoch": 2.5665236051502145,
+      "grad_norm": 1.6518504203265545,
+      "learning_rate": 4.226353326048594e-06,
+      "loss": 1.4462,
+      "step": 151
+    },
+    {
+      "epoch": 2.5836909871244638,
+      "grad_norm": 1.0690977885341415,
+      "learning_rate": 4.14120473454362e-06,
+      "loss": 1.4094,
+      "step": 152
+    },
+    {
+      "epoch": 2.6008583690987126,
+      "grad_norm": 1.2319353745161556,
+      "learning_rate": 4.056312022735417e-06,
+      "loss": 1.4279,
+      "step": 153
+    },
+    {
+      "epoch": 2.6180257510729614,
+      "grad_norm": 1.4981453391586554,
+      "learning_rate": 3.9717004845703175e-06,
+      "loss": 1.404,
+      "step": 154
+    },
+    {
+      "epoch": 2.6351931330472103,
+      "grad_norm": 1.1718194614512722,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 1.3936,
+      "step": 155
+    },
+    {
+      "epoch": 2.652360515021459,
+      "grad_norm": 1.382020649765366,
+      "learning_rate": 3.803421678562213e-06,
+      "loss": 1.4432,
+      "step": 156
+    },
+    {
+      "epoch": 2.6695278969957084,
+      "grad_norm": 1.0295860006980109,
+      "learning_rate": 3.7198045497122647e-06,
+      "loss": 1.4189,
+      "step": 157
+    },
+    {
+      "epoch": 2.686695278969957,
+      "grad_norm": 1.6145284029231795,
+      "learning_rate": 3.6365688575525315e-06,
+      "loss": 1.4579,
+      "step": 158
+    },
+    {
+      "epoch": 2.703862660944206,
+      "grad_norm": 1.1519727791811123,
+      "learning_rate": 3.553739402317162e-06,
+      "loss": 1.4404,
+      "step": 159
+    },
+    {
+      "epoch": 2.721030042918455,
+      "grad_norm": 1.6702535379739811,
+      "learning_rate": 3.471340863201237e-06,
+      "loss": 1.4247,
+      "step": 160
+    },
+    {
+      "epoch": 2.7381974248927037,
+      "grad_norm": 1.4413775372344653,
+      "learning_rate": 3.389397791007548e-06,
+      "loss": 1.4669,
+      "step": 161
+    },
+    {
+      "epoch": 2.755364806866953,
+      "grad_norm": 1.6769364420250672,
+      "learning_rate": 3.307934600831648e-06,
+      "loss": 1.3987,
+      "step": 162
+    },
+    {
+      "epoch": 2.772532188841202,
+      "grad_norm": 1.4127696099779041,
+      "learning_rate": 3.226975564787322e-06,
+      "loss": 1.4577,
+      "step": 163
+    },
+    {
+      "epoch": 2.7896995708154506,
+      "grad_norm": 1.3981396160008468,
+      "learning_rate": 3.1465448047746626e-06,
+      "loss": 1.4643,
+      "step": 164
+    },
+    {
+      "epoch": 2.8068669527896994,
+      "grad_norm": 1.1640956539171732,
+      "learning_rate": 3.0666662852929063e-06,
+      "loss": 1.4127,
+      "step": 165
+    },
+    {
+      "epoch": 2.8240343347639483,
+      "grad_norm": 1.524450627139972,
+      "learning_rate": 2.9873638063001633e-06,
+      "loss": 1.4114,
+      "step": 166
+    },
+    {
+      "epoch": 2.8412017167381975,
+      "grad_norm": 1.3456136782749846,
+      "learning_rate": 2.9086609961221758e-06,
+      "loss": 1.435,
+      "step": 167
+    },
+    {
+      "epoch": 2.8583690987124464,
+      "grad_norm": 1.2127544846215854,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 1.464,
+      "step": 168
+    },
+    {
+      "epoch": 2.875536480686695,
+      "grad_norm": 1.1389112761416087,
+      "learning_rate": 2.7531479951641928e-06,
+      "loss": 1.4468,
+      "step": 169
+    },
+    {
+      "epoch": 2.8927038626609445,
+      "grad_norm": 1.2715694866770404,
+      "learning_rate": 2.6763841397811576e-06,
+      "loss": 1.451,
+      "step": 170
+    },
+    {
+      "epoch": 2.909871244635193,
+      "grad_norm": 1.2899452182832583,
+      "learning_rate": 2.6003126102010696e-06,
+      "loss": 1.3969,
+      "step": 171
+    },
+    {
+      "epoch": 2.927038626609442,
+      "grad_norm": 1.1876736667702164,
+      "learning_rate": 2.524956072082093e-06,
+      "loss": 1.4894,
+      "step": 172
+    },
+    {
+      "epoch": 2.944206008583691,
+      "grad_norm": 1.0044043551342703,
+      "learning_rate": 2.450336978049322e-06,
+      "loss": 1.3833,
+      "step": 173
+    },
+    {
+      "epoch": 2.96137339055794,
+      "grad_norm": 1.1006453119175361,
+      "learning_rate": 2.37647756100496e-06,
+      "loss": 1.422,
+      "step": 174
+    },
+    {
+      "epoch": 2.978540772532189,
+      "grad_norm": 1.1339844183954066,
+      "learning_rate": 2.3033998275040047e-06,
+      "loss": 1.4416,
+      "step": 175
+    },
+    {
+      "epoch": 2.995708154506438,
+      "grad_norm": 1.0443241596589774,
+      "learning_rate": 2.2311255511973347e-06,
+      "loss": 1.3739,
+      "step": 176
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0443241596589774,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 1.4492,
+      "step": 177
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.3466758728027344,
+      "eval_runtime": 55.4567,
+      "eval_samples_per_second": 6.492,
+      "eval_steps_per_second": 0.216,
+      "step": 177
+    },
+    {
+      "epoch": 3.017167381974249,
+      "grad_norm": 2.208608681250419,
+      "learning_rate": 2.089073261396148e-06,
+      "loss": 1.4496,
+      "step": 178
+    },
+    {
+      "epoch": 3.0343347639484977,
+      "grad_norm": 2.068961082241978,
+      "learning_rate": 2.0193375726538737e-06,
+      "loss": 1.4599,
+      "step": 179
+    },
+    {
+      "epoch": 3.051502145922747,
+      "grad_norm": 1.2686715786339267,
+      "learning_rate": 1.9504899779996354e-06,
+      "loss": 1.4241,
+      "step": 180
+    },
+    {
+      "epoch": 3.0686695278969958,
+      "grad_norm": 0.9766943956912364,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 1.3856,
+      "step": 181
+    },
+    {
+      "epoch": 3.0858369098712446,
+      "grad_norm": 0.9570891019240637,
+      "learning_rate": 1.8155408533255553e-06,
+      "loss": 1.3267,
+      "step": 182
+    },
+    {
+      "epoch": 3.1030042918454934,
+      "grad_norm": 0.9858819209987062,
+      "learning_rate": 1.7494795316562791e-06,
+      "loss": 1.4371,
+      "step": 183
+    },
+    {
+      "epoch": 3.1201716738197427,
+      "grad_norm": 0.9400585321740289,
+      "learning_rate": 1.6843867087960252e-06,
+      "loss": 1.4347,
+      "step": 184
+    },
+    {
+      "epoch": 3.1373390557939915,
+      "grad_norm": 1.0563349262899193,
+      "learning_rate": 1.6202817792762283e-06,
+      "loss": 1.4431,
+      "step": 185
+    },
+    {
+      "epoch": 3.1545064377682404,
+      "grad_norm": 0.9217174697986299,
+      "learning_rate": 1.557183843283614e-06,
+      "loss": 1.3872,
+      "step": 186
+    },
+    {
+      "epoch": 3.171673819742489,
+      "grad_norm": 0.9537020658805889,
+      "learning_rate": 1.4951117009692528e-06,
+      "loss": 1.4342,
+      "step": 187
+    },
+    {
+      "epoch": 3.188841201716738,
+      "grad_norm": 0.931415129363885,
+      "learning_rate": 1.4340838468470198e-06,
+      "loss": 1.4167,
+      "step": 188
+    },
+    {
+      "epoch": 3.2060085836909873,
+      "grad_norm": 0.8848653838809811,
+      "learning_rate": 1.374118464283119e-06,
+      "loss": 1.3483,
+      "step": 189
+    },
+    {
+      "epoch": 3.223175965665236,
+      "grad_norm": 0.8999049162268763,
+      "learning_rate": 1.3152334200783167e-06,
+      "loss": 1.3486,
+      "step": 190
+    },
+    {
+      "epoch": 3.240343347639485,
+      "grad_norm": 0.913466824589116,
+      "learning_rate": 1.257446259144494e-06,
+      "loss": 1.372,
+      "step": 191
+    },
+    {
+      "epoch": 3.257510729613734,
+      "grad_norm": 0.9910112277396748,
+      "learning_rate": 1.2007741992771065e-06,
+      "loss": 1.4064,
+      "step": 192
+    },
+    {
+      "epoch": 3.274678111587983,
+      "grad_norm": 0.883357238281907,
+      "learning_rate": 1.145234126025102e-06,
+      "loss": 1.3869,
+      "step": 193
+    },
+    {
+      "epoch": 3.291845493562232,
+      "grad_norm": 0.9234833713444595,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 1.4469,
+      "step": 194
+    },
+    {
+      "epoch": 3.3090128755364807,
+      "grad_norm": 0.859382750295263,
+      "learning_rate": 1.037615790244549e-06,
+      "loss": 1.3571,
+      "step": 195
+    },
+    {
+      "epoch": 3.3261802575107295,
+      "grad_norm": 0.815275008698639,
+      "learning_rate": 9.85569592805588e-07,
+      "loss": 1.3635,
+      "step": 196
+    },
+    {
+      "epoch": 3.3433476394849784,
+      "grad_norm": 0.8740357211724161,
+      "learning_rate": 9.347195026073369e-07,
+      "loss": 1.4195,
+      "step": 197
+    },
+    {
+      "epoch": 3.3605150214592276,
+      "grad_norm": 0.8549841652198367,
+      "learning_rate": 8.850806705317183e-07,
+      "loss": 1.4011,
+      "step": 198
+    },
+    {
+      "epoch": 3.3776824034334765,
+      "grad_norm": 0.8255973582968239,
+      "learning_rate": 8.366678865639688e-07,
+      "loss": 1.3907,
+      "step": 199
+    },
+    {
+      "epoch": 3.3948497854077253,
+      "grad_norm": 0.8469777726661422,
+      "learning_rate": 7.894955753859412e-07,
+      "loss": 1.3586,
+      "step": 200
+    },
+    {
+      "epoch": 3.412017167381974,
+      "grad_norm": 0.84555567071041,
+      "learning_rate": 7.435777920782444e-07,
+      "loss": 1.344,
+      "step": 201
+    },
+    {
+      "epoch": 3.429184549356223,
+      "grad_norm": 0.8100696398102393,
+      "learning_rate": 6.989282179324963e-07,
+      "loss": 1.4253,
+      "step": 202
+    },
+    {
+      "epoch": 3.4463519313304722,
+      "grad_norm": 0.853525501890134,
+      "learning_rate": 6.555601563749675e-07,
+      "loss": 1.4028,
+      "step": 203
+    },
+    {
+      "epoch": 3.463519313304721,
+      "grad_norm": 2.5389247756358455,
+      "learning_rate": 6.134865290027903e-07,
+      "loss": 1.4282,
+      "step": 204
+    },
+    {
+      "epoch": 3.48068669527897,
+      "grad_norm": 1.2453666685589984,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 1.3921,
+      "step": 205
+    },
+    {
+      "epoch": 3.4978540772532187,
+      "grad_norm": 0.7642367373812298,
+      "learning_rate": 5.332723310721855e-07,
+      "loss": 1.365,
+      "step": 206
+    },
+    {
+      "epoch": 3.5150214592274676,
+      "grad_norm": 0.9270502698949785,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 1.4041,
+      "step": 207
+    },
+    {
+      "epoch": 3.532188841201717,
+      "grad_norm": 0.8098170144667726,
+      "learning_rate": 4.5838121691622995e-07,
+      "loss": 1.4315,
+      "step": 208
+    },
+    {
+      "epoch": 3.5493562231759657,
+      "grad_norm": 0.7857989969064568,
+      "learning_rate": 4.2295995737316854e-07,
+      "loss": 1.332,
+      "step": 209
+    },
+    {
+      "epoch": 3.5665236051502145,
+      "grad_norm": 0.8648677468818124,
+      "learning_rate": 3.8890243569094874e-07,
+      "loss": 1.4088,
+      "step": 210
+    },
+    {
+      "epoch": 3.5836909871244638,
+      "grad_norm": 0.8148105107754193,
+      "learning_rate": 3.5621879937348836e-07,
+      "loss": 1.3708,
+      "step": 211
+    },
+    {
+      "epoch": 3.6008583690987126,
+      "grad_norm": 0.8784091247812043,
+      "learning_rate": 3.2491878657292643e-07,
+      "loss": 1.3931,
+      "step": 212
+    },
+    {
+      "epoch": 3.6180257510729614,
+      "grad_norm": 0.8314788876032824,
+      "learning_rate": 2.9501172318811834e-07,
+      "loss": 1.3706,
+      "step": 213
+    },
+    {
+      "epoch": 3.6351931330472103,
+      "grad_norm": 0.8122583055213561,
+      "learning_rate": 2.6650652008597067e-07,
+      "loss": 1.3595,
+      "step": 214
+    },
+    {
+      "epoch": 3.652360515021459,
+      "grad_norm": 0.8988415508956524,
+      "learning_rate": 2.394116704464294e-07,
+      "loss": 1.4083,
+      "step": 215
+    },
+    {
+      "epoch": 3.6695278969957084,
+      "grad_norm": 0.7489347389916948,
+      "learning_rate": 2.137352472319215e-07,
+      "loss": 1.3862,
+      "step": 216
+    },
+    {
+      "epoch": 3.686695278969957,
+      "grad_norm": 0.8026525023223839,
+      "learning_rate": 1.8948490078199767e-07,
+      "loss": 1.4263,
+      "step": 217
+    },
+    {
+      "epoch": 3.703862660944206,
+      "grad_norm": 0.8691178194849434,
+      "learning_rate": 1.666678565339025e-07,
+      "loss": 1.4107,
+      "step": 218
+    },
+    {
+      "epoch": 3.721030042918455,
+      "grad_norm": 0.8295342705741752,
+      "learning_rate": 1.4529091286973994e-07,
+      "loss": 1.3977,
+      "step": 219
+    },
+    {
+      "epoch": 3.7381974248927037,
+      "grad_norm": 0.9952946458735904,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 1.44,
+      "step": 220
+    },
+    {
+      "epoch": 3.755364806866953,
+      "grad_norm": 0.8929004736914973,
+      "learning_rate": 1.0688237352022346e-07,
+      "loss": 1.3744,
+      "step": 221
+    },
+    {
+      "epoch": 3.772532188841202,
+      "grad_norm": 0.7817159407340549,
+      "learning_rate": 8.986222173284876e-08,
+      "loss": 1.4323,
+      "step": 222
+    },
+    {
+      "epoch": 3.7896995708154506,
+      "grad_norm": 0.7269772041119471,
+      "learning_rate": 7.430505491563101e-08,
+      "loss": 1.4378,
+      "step": 223
+    },
+    {
+      "epoch": 3.8068669527896994,
+      "grad_norm": 0.846076015787421,
+      "learning_rate": 6.021550835626777e-08,
+      "loss": 1.3876,
+      "step": 224
+    },
+    {
+      "epoch": 3.8240343347639483,
+      "grad_norm": 0.7622844494333099,
+      "learning_rate": 4.759778006218407e-08,
+      "loss": 1.3879,
+      "step": 225
+    },
+    {
+      "epoch": 3.8412017167381975,
+      "grad_norm": 0.7517386279788537,
+      "learning_rate": 3.645562950973014e-08,
+      "loss": 1.4094,
+      "step": 226
+    },
+    {
+      "epoch": 3.8583690987124464,
+      "grad_norm": 0.7555615969516848,
+      "learning_rate": 2.6792376524036878e-08,
+      "loss": 1.4385,
+      "step": 227
+    },
+    {
+      "epoch": 3.875536480686695,
+      "grad_norm": 0.759032041862736,
+      "learning_rate": 1.8610900289867673e-08,
+      "loss": 1.4219,
+      "step": 228
+    },
+    {
+      "epoch": 3.8927038626609445,
+      "grad_norm": 0.8896057625292756,
+      "learning_rate": 1.1913638493762369e-08,
+      "loss": 1.4286,
+      "step": 229
+    },
+    {
+      "epoch": 3.909871244635193,
+      "grad_norm": 0.8049879121289703,
+      "learning_rate": 6.702586597719385e-09,
+      "loss": 1.3756,
+      "step": 230
+    },
+    {
+      "epoch": 3.927038626609442,
+      "grad_norm": 0.8081459120471564,
+      "learning_rate": 2.9792972446479605e-09,
+      "loss": 1.4649,
+      "step": 231
+    },
+    {
+      "epoch": 3.944206008583691,
+      "grad_norm": 0.7889695020980092,
+      "learning_rate": 7.448797957526621e-10,
+      "loss": 1.3612,
+      "step": 232
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 232,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 29,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9152650971882455e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b486ccd0c0143e3e570dbeebcb0c4131aa4e86047e6147f2d8f8c5842f3421
+size 8913

zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/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 json
+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)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in 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}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_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)
+
+    # 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")
+        state_dict_split = split_torch_state_dict_into_shards(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
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # 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)