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
+025/tokenizer.json filter=lfs diff=lfs merge=lfs -text

025/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/raid/HUB_LLM/Llama-3.3-70B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 16000,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

025/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

025/latest

@@ -0,0 +1 @@
+global_step428

025/model-00001-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d2f818fff9d10231768c2fb40650a55141b9bef51863ff8b1a90b1022ee05c
+size 4584408808

025/model-00002-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2dda9c77d8437bb080d2a2c879661149ee4533212f8a243a82c89fe9dd03a21
+size 4664167376

025/model-00003-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934dda9e7dc90ef6befc312d7fed970fb64c5177013502b7db872c5f6c03a7e8
+size 4999711704

025/model-00004-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312f2ac2eb090fbc373ceb63f257d65b6235a3767bdce137fdbadd25bac57be8
+size 4966157032

025/model-00005-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6609b8fbc36fe7333cfe7ca6f53220203dba227631eedf6b99c05494b66a6ad
+size 4664134408

025/model-00006-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b4cc42268034e407615e13edbeb24ec27023f0de185e93c1ee96cc8a7be4a2
+size 4664167408

025/model-00007-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b5f5d1c42f2a1807630a8bea3b86c8c2f0043c14f71fa3852803820573dab7
+size 4664167408

025/model-00008-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d26709a833a2eb283714d5b76817de3c977e2cc1f5b94c2e9094656dd3bbffb9
+size 4999711728

025/model-00009-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444811413d838ed1fcf56270c37bbd5202a9ed4db5dffc1692a6cd39a1bf2a5b
+size 4966157056

025/model-00010-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d123691f67e41947c4972f3fdcb3beddc895387a2ae3718fe9c46c6483429d
+size 4664134408

025/model-00011-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9659ada06088636cfa5e9f98a66d36ac55516193c1e9a559cb53d38dea4846d1
+size 4664167408

025/model-00012-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7efecfb217c2cc64d318f5e0e189ba819bb808e96673f9507b2e0856b2e0a20f
+size 4664167408

025/model-00013-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0276b5bcc7755ad7668ab7b12b7274d7af48f526e933d9ce7060f9f3c5cc4d0
+size 4999711728

025/model-00014-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e1e45e93799f3c37541f72614a04e8ae03ca9f1aabd41150da6df5d189defc
+size 4966157056

025/model-00015-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc9041a75fc018c16afefcd3a01bb633571f78066fd400a09a54f69812aa04d6
+size 4664134408

025/model-00016-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872432b99f2e9bb8dbd85e3641a04049c7a6cfe35dfc8f90034d4c32e2df2d7c
+size 4664167408

025/model-00017-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093cc90b3fc795e28922e15a5c6e41931447be66832aa8cc8ff2562f1c93b0c7
+size 4664167408

025/model-00018-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4400cbb4f16b0d571ef50bf1d15648685d27610950a1a12acba2257daafb1e
+size 4999711728

025/model-00019-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97689a9817abb8c2153578e15aa2f10eb74c5c0f2b57f7bf0f73ce0852c72199
+size 4966157056

025/model-00020-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39bf896199869e224a95489e5056702b1afdd11faa0c7b6f8dd543713521fea
+size 4664134408

025/model-00021-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52bd737d80594f581ae89522de308e38acce533e6da57a8cad3befbb31e1e6e7
+size 4664167408

025/model-00022-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d30ff644ed18c96f8e6bb0cf6314d4bfaba365acf55b959b4fa1b757c78661
+size 4664167408

025/model-00023-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07871bf37c06d008fbce1d33918288ff39491cf5a9b75291b116deb6927e5e63
+size 4999711728

025/model-00024-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875555b63b489868973cceadee96eb84e6d40ee86341a6137ee87ad2c9a9e381
+size 4966157056

025/model-00025-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4339a5d89cc040e229a84d5929764f3430ecc2b97a8cdeab5d676d9098209f1f
+size 4664134408

025/model-00026-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68ffb7810fe9bd1da5663053feed318f65d9c4195d832667310ef048ebbf057
+size 4664167408

025/model-00027-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189aa059b991046289318e44c98608cd8c7ef070e0ac224feeffcbd2f7db8db8
+size 4664167408

025/model-00028-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0079c7a77eb485ec332df0a5e58f8cdf57b47865e08f174ad7e95d84715e31f
+size 4999711728

025/model-00029-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b74aee1a56eb6c78be4de43f28700453ba32b7d77748c009327d105f003cf4d
+size 4966173536

025/model-00030-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c3617e2eca754d44d623b17efd82bcc815e2741c74d70a7a3f3fde74aedd703
+size 2101346432

025/model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 141107412992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00030-of-00030.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
+    "model.norm.weight": "model-00029-of-00030.safetensors"
+  }
+}

025/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575119a228f98110923ffa2dedcb50e3317251b26054355d015e0b2240d566f2
+size 15984

025/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0728b56dab7abb5ef8a0d4bae3519c5767c97467bdd886d26bf19cc8599d0312
+size 15984

025/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e481d4ef1546694da7337f6bb6c658b866dcb79b85deeb477da0d27ebe851e
+size 15984

025/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353c60be37ea56fc992fca446598ceca5d1fd002aa3bd6dbb9ad740e6f47ebb3
+size 15984

025/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9107fe964ba7205e354084b85210e5a5ea1c98cfd4d38adb9cd3926945dcae4
+size 15984

025/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d1bb1abee38b92e53f3f23549b642ce0f1edcdccf7b6129847ac61636e96d5
+size 15984

025/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd5516048e20f36959601574e29e40106085a7d3cdc7bf425ce5e84633490e6
+size 15984

025/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2c46927fc06939b4c976a01e4b95dec1f8b98ceaea86d31a5d756fc30ff006
+size 15984

025/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cbebd6c6d43be382fa69bd32785749eeeaad82c53959217cd3e263b5f4ca6b5
+size 1064

025/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

025/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

025/tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

025/trainer_state.json

@@ -0,0 +1,3029 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2504113796760157,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005850733170000365,
+      "grad_norm": 0.3784801935906415,
+      "learning_rate": 7.999998479354072e-06,
+      "loss": 1.1815,
+      "step": 1
+    },
+    {
+      "epoch": 0.001170146634000073,
+      "grad_norm": 0.10369689761982695,
+      "learning_rate": 7.999993917417574e-06,
+      "loss": 1.0085,
+      "step": 2
+    },
+    {
+      "epoch": 0.0017552199510001097,
+      "grad_norm": 0.08165678751844849,
+      "learning_rate": 7.99998631419436e-06,
+      "loss": 0.934,
+      "step": 3
+    },
+    {
+      "epoch": 0.002340293268000146,
+      "grad_norm": 0.06369675215202451,
+      "learning_rate": 7.999975669690855e-06,
+      "loss": 1.0323,
+      "step": 4
+    },
+    {
+      "epoch": 0.002925366585000183,
+      "grad_norm": 0.08076101376684344,
+      "learning_rate": 7.999961983916048e-06,
+      "loss": 1.0676,
+      "step": 5
+    },
+    {
+      "epoch": 0.0035104399020002195,
+      "grad_norm": 0.06288930819751326,
+      "learning_rate": 7.999945256881502e-06,
+      "loss": 1.0421,
+      "step": 6
+    },
+    {
+      "epoch": 0.004095513219000256,
+      "grad_norm": 0.06851051488443692,
+      "learning_rate": 7.999925488601348e-06,
+      "loss": 0.9544,
+      "step": 7
+    },
+    {
+      "epoch": 0.004680586536000292,
+      "grad_norm": 0.06007707301663692,
+      "learning_rate": 7.999902679092287e-06,
+      "loss": 1.0349,
+      "step": 8
+    },
+    {
+      "epoch": 0.005265659853000329,
+      "grad_norm": 0.07674940091671953,
+      "learning_rate": 7.99987682837359e-06,
+      "loss": 1.1809,
+      "step": 9
+    },
+    {
+      "epoch": 0.005850733170000366,
+      "grad_norm": 0.06356726822529891,
+      "learning_rate": 7.999847936467093e-06,
+      "loss": 0.9502,
+      "step": 10
+    },
+    {
+      "epoch": 0.006435806487000402,
+      "grad_norm": 0.060093989725189235,
+      "learning_rate": 7.999816003397203e-06,
+      "loss": 1.0007,
+      "step": 11
+    },
+    {
+      "epoch": 0.007020879804000439,
+      "grad_norm": 0.04797598057222403,
+      "learning_rate": 7.999781029190902e-06,
+      "loss": 1.0316,
+      "step": 12
+    },
+    {
+      "epoch": 0.007605953121000476,
+      "grad_norm": 0.08827709210231136,
+      "learning_rate": 7.999743013877734e-06,
+      "loss": 1.0688,
+      "step": 13
+    },
+    {
+      "epoch": 0.008191026438000511,
+      "grad_norm": 0.04993529689396162,
+      "learning_rate": 7.999701957489811e-06,
+      "loss": 0.9695,
+      "step": 14
+    },
+    {
+      "epoch": 0.008776099755000549,
+      "grad_norm": 0.053685150458545855,
+      "learning_rate": 7.999657860061823e-06,
+      "loss": 1.0826,
+      "step": 15
+    },
+    {
+      "epoch": 0.009361173072000585,
+      "grad_norm": 0.04357397086005245,
+      "learning_rate": 7.99961072163102e-06,
+      "loss": 0.9788,
+      "step": 16
+    },
+    {
+      "epoch": 0.009946246389000622,
+      "grad_norm": 0.051838589957396514,
+      "learning_rate": 7.999560542237226e-06,
+      "loss": 1.0222,
+      "step": 17
+    },
+    {
+      "epoch": 0.010531319706000658,
+      "grad_norm": 0.04948384582310689,
+      "learning_rate": 7.999507321922833e-06,
+      "loss": 0.9882,
+      "step": 18
+    },
+    {
+      "epoch": 0.011116393023000696,
+      "grad_norm": 0.05488935540485584,
+      "learning_rate": 7.9994510607328e-06,
+      "loss": 1.0124,
+      "step": 19
+    },
+    {
+      "epoch": 0.011701466340000731,
+      "grad_norm": 0.04632979465330071,
+      "learning_rate": 7.999391758714659e-06,
+      "loss": 0.9646,
+      "step": 20
+    },
+    {
+      "epoch": 0.012286539657000767,
+      "grad_norm": 0.04102257708769348,
+      "learning_rate": 7.999329415918508e-06,
+      "loss": 0.8946,
+      "step": 21
+    },
+    {
+      "epoch": 0.012871612974000805,
+      "grad_norm": 0.045466366302330634,
+      "learning_rate": 7.999264032397013e-06,
+      "loss": 0.9973,
+      "step": 22
+    },
+    {
+      "epoch": 0.01345668629100084,
+      "grad_norm": 0.04440538659368297,
+      "learning_rate": 7.99919560820541e-06,
+      "loss": 1.0596,
+      "step": 23
+    },
+    {
+      "epoch": 0.014041759608000878,
+      "grad_norm": 0.042500986542824803,
+      "learning_rate": 7.999124143401507e-06,
+      "loss": 0.9303,
+      "step": 24
+    },
+    {
+      "epoch": 0.014626832925000914,
+      "grad_norm": 0.05180121412922999,
+      "learning_rate": 7.999049638045675e-06,
+      "loss": 0.9412,
+      "step": 25
+    },
+    {
+      "epoch": 0.015211906242000951,
+      "grad_norm": 0.06441302150178038,
+      "learning_rate": 7.998972092200859e-06,
+      "loss": 0.9986,
+      "step": 26
+    },
+    {
+      "epoch": 0.015796979559000987,
+      "grad_norm": 0.05297417453471626,
+      "learning_rate": 7.998891505932565e-06,
+      "loss": 1.0701,
+      "step": 27
+    },
+    {
+      "epoch": 0.016382052876001023,
+      "grad_norm": 0.04305692283062352,
+      "learning_rate": 7.998807879308878e-06,
+      "loss": 0.9823,
+      "step": 28
+    },
+    {
+      "epoch": 0.016967126193001062,
+      "grad_norm": 0.048331091733781785,
+      "learning_rate": 7.998721212400443e-06,
+      "loss": 0.9145,
+      "step": 29
+    },
+    {
+      "epoch": 0.017552199510001098,
+      "grad_norm": 0.04249327256576877,
+      "learning_rate": 7.998631505280477e-06,
+      "loss": 0.9469,
+      "step": 30
+    },
+    {
+      "epoch": 0.018137272827001134,
+      "grad_norm": 0.042672714299481426,
+      "learning_rate": 7.998538758024765e-06,
+      "loss": 0.9814,
+      "step": 31
+    },
+    {
+      "epoch": 0.01872234614400117,
+      "grad_norm": 0.04643044969291229,
+      "learning_rate": 7.998442970711661e-06,
+      "loss": 0.9342,
+      "step": 32
+    },
+    {
+      "epoch": 0.019307419461001205,
+      "grad_norm": 0.042411147754236,
+      "learning_rate": 7.998344143422087e-06,
+      "loss": 0.8851,
+      "step": 33
+    },
+    {
+      "epoch": 0.019892492778001244,
+      "grad_norm": 0.04407093546490425,
+      "learning_rate": 7.998242276239527e-06,
+      "loss": 1.0026,
+      "step": 34
+    },
+    {
+      "epoch": 0.02047756609500128,
+      "grad_norm": 0.044039695433035646,
+      "learning_rate": 7.998137369250046e-06,
+      "loss": 0.9637,
+      "step": 35
+    },
+    {
+      "epoch": 0.021062639412001316,
+      "grad_norm": 0.04258725681727216,
+      "learning_rate": 7.998029422542267e-06,
+      "loss": 0.9249,
+      "step": 36
+    },
+    {
+      "epoch": 0.021647712729001352,
+      "grad_norm": 0.045486820543060684,
+      "learning_rate": 7.997918436207383e-06,
+      "loss": 1.005,
+      "step": 37
+    },
+    {
+      "epoch": 0.02223278604600139,
+      "grad_norm": 0.03843585783476988,
+      "learning_rate": 7.997804410339156e-06,
+      "loss": 0.9815,
+      "step": 38
+    },
+    {
+      "epoch": 0.022817859363001427,
+      "grad_norm": 0.05544665751989288,
+      "learning_rate": 7.997687345033915e-06,
+      "loss": 0.94,
+      "step": 39
+    },
+    {
+      "epoch": 0.023402932680001463,
+      "grad_norm": 0.041440042889966715,
+      "learning_rate": 7.99756724039056e-06,
+      "loss": 0.9337,
+      "step": 40
+    },
+    {
+      "epoch": 0.0239880059970015,
+      "grad_norm": 0.040659761048442974,
+      "learning_rate": 7.997444096510552e-06,
+      "loss": 0.897,
+      "step": 41
+    },
+    {
+      "epoch": 0.024573079314001534,
+      "grad_norm": 0.06541743477477353,
+      "learning_rate": 7.997317913497925e-06,
+      "loss": 0.9325,
+      "step": 42
+    },
+    {
+      "epoch": 0.025158152631001574,
+      "grad_norm": 0.04101226832374059,
+      "learning_rate": 7.997188691459279e-06,
+      "loss": 0.9323,
+      "step": 43
+    },
+    {
+      "epoch": 0.02574322594800161,
+      "grad_norm": 0.03954326036578227,
+      "learning_rate": 7.997056430503782e-06,
+      "loss": 0.8793,
+      "step": 44
+    },
+    {
+      "epoch": 0.026328299265001645,
+      "grad_norm": 0.0396268421897809,
+      "learning_rate": 7.996921130743165e-06,
+      "loss": 0.9849,
+      "step": 45
+    },
+    {
+      "epoch": 0.02691337258200168,
+      "grad_norm": 0.03855187149117414,
+      "learning_rate": 7.996782792291732e-06,
+      "loss": 0.9328,
+      "step": 46
+    },
+    {
+      "epoch": 0.02749844589900172,
+      "grad_norm": 0.03791722568157901,
+      "learning_rate": 7.996641415266355e-06,
+      "loss": 0.9293,
+      "step": 47
+    },
+    {
+      "epoch": 0.028083519216001756,
+      "grad_norm": 0.04497262810695708,
+      "learning_rate": 7.996496999786465e-06,
+      "loss": 0.9884,
+      "step": 48
+    },
+    {
+      "epoch": 0.02866859253300179,
+      "grad_norm": 0.041089653577607424,
+      "learning_rate": 7.996349545974065e-06,
+      "loss": 0.9305,
+      "step": 49
+    },
+    {
+      "epoch": 0.029253665850001827,
+      "grad_norm": 0.04162057876282252,
+      "learning_rate": 7.996199053953729e-06,
+      "loss": 1.0771,
+      "step": 50
+    },
+    {
+      "epoch": 0.029838739167001863,
+      "grad_norm": 0.045060287442874644,
+      "learning_rate": 7.996045523852587e-06,
+      "loss": 0.9819,
+      "step": 51
+    },
+    {
+      "epoch": 0.030423812484001903,
+      "grad_norm": 0.03950486400361273,
+      "learning_rate": 7.995888955800346e-06,
+      "loss": 0.8911,
+      "step": 52
+    },
+    {
+      "epoch": 0.03100888580100194,
+      "grad_norm": 0.040638774400984866,
+      "learning_rate": 7.995729349929275e-06,
+      "loss": 0.9289,
+      "step": 53
+    },
+    {
+      "epoch": 0.031593959118001974,
+      "grad_norm": 0.04034434081592363,
+      "learning_rate": 7.995566706374206e-06,
+      "loss": 0.9529,
+      "step": 54
+    },
+    {
+      "epoch": 0.03217903243500201,
+      "grad_norm": 0.04315614004870732,
+      "learning_rate": 7.995401025272545e-06,
+      "loss": 0.9554,
+      "step": 55
+    },
+    {
+      "epoch": 0.032764105752002046,
+      "grad_norm": 0.03862522293897866,
+      "learning_rate": 7.995232306764258e-06,
+      "loss": 0.9604,
+      "step": 56
+    },
+    {
+      "epoch": 0.03334917906900208,
+      "grad_norm": 0.042952485422922036,
+      "learning_rate": 7.995060550991879e-06,
+      "loss": 0.9731,
+      "step": 57
+    },
+    {
+      "epoch": 0.033934252386002124,
+      "grad_norm": 0.04399639647859174,
+      "learning_rate": 7.994885758100508e-06,
+      "loss": 0.868,
+      "step": 58
+    },
+    {
+      "epoch": 0.03451932570300216,
+      "grad_norm": 0.03794998627596821,
+      "learning_rate": 7.99470792823781e-06,
+      "loss": 0.9176,
+      "step": 59
+    },
+    {
+      "epoch": 0.035104399020002196,
+      "grad_norm": 0.046410465067380204,
+      "learning_rate": 7.99452706155402e-06,
+      "loss": 0.9456,
+      "step": 60
+    },
+    {
+      "epoch": 0.03568947233700223,
+      "grad_norm": 0.04773216743183266,
+      "learning_rate": 7.994343158201927e-06,
+      "loss": 1.0049,
+      "step": 61
+    },
+    {
+      "epoch": 0.03627454565400227,
+      "grad_norm": 0.04395331205981261,
+      "learning_rate": 7.994156218336901e-06,
+      "loss": 0.9197,
+      "step": 62
+    },
+    {
+      "epoch": 0.0368596189710023,
+      "grad_norm": 0.04353152162367831,
+      "learning_rate": 7.993966242116865e-06,
+      "loss": 0.8978,
+      "step": 63
+    },
+    {
+      "epoch": 0.03744469228800234,
+      "grad_norm": 0.041195331266407585,
+      "learning_rate": 7.993773229702312e-06,
+      "loss": 0.965,
+      "step": 64
+    },
+    {
+      "epoch": 0.038029765605002375,
+      "grad_norm": 0.050163343033375746,
+      "learning_rate": 7.993577181256304e-06,
+      "loss": 0.8876,
+      "step": 65
+    },
+    {
+      "epoch": 0.03861483892200241,
+      "grad_norm": 0.06660490581550026,
+      "learning_rate": 7.993378096944456e-06,
+      "loss": 0.9082,
+      "step": 66
+    },
+    {
+      "epoch": 0.03919991223900245,
+      "grad_norm": 0.03984407119317513,
+      "learning_rate": 7.99317597693496e-06,
+      "loss": 0.9233,
+      "step": 67
+    },
+    {
+      "epoch": 0.03978498555600249,
+      "grad_norm": 0.04866369054757869,
+      "learning_rate": 7.992970821398567e-06,
+      "loss": 0.9349,
+      "step": 68
+    },
+    {
+      "epoch": 0.040370058873002525,
+      "grad_norm": 0.04990567711730111,
+      "learning_rate": 7.99276263050859e-06,
+      "loss": 0.985,
+      "step": 69
+    },
+    {
+      "epoch": 0.04095513219000256,
+      "grad_norm": 0.17411986574945643,
+      "learning_rate": 7.992551404440914e-06,
+      "loss": 1.0208,
+      "step": 70
+    },
+    {
+      "epoch": 0.041540205507002596,
+      "grad_norm": 0.04353986815925501,
+      "learning_rate": 7.992337143373981e-06,
+      "loss": 0.9633,
+      "step": 71
+    },
+    {
+      "epoch": 0.04212527882400263,
+      "grad_norm": 0.05318272939257367,
+      "learning_rate": 7.9921198474888e-06,
+      "loss": 1.0015,
+      "step": 72
+    },
+    {
+      "epoch": 0.04271035214100267,
+      "grad_norm": 0.059411931897509304,
+      "learning_rate": 7.991899516968942e-06,
+      "loss": 1.0224,
+      "step": 73
+    },
+    {
+      "epoch": 0.043295425458002704,
+      "grad_norm": 0.05746696657441689,
+      "learning_rate": 7.991676152000545e-06,
+      "loss": 0.9817,
+      "step": 74
+    },
+    {
+      "epoch": 0.04388049877500274,
+      "grad_norm": 0.03994063377968752,
+      "learning_rate": 7.991449752772307e-06,
+      "loss": 0.899,
+      "step": 75
+    },
+    {
+      "epoch": 0.04446557209200278,
+      "grad_norm": 0.05114807327866483,
+      "learning_rate": 7.991220319475492e-06,
+      "loss": 0.9627,
+      "step": 76
+    },
+    {
+      "epoch": 0.04505064540900282,
+      "grad_norm": 0.043413594203031196,
+      "learning_rate": 7.990987852303923e-06,
+      "loss": 0.9385,
+      "step": 77
+    },
+    {
+      "epoch": 0.045635718726002854,
+      "grad_norm": 0.044141893159488445,
+      "learning_rate": 7.990752351453994e-06,
+      "loss": 0.9214,
+      "step": 78
+    },
+    {
+      "epoch": 0.04622079204300289,
+      "grad_norm": 0.07098639926950194,
+      "learning_rate": 7.990513817124652e-06,
+      "loss": 0.9762,
+      "step": 79
+    },
+    {
+      "epoch": 0.046805865360002925,
+      "grad_norm": 0.04487096138718826,
+      "learning_rate": 7.990272249517416e-06,
+      "loss": 0.9379,
+      "step": 80
+    },
+    {
+      "epoch": 0.04739093867700296,
+      "grad_norm": 0.040488382771263605,
+      "learning_rate": 7.990027648836359e-06,
+      "loss": 0.9563,
+      "step": 81
+    },
+    {
+      "epoch": 0.047976011994003,
+      "grad_norm": 0.04352730030611419,
+      "learning_rate": 7.989780015288123e-06,
+      "loss": 0.9488,
+      "step": 82
+    },
+    {
+      "epoch": 0.04856108531100303,
+      "grad_norm": 0.04413441845817798,
+      "learning_rate": 7.98952934908191e-06,
+      "loss": 1.0336,
+      "step": 83
+    },
+    {
+      "epoch": 0.04914615862800307,
+      "grad_norm": 0.04193745680850997,
+      "learning_rate": 7.989275650429482e-06,
+      "loss": 0.8785,
+      "step": 84
+    },
+    {
+      "epoch": 0.04973123194500311,
+      "grad_norm": 0.04475381091812719,
+      "learning_rate": 7.989018919545165e-06,
+      "loss": 0.9443,
+      "step": 85
+    },
+    {
+      "epoch": 0.05031630526200315,
+      "grad_norm": 0.04234754821679888,
+      "learning_rate": 7.988759156645845e-06,
+      "loss": 0.9564,
+      "step": 86
+    },
+    {
+      "epoch": 0.05090137857900318,
+      "grad_norm": 0.054324472784088765,
+      "learning_rate": 7.988496361950972e-06,
+      "loss": 0.9824,
+      "step": 87
+    },
+    {
+      "epoch": 0.05148645189600322,
+      "grad_norm": 0.051967709927586946,
+      "learning_rate": 7.988230535682556e-06,
+      "loss": 0.914,
+      "step": 88
+    },
+    {
+      "epoch": 0.052071525213003254,
+      "grad_norm": 0.03996756018971234,
+      "learning_rate": 7.987961678065169e-06,
+      "loss": 0.9421,
+      "step": 89
+    },
+    {
+      "epoch": 0.05265659853000329,
+      "grad_norm": 0.07556612961446735,
+      "learning_rate": 7.987689789325939e-06,
+      "loss": 0.9791,
+      "step": 90
+    },
+    {
+      "epoch": 0.053241671847003326,
+      "grad_norm": 0.04557130060143385,
+      "learning_rate": 7.987414869694562e-06,
+      "loss": 0.9318,
+      "step": 91
+    },
+    {
+      "epoch": 0.05382674516400336,
+      "grad_norm": 0.0424700455078842,
+      "learning_rate": 7.98713691940329e-06,
+      "loss": 0.9745,
+      "step": 92
+    },
+    {
+      "epoch": 0.0544118184810034,
+      "grad_norm": 0.07879025661937863,
+      "learning_rate": 7.986855938686935e-06,
+      "loss": 0.9614,
+      "step": 93
+    },
+    {
+      "epoch": 0.05499689179800344,
+      "grad_norm": 0.04227267907542001,
+      "learning_rate": 7.986571927782871e-06,
+      "loss": 0.9317,
+      "step": 94
+    },
+    {
+      "epoch": 0.055581965115003476,
+      "grad_norm": 0.042275976377898476,
+      "learning_rate": 7.986284886931033e-06,
+      "loss": 0.8982,
+      "step": 95
+    },
+    {
+      "epoch": 0.05616703843200351,
+      "grad_norm": 0.0457764180229334,
+      "learning_rate": 7.985994816373913e-06,
+      "loss": 0.8803,
+      "step": 96
+    },
+    {
+      "epoch": 0.05675211174900355,
+      "grad_norm": 0.04305545472943831,
+      "learning_rate": 7.985701716356565e-06,
+      "loss": 0.9786,
+      "step": 97
+    },
+    {
+      "epoch": 0.05733718506600358,
+      "grad_norm": 0.045580685701444475,
+      "learning_rate": 7.985405587126597e-06,
+      "loss": 0.9036,
+      "step": 98
+    },
+    {
+      "epoch": 0.05792225838300362,
+      "grad_norm": 0.0442896526405325,
+      "learning_rate": 7.985106428934183e-06,
+      "loss": 0.9871,
+      "step": 99
+    },
+    {
+      "epoch": 0.058507331700003655,
+      "grad_norm": 0.04396583794537118,
+      "learning_rate": 7.984804242032051e-06,
+      "loss": 1.0145,
+      "step": 100
+    },
+    {
+      "epoch": 0.05909240501700369,
+      "grad_norm": 0.04488641679254391,
+      "learning_rate": 7.984499026675494e-06,
+      "loss": 0.9673,
+      "step": 101
+    },
+    {
+      "epoch": 0.05967747833400373,
+      "grad_norm": 0.0402258783966036,
+      "learning_rate": 7.984190783122351e-06,
+      "loss": 1.0458,
+      "step": 102
+    },
+    {
+      "epoch": 0.06026255165100377,
+      "grad_norm": 0.048502182555142354,
+      "learning_rate": 7.983879511633036e-06,
+      "loss": 0.8879,
+      "step": 103
+    },
+    {
+      "epoch": 0.060847624968003805,
+      "grad_norm": 0.04818474096979939,
+      "learning_rate": 7.983565212470504e-06,
+      "loss": 0.9467,
+      "step": 104
+    },
+    {
+      "epoch": 0.06143269828500384,
+      "grad_norm": 0.04176125713160911,
+      "learning_rate": 7.983247885900283e-06,
+      "loss": 0.9266,
+      "step": 105
+    },
+    {
+      "epoch": 0.06201777160200388,
+      "grad_norm": 0.04212530605033032,
+      "learning_rate": 7.982927532190447e-06,
+      "loss": 0.9179,
+      "step": 106
+    },
+    {
+      "epoch": 0.06260284491900392,
+      "grad_norm": 0.037198964746819226,
+      "learning_rate": 7.982604151611633e-06,
+      "loss": 1.0018,
+      "step": 107
+    },
+    {
+      "epoch": 0.06318791823600395,
+      "grad_norm": 0.04090799839826158,
+      "learning_rate": 7.982277744437035e-06,
+      "loss": 0.8756,
+      "step": 108
+    },
+    {
+      "epoch": 0.06377299155300399,
+      "grad_norm": 0.03857422273289164,
+      "learning_rate": 7.981948310942402e-06,
+      "loss": 0.8855,
+      "step": 109
+    },
+    {
+      "epoch": 0.06435806487000402,
+      "grad_norm": 0.05241752689478532,
+      "learning_rate": 7.981615851406039e-06,
+      "loss": 0.8862,
+      "step": 110
+    },
+    {
+      "epoch": 0.06494313818700406,
+      "grad_norm": 0.04086973369607326,
+      "learning_rate": 7.981280366108814e-06,
+      "loss": 0.9221,
+      "step": 111
+    },
+    {
+      "epoch": 0.06552821150400409,
+      "grad_norm": 0.03931043694281754,
+      "learning_rate": 7.98094185533414e-06,
+      "loss": 0.9417,
+      "step": 112
+    },
+    {
+      "epoch": 0.06611328482100413,
+      "grad_norm": 0.04169878931857935,
+      "learning_rate": 7.980600319367995e-06,
+      "loss": 0.958,
+      "step": 113
+    },
+    {
+      "epoch": 0.06669835813800416,
+      "grad_norm": 0.044230077430854955,
+      "learning_rate": 7.980255758498908e-06,
+      "loss": 0.9265,
+      "step": 114
+    },
+    {
+      "epoch": 0.0672834314550042,
+      "grad_norm": 0.04488148180330816,
+      "learning_rate": 7.979908173017968e-06,
+      "loss": 0.8908,
+      "step": 115
+    },
+    {
+      "epoch": 0.06786850477200425,
+      "grad_norm": 0.042038370275589085,
+      "learning_rate": 7.979557563218815e-06,
+      "loss": 0.8961,
+      "step": 116
+    },
+    {
+      "epoch": 0.06845357808900428,
+      "grad_norm": 0.04747064970378541,
+      "learning_rate": 7.979203929397646e-06,
+      "loss": 1.0609,
+      "step": 117
+    },
+    {
+      "epoch": 0.06903865140600432,
+      "grad_norm": 0.04392999493678844,
+      "learning_rate": 7.97884727185321e-06,
+      "loss": 0.9001,
+      "step": 118
+    },
+    {
+      "epoch": 0.06962372472300435,
+      "grad_norm": 0.040693633998808994,
+      "learning_rate": 7.978487590886814e-06,
+      "loss": 0.8562,
+      "step": 119
+    },
+    {
+      "epoch": 0.07020879804000439,
+      "grad_norm": 0.08337676841807191,
+      "learning_rate": 7.978124886802316e-06,
+      "loss": 0.9344,
+      "step": 120
+    },
+    {
+      "epoch": 0.07079387135700442,
+      "grad_norm": 0.03951441645023813,
+      "learning_rate": 7.977759159906134e-06,
+      "loss": 0.9182,
+      "step": 121
+    },
+    {
+      "epoch": 0.07137894467400446,
+      "grad_norm": 0.04427536962304041,
+      "learning_rate": 7.977390410507229e-06,
+      "loss": 0.9079,
+      "step": 122
+    },
+    {
+      "epoch": 0.07196401799100449,
+      "grad_norm": 0.047402666476443076,
+      "learning_rate": 7.977018638917126e-06,
+      "loss": 0.9442,
+      "step": 123
+    },
+    {
+      "epoch": 0.07254909130800453,
+      "grad_norm": 0.07806155365092546,
+      "learning_rate": 7.976643845449897e-06,
+      "loss": 0.9453,
+      "step": 124
+    },
+    {
+      "epoch": 0.07313416462500458,
+      "grad_norm": 0.04187989433422361,
+      "learning_rate": 7.97626603042217e-06,
+      "loss": 0.9762,
+      "step": 125
+    },
+    {
+      "epoch": 0.0737192379420046,
+      "grad_norm": 0.038153971027990764,
+      "learning_rate": 7.975885194153125e-06,
+      "loss": 0.9377,
+      "step": 126
+    },
+    {
+      "epoch": 0.07430431125900465,
+      "grad_norm": 0.04398811005912341,
+      "learning_rate": 7.975501336964492e-06,
+      "loss": 0.9655,
+      "step": 127
+    },
+    {
+      "epoch": 0.07488938457600468,
+      "grad_norm": 0.04310577216463342,
+      "learning_rate": 7.975114459180555e-06,
+      "loss": 0.9082,
+      "step": 128
+    },
+    {
+      "epoch": 0.07547445789300472,
+      "grad_norm": 0.04552741227747631,
+      "learning_rate": 7.97472456112815e-06,
+      "loss": 0.8667,
+      "step": 129
+    },
+    {
+      "epoch": 0.07605953121000475,
+      "grad_norm": 0.0406705187810207,
+      "learning_rate": 7.974331643136666e-06,
+      "loss": 0.9286,
+      "step": 130
+    },
+    {
+      "epoch": 0.07664460452700479,
+      "grad_norm": 0.16819457832404855,
+      "learning_rate": 7.973935705538039e-06,
+      "loss": 0.9724,
+      "step": 131
+    },
+    {
+      "epoch": 0.07722967784400482,
+      "grad_norm": 0.04524796652654962,
+      "learning_rate": 7.973536748666756e-06,
+      "loss": 0.961,
+      "step": 132
+    },
+    {
+      "epoch": 0.07781475116100486,
+      "grad_norm": 0.051171072191227115,
+      "learning_rate": 7.973134772859862e-06,
+      "loss": 0.9513,
+      "step": 133
+    },
+    {
+      "epoch": 0.0783998244780049,
+      "grad_norm": 0.044436153110071305,
+      "learning_rate": 7.972729778456946e-06,
+      "loss": 0.9363,
+      "step": 134
+    },
+    {
+      "epoch": 0.07898489779500494,
+      "grad_norm": 0.04485419817375143,
+      "learning_rate": 7.97232176580015e-06,
+      "loss": 0.8583,
+      "step": 135
+    },
+    {
+      "epoch": 0.07956997111200498,
+      "grad_norm": 0.044866876801222304,
+      "learning_rate": 7.971910735234161e-06,
+      "loss": 0.9859,
+      "step": 136
+    },
+    {
+      "epoch": 0.080155044429005,
+      "grad_norm": 0.03934716109284772,
+      "learning_rate": 7.971496687106219e-06,
+      "loss": 0.8592,
+      "step": 137
+    },
+    {
+      "epoch": 0.08074011774600505,
+      "grad_norm": 0.041852675369480244,
+      "learning_rate": 7.971079621766117e-06,
+      "loss": 0.9353,
+      "step": 138
+    },
+    {
+      "epoch": 0.08132519106300508,
+      "grad_norm": 0.3430745253576026,
+      "learning_rate": 7.97065953956619e-06,
+      "loss": 0.9602,
+      "step": 139
+    },
+    {
+      "epoch": 0.08191026438000512,
+      "grad_norm": 0.44783710464834237,
+      "learning_rate": 7.970236440861327e-06,
+      "loss": 0.9833,
+      "step": 140
+    },
+    {
+      "epoch": 0.08249533769700515,
+      "grad_norm": 0.29750847371388817,
+      "learning_rate": 7.96981032600896e-06,
+      "loss": 0.8244,
+      "step": 141
+    },
+    {
+      "epoch": 0.08308041101400519,
+      "grad_norm": 0.169443611740874,
+      "learning_rate": 7.969381195369076e-06,
+      "loss": 0.8983,
+      "step": 142
+    },
+    {
+      "epoch": 0.08366548433100524,
+      "grad_norm": 0.04111262427570532,
+      "learning_rate": 7.968949049304204e-06,
+      "loss": 0.9552,
+      "step": 143
+    },
+    {
+      "epoch": 0.08425055764800526,
+      "grad_norm": 0.04087231642049412,
+      "learning_rate": 7.968513888179421e-06,
+      "loss": 0.9051,
+      "step": 144
+    },
+    {
+      "epoch": 0.08483563096500531,
+      "grad_norm": 0.05663350951363164,
+      "learning_rate": 7.968075712362356e-06,
+      "loss": 0.8366,
+      "step": 145
+    },
+    {
+      "epoch": 0.08542070428200534,
+      "grad_norm": 0.04202895629977615,
+      "learning_rate": 7.967634522223179e-06,
+      "loss": 0.8115,
+      "step": 146
+    },
+    {
+      "epoch": 0.08600577759900538,
+      "grad_norm": 0.04238111014919017,
+      "learning_rate": 7.96719031813461e-06,
+      "loss": 0.9086,
+      "step": 147
+    },
+    {
+      "epoch": 0.08659085091600541,
+      "grad_norm": 0.04226501020383857,
+      "learning_rate": 7.966743100471913e-06,
+      "loss": 0.9286,
+      "step": 148
+    },
+    {
+      "epoch": 0.08717592423300545,
+      "grad_norm": 0.046325797442375215,
+      "learning_rate": 7.9662928696129e-06,
+      "loss": 0.9393,
+      "step": 149
+    },
+    {
+      "epoch": 0.08776099755000548,
+      "grad_norm": 0.05532068772615188,
+      "learning_rate": 7.965839625937926e-06,
+      "loss": 0.9202,
+      "step": 150
+    },
+    {
+      "epoch": 0.08834607086700552,
+      "grad_norm": 0.039360829289514745,
+      "learning_rate": 7.965383369829894e-06,
+      "loss": 0.908,
+      "step": 151
+    },
+    {
+      "epoch": 0.08893114418400556,
+      "grad_norm": 0.04965498407233415,
+      "learning_rate": 7.964924101674252e-06,
+      "loss": 0.9406,
+      "step": 152
+    },
+    {
+      "epoch": 0.0895162175010056,
+      "grad_norm": 0.04177674200968805,
+      "learning_rate": 7.964461821858987e-06,
+      "loss": 0.8933,
+      "step": 153
+    },
+    {
+      "epoch": 0.09010129081800564,
+      "grad_norm": 0.04711456314429998,
+      "learning_rate": 7.963996530774639e-06,
+      "loss": 1.0111,
+      "step": 154
+    },
+    {
+      "epoch": 0.09068636413500566,
+      "grad_norm": 0.045100723994096155,
+      "learning_rate": 7.963528228814285e-06,
+      "loss": 0.9806,
+      "step": 155
+    },
+    {
+      "epoch": 0.09127143745200571,
+      "grad_norm": 0.09448573408012474,
+      "learning_rate": 7.96305691637355e-06,
+      "loss": 0.9142,
+      "step": 156
+    },
+    {
+      "epoch": 0.09185651076900574,
+      "grad_norm": 0.04297907772876167,
+      "learning_rate": 7.962582593850596e-06,
+      "loss": 0.8852,
+      "step": 157
+    },
+    {
+      "epoch": 0.09244158408600578,
+      "grad_norm": 0.05151683390684187,
+      "learning_rate": 7.962105261646138e-06,
+      "loss": 0.9975,
+      "step": 158
+    },
+    {
+      "epoch": 0.09302665740300581,
+      "grad_norm": 0.07242957126413647,
+      "learning_rate": 7.961624920163423e-06,
+      "loss": 0.9196,
+      "step": 159
+    },
+    {
+      "epoch": 0.09361173072000585,
+      "grad_norm": 0.08840439035290122,
+      "learning_rate": 7.961141569808248e-06,
+      "loss": 0.92,
+      "step": 160
+    },
+    {
+      "epoch": 0.0941968040370059,
+      "grad_norm": 0.11047843778949552,
+      "learning_rate": 7.960655210988948e-06,
+      "loss": 0.9452,
+      "step": 161
+    },
+    {
+      "epoch": 0.09478187735400592,
+      "grad_norm": 0.04275273565605597,
+      "learning_rate": 7.960165844116399e-06,
+      "loss": 0.9641,
+      "step": 162
+    },
+    {
+      "epoch": 0.09536695067100597,
+      "grad_norm": 0.05662855927390397,
+      "learning_rate": 7.959673469604025e-06,
+      "loss": 0.9354,
+      "step": 163
+    },
+    {
+      "epoch": 0.095952023988006,
+      "grad_norm": 0.04769002643125012,
+      "learning_rate": 7.959178087867779e-06,
+      "loss": 0.9087,
+      "step": 164
+    },
+    {
+      "epoch": 0.09653709730500604,
+      "grad_norm": 0.050744023655463925,
+      "learning_rate": 7.958679699326164e-06,
+      "loss": 0.9561,
+      "step": 165
+    },
+    {
+      "epoch": 0.09712217062200607,
+      "grad_norm": 0.058451109924341715,
+      "learning_rate": 7.958178304400222e-06,
+      "loss": 0.9881,
+      "step": 166
+    },
+    {
+      "epoch": 0.09770724393900611,
+      "grad_norm": 0.04338399471073774,
+      "learning_rate": 7.95767390351353e-06,
+      "loss": 0.9705,
+      "step": 167
+    },
+    {
+      "epoch": 0.09829231725600614,
+      "grad_norm": 0.04901291931441639,
+      "learning_rate": 7.95716649709221e-06,
+      "loss": 0.9229,
+      "step": 168
+    },
+    {
+      "epoch": 0.09887739057300618,
+      "grad_norm": 0.044284928725944674,
+      "learning_rate": 7.95665608556492e-06,
+      "loss": 0.9493,
+      "step": 169
+    },
+    {
+      "epoch": 0.09946246389000622,
+      "grad_norm": 0.04914804115067185,
+      "learning_rate": 7.956142669362855e-06,
+      "loss": 0.9879,
+      "step": 170
+    },
+    {
+      "epoch": 0.10004753720700625,
+      "grad_norm": 0.04087870881565583,
+      "learning_rate": 7.955626248919752e-06,
+      "loss": 0.9435,
+      "step": 171
+    },
+    {
+      "epoch": 0.1006326105240063,
+      "grad_norm": 0.04938743203389444,
+      "learning_rate": 7.955106824671888e-06,
+      "loss": 0.8813,
+      "step": 172
+    },
+    {
+      "epoch": 0.10121768384100632,
+      "grad_norm": 0.04440441336302364,
+      "learning_rate": 7.95458439705807e-06,
+      "loss": 0.954,
+      "step": 173
+    },
+    {
+      "epoch": 0.10180275715800637,
+      "grad_norm": 0.04052619663535755,
+      "learning_rate": 7.954058966519649e-06,
+      "loss": 0.8759,
+      "step": 174
+    },
+    {
+      "epoch": 0.1023878304750064,
+      "grad_norm": 0.04315943430366373,
+      "learning_rate": 7.953530533500507e-06,
+      "loss": 0.8621,
+      "step": 175
+    },
+    {
+      "epoch": 0.10297290379200644,
+      "grad_norm": 0.07065437183104553,
+      "learning_rate": 7.952999098447072e-06,
+      "loss": 0.9796,
+      "step": 176
+    },
+    {
+      "epoch": 0.10355797710900647,
+      "grad_norm": 0.04286710979601013,
+      "learning_rate": 7.952464661808297e-06,
+      "loss": 0.9187,
+      "step": 177
+    },
+    {
+      "epoch": 0.10414305042600651,
+      "grad_norm": 0.044637305084684484,
+      "learning_rate": 7.951927224035678e-06,
+      "loss": 0.8772,
+      "step": 178
+    },
+    {
+      "epoch": 0.10472812374300655,
+      "grad_norm": 0.04369651860095562,
+      "learning_rate": 7.951386785583244e-06,
+      "loss": 0.8969,
+      "step": 179
+    },
+    {
+      "epoch": 0.10531319706000658,
+      "grad_norm": 0.05048322425196143,
+      "learning_rate": 7.950843346907559e-06,
+      "loss": 0.8907,
+      "step": 180
+    },
+    {
+      "epoch": 0.10589827037700662,
+      "grad_norm": 0.03884181381210202,
+      "learning_rate": 7.95029690846772e-06,
+      "loss": 0.931,
+      "step": 181
+    },
+    {
+      "epoch": 0.10648334369400665,
+      "grad_norm": 0.05060670376656713,
+      "learning_rate": 7.949747470725362e-06,
+      "loss": 0.8624,
+      "step": 182
+    },
+    {
+      "epoch": 0.1070684170110067,
+      "grad_norm": 0.04162121727818916,
+      "learning_rate": 7.949195034144653e-06,
+      "loss": 0.9141,
+      "step": 183
+    },
+    {
+      "epoch": 0.10765349032800672,
+      "grad_norm": 0.04729330740672752,
+      "learning_rate": 7.94863959919229e-06,
+      "loss": 0.921,
+      "step": 184
+    },
+    {
+      "epoch": 0.10823856364500677,
+      "grad_norm": 0.04459204791909808,
+      "learning_rate": 7.948081166337509e-06,
+      "loss": 0.8993,
+      "step": 185
+    },
+    {
+      "epoch": 0.1088236369620068,
+      "grad_norm": 0.04645986236352756,
+      "learning_rate": 7.947519736052075e-06,
+      "loss": 0.9158,
+      "step": 186
+    },
+    {
+      "epoch": 0.10940871027900684,
+      "grad_norm": 0.04275967646092167,
+      "learning_rate": 7.946955308810285e-06,
+      "loss": 0.9387,
+      "step": 187
+    },
+    {
+      "epoch": 0.10999378359600688,
+      "grad_norm": 0.07421648959437231,
+      "learning_rate": 7.94638788508897e-06,
+      "loss": 0.8497,
+      "step": 188
+    },
+    {
+      "epoch": 0.11057885691300691,
+      "grad_norm": 0.04955170539289863,
+      "learning_rate": 7.945817465367493e-06,
+      "loss": 0.8525,
+      "step": 189
+    },
+    {
+      "epoch": 0.11116393023000695,
+      "grad_norm": 0.12013696366466048,
+      "learning_rate": 7.945244050127744e-06,
+      "loss": 0.9616,
+      "step": 190
+    },
+    {
+      "epoch": 0.11174900354700698,
+      "grad_norm": 0.040829512145039985,
+      "learning_rate": 7.944667639854148e-06,
+      "loss": 0.8344,
+      "step": 191
+    },
+    {
+      "epoch": 0.11233407686400702,
+      "grad_norm": 0.05068364591326354,
+      "learning_rate": 7.944088235033657e-06,
+      "loss": 0.9403,
+      "step": 192
+    },
+    {
+      "epoch": 0.11291915018100705,
+      "grad_norm": 0.0499939002215986,
+      "learning_rate": 7.943505836155753e-06,
+      "loss": 0.9475,
+      "step": 193
+    },
+    {
+      "epoch": 0.1135042234980071,
+      "grad_norm": 0.05407026250866459,
+      "learning_rate": 7.94292044371245e-06,
+      "loss": 0.9101,
+      "step": 194
+    },
+    {
+      "epoch": 0.11408929681500712,
+      "grad_norm": 0.06417314751489454,
+      "learning_rate": 7.94233205819829e-06,
+      "loss": 0.8787,
+      "step": 195
+    },
+    {
+      "epoch": 0.11467437013200717,
+      "grad_norm": 0.03871241656337873,
+      "learning_rate": 7.941740680110343e-06,
+      "loss": 0.9059,
+      "step": 196
+    },
+    {
+      "epoch": 0.11525944344900721,
+      "grad_norm": 0.041501526897382096,
+      "learning_rate": 7.941146309948205e-06,
+      "loss": 0.8946,
+      "step": 197
+    },
+    {
+      "epoch": 0.11584451676600724,
+      "grad_norm": 0.037938175729775744,
+      "learning_rate": 7.940548948214005e-06,
+      "loss": 0.8534,
+      "step": 198
+    },
+    {
+      "epoch": 0.11642959008300728,
+      "grad_norm": 0.038697315108935856,
+      "learning_rate": 7.939948595412394e-06,
+      "loss": 0.9671,
+      "step": 199
+    },
+    {
+      "epoch": 0.11701466340000731,
+      "grad_norm": 0.040128164685532784,
+      "learning_rate": 7.939345252050552e-06,
+      "loss": 0.9452,
+      "step": 200
+    },
+    {
+      "epoch": 0.11759973671700735,
+      "grad_norm": 0.04159138776071103,
+      "learning_rate": 7.938738918638187e-06,
+      "loss": 0.9525,
+      "step": 201
+    },
+    {
+      "epoch": 0.11818481003400738,
+      "grad_norm": 0.044356876333774484,
+      "learning_rate": 7.93812959568753e-06,
+      "loss": 0.8863,
+      "step": 202
+    },
+    {
+      "epoch": 0.11876988335100742,
+      "grad_norm": 0.04110203273326361,
+      "learning_rate": 7.93751728371334e-06,
+      "loss": 0.8585,
+      "step": 203
+    },
+    {
+      "epoch": 0.11935495666800745,
+      "grad_norm": 0.03907623380015084,
+      "learning_rate": 7.9369019832329e-06,
+      "loss": 0.8901,
+      "step": 204
+    },
+    {
+      "epoch": 0.1199400299850075,
+      "grad_norm": 0.06841747716076531,
+      "learning_rate": 7.936283694766016e-06,
+      "loss": 0.9382,
+      "step": 205
+    },
+    {
+      "epoch": 0.12052510330200754,
+      "grad_norm": 0.03864267029597622,
+      "learning_rate": 7.935662418835023e-06,
+      "loss": 0.9445,
+      "step": 206
+    },
+    {
+      "epoch": 0.12111017661900757,
+      "grad_norm": 0.04187477888552647,
+      "learning_rate": 7.935038155964775e-06,
+      "loss": 0.949,
+      "step": 207
+    },
+    {
+      "epoch": 0.12169524993600761,
+      "grad_norm": 0.03844046778107278,
+      "learning_rate": 7.934410906682653e-06,
+      "loss": 0.8185,
+      "step": 208
+    },
+    {
+      "epoch": 0.12228032325300764,
+      "grad_norm": 0.03894778215959397,
+      "learning_rate": 7.933780671518558e-06,
+      "loss": 0.8226,
+      "step": 209
+    },
+    {
+      "epoch": 0.12286539657000768,
+      "grad_norm": 0.05316470088962357,
+      "learning_rate": 7.933147451004914e-06,
+      "loss": 0.9149,
+      "step": 210
+    },
+    {
+      "epoch": 0.12345046988700771,
+      "grad_norm": 0.04054196015487159,
+      "learning_rate": 7.932511245676669e-06,
+      "loss": 0.907,
+      "step": 211
+    },
+    {
+      "epoch": 0.12403554320400775,
+      "grad_norm": 0.04197248747401694,
+      "learning_rate": 7.931872056071292e-06,
+      "loss": 0.8974,
+      "step": 212
+    },
+    {
+      "epoch": 0.12462061652100778,
+      "grad_norm": 0.04107563523275673,
+      "learning_rate": 7.931229882728771e-06,
+      "loss": 0.8758,
+      "step": 213
+    },
+    {
+      "epoch": 0.12520568983800784,
+      "grad_norm": 0.04898006391812857,
+      "learning_rate": 7.930584726191616e-06,
+      "loss": 0.9015,
+      "step": 214
+    },
+    {
+      "epoch": 0.12579076315500787,
+      "grad_norm": 0.053828637223887026,
+      "learning_rate": 7.92993658700486e-06,
+      "loss": 0.9095,
+      "step": 215
+    },
+    {
+      "epoch": 0.1263758364720079,
+      "grad_norm": 0.041596264391364365,
+      "learning_rate": 7.929285465716051e-06,
+      "loss": 0.9324,
+      "step": 216
+    },
+    {
+      "epoch": 0.12696090978900793,
+      "grad_norm": 0.04270202089537964,
+      "learning_rate": 7.928631362875258e-06,
+      "loss": 0.9712,
+      "step": 217
+    },
+    {
+      "epoch": 0.12754598310600798,
+      "grad_norm": 0.04508600982672278,
+      "learning_rate": 7.927974279035069e-06,
+      "loss": 0.8526,
+      "step": 218
+    },
+    {
+      "epoch": 0.128131056423008,
+      "grad_norm": 0.04210505656160864,
+      "learning_rate": 7.927314214750592e-06,
+      "loss": 0.8483,
+      "step": 219
+    },
+    {
+      "epoch": 0.12871612974000804,
+      "grad_norm": 0.04228456764136032,
+      "learning_rate": 7.926651170579451e-06,
+      "loss": 1.0049,
+      "step": 220
+    },
+    {
+      "epoch": 0.12930120305700807,
+      "grad_norm": 0.039866451292078504,
+      "learning_rate": 7.92598514708179e-06,
+      "loss": 0.9421,
+      "step": 221
+    },
+    {
+      "epoch": 0.12988627637400812,
+      "grad_norm": 0.037613132725661406,
+      "learning_rate": 7.925316144820263e-06,
+      "loss": 0.9474,
+      "step": 222
+    },
+    {
+      "epoch": 0.13047134969100815,
+      "grad_norm": 0.04168086524600805,
+      "learning_rate": 7.92464416436005e-06,
+      "loss": 0.9058,
+      "step": 223
+    },
+    {
+      "epoch": 0.13105642300800818,
+      "grad_norm": 0.039621964711338775,
+      "learning_rate": 7.923969206268839e-06,
+      "loss": 0.9086,
+      "step": 224
+    },
+    {
+      "epoch": 0.13164149632500824,
+      "grad_norm": 0.05209282643387043,
+      "learning_rate": 7.923291271116838e-06,
+      "loss": 0.9298,
+      "step": 225
+    },
+    {
+      "epoch": 0.13222656964200827,
+      "grad_norm": 0.044258185244179175,
+      "learning_rate": 7.92261035947677e-06,
+      "loss": 0.8925,
+      "step": 226
+    },
+    {
+      "epoch": 0.1328116429590083,
+      "grad_norm": 0.039844108391859055,
+      "learning_rate": 7.92192647192387e-06,
+      "loss": 0.8392,
+      "step": 227
+    },
+    {
+      "epoch": 0.13339671627600833,
+      "grad_norm": 0.044744651789733476,
+      "learning_rate": 7.92123960903589e-06,
+      "loss": 0.9329,
+      "step": 228
+    },
+    {
+      "epoch": 0.13398178959300838,
+      "grad_norm": 0.04494192821446448,
+      "learning_rate": 7.92054977139309e-06,
+      "loss": 0.8606,
+      "step": 229
+    },
+    {
+      "epoch": 0.1345668629100084,
+      "grad_norm": 0.05863838322698434,
+      "learning_rate": 7.919856959578252e-06,
+      "loss": 0.9302,
+      "step": 230
+    },
+    {
+      "epoch": 0.13515193622700844,
+      "grad_norm": 0.04085984556832983,
+      "learning_rate": 7.919161174176663e-06,
+      "loss": 0.9993,
+      "step": 231
+    },
+    {
+      "epoch": 0.1357370095440085,
+      "grad_norm": 0.04500674877406008,
+      "learning_rate": 7.918462415776125e-06,
+      "loss": 0.9377,
+      "step": 232
+    },
+    {
+      "epoch": 0.13632208286100853,
+      "grad_norm": 0.039173528958006375,
+      "learning_rate": 7.917760684966955e-06,
+      "loss": 0.813,
+      "step": 233
+    },
+    {
+      "epoch": 0.13690715617800855,
+      "grad_norm": 0.04298295272921228,
+      "learning_rate": 7.91705598234197e-06,
+      "loss": 0.8952,
+      "step": 234
+    },
+    {
+      "epoch": 0.13749222949500858,
+      "grad_norm": 0.04028408438122686,
+      "learning_rate": 7.916348308496513e-06,
+      "loss": 0.9051,
+      "step": 235
+    },
+    {
+      "epoch": 0.13807730281200864,
+      "grad_norm": 0.06743695497866435,
+      "learning_rate": 7.915637664028423e-06,
+      "loss": 0.9475,
+      "step": 236
+    },
+    {
+      "epoch": 0.13866237612900867,
+      "grad_norm": 0.03949575625475006,
+      "learning_rate": 7.914924049538061e-06,
+      "loss": 0.9316,
+      "step": 237
+    },
+    {
+      "epoch": 0.1392474494460087,
+      "grad_norm": 0.04030623921903529,
+      "learning_rate": 7.914207465628284e-06,
+      "loss": 0.885,
+      "step": 238
+    },
+    {
+      "epoch": 0.13983252276300873,
+      "grad_norm": 0.047528726409039795,
+      "learning_rate": 7.91348791290447e-06,
+      "loss": 0.918,
+      "step": 239
+    },
+    {
+      "epoch": 0.14041759608000878,
+      "grad_norm": 0.04466991571391728,
+      "learning_rate": 7.912765391974496e-06,
+      "loss": 0.9305,
+      "step": 240
+    },
+    {
+      "epoch": 0.1410026693970088,
+      "grad_norm": 0.04186868219039162,
+      "learning_rate": 7.912039903448752e-06,
+      "loss": 0.9415,
+      "step": 241
+    },
+    {
+      "epoch": 0.14158774271400884,
+      "grad_norm": 0.05801571080351748,
+      "learning_rate": 7.91131144794013e-06,
+      "loss": 0.8787,
+      "step": 242
+    },
+    {
+      "epoch": 0.1421728160310089,
+      "grad_norm": 0.045088484806881386,
+      "learning_rate": 7.910580026064038e-06,
+      "loss": 1.0604,
+      "step": 243
+    },
+    {
+      "epoch": 0.14275788934800893,
+      "grad_norm": 0.06574863742707004,
+      "learning_rate": 7.909845638438377e-06,
+      "loss": 0.9216,
+      "step": 244
+    },
+    {
+      "epoch": 0.14334296266500896,
+      "grad_norm": 0.0372095564143721,
+      "learning_rate": 7.909108285683563e-06,
+      "loss": 0.9336,
+      "step": 245
+    },
+    {
+      "epoch": 0.14392803598200898,
+      "grad_norm": 0.04397627871472844,
+      "learning_rate": 7.908367968422515e-06,
+      "loss": 0.9261,
+      "step": 246
+    },
+    {
+      "epoch": 0.14451310929900904,
+      "grad_norm": 0.04276892267104892,
+      "learning_rate": 7.907624687280654e-06,
+      "loss": 0.8673,
+      "step": 247
+    },
+    {
+      "epoch": 0.14509818261600907,
+      "grad_norm": 0.045304865664725656,
+      "learning_rate": 7.906878442885907e-06,
+      "loss": 0.9475,
+      "step": 248
+    },
+    {
+      "epoch": 0.1456832559330091,
+      "grad_norm": 0.04370076931511423,
+      "learning_rate": 7.906129235868702e-06,
+      "loss": 0.8433,
+      "step": 249
+    },
+    {
+      "epoch": 0.14626832925000915,
+      "grad_norm": 0.0672588807453601,
+      "learning_rate": 7.905377066861973e-06,
+      "loss": 0.9124,
+      "step": 250
+    },
+    {
+      "epoch": 0.14685340256700918,
+      "grad_norm": 0.046912566764935076,
+      "learning_rate": 7.904621936501156e-06,
+      "loss": 0.9044,
+      "step": 251
+    },
+    {
+      "epoch": 0.1474384758840092,
+      "grad_norm": 0.07278415346178851,
+      "learning_rate": 7.903863845424185e-06,
+      "loss": 0.901,
+      "step": 252
+    },
+    {
+      "epoch": 0.14802354920100924,
+      "grad_norm": 0.04218918671820467,
+      "learning_rate": 7.9031027942715e-06,
+      "loss": 0.9019,
+      "step": 253
+    },
+    {
+      "epoch": 0.1486086225180093,
+      "grad_norm": 0.03858325311022567,
+      "learning_rate": 7.90233878368604e-06,
+      "loss": 0.8601,
+      "step": 254
+    },
+    {
+      "epoch": 0.14919369583500933,
+      "grad_norm": 0.04209886442727145,
+      "learning_rate": 7.90157181431324e-06,
+      "loss": 0.8681,
+      "step": 255
+    },
+    {
+      "epoch": 0.14977876915200936,
+      "grad_norm": 0.049400812285918,
+      "learning_rate": 7.90080188680104e-06,
+      "loss": 0.9494,
+      "step": 256
+    },
+    {
+      "epoch": 0.15036384246900938,
+      "grad_norm": 0.047941941474994906,
+      "learning_rate": 7.900029001799882e-06,
+      "loss": 0.8439,
+      "step": 257
+    },
+    {
+      "epoch": 0.15094891578600944,
+      "grad_norm": 0.042101153780900284,
+      "learning_rate": 7.899253159962694e-06,
+      "loss": 0.917,
+      "step": 258
+    },
+    {
+      "epoch": 0.15153398910300947,
+      "grad_norm": 0.040583990176968884,
+      "learning_rate": 7.898474361944915e-06,
+      "loss": 0.9328,
+      "step": 259
+    },
+    {
+      "epoch": 0.1521190624200095,
+      "grad_norm": 0.04000469028913075,
+      "learning_rate": 7.897692608404474e-06,
+      "loss": 0.9454,
+      "step": 260
+    },
+    {
+      "epoch": 0.15270413573700956,
+      "grad_norm": 0.04819787772789072,
+      "learning_rate": 7.8969079000018e-06,
+      "loss": 1.0061,
+      "step": 261
+    },
+    {
+      "epoch": 0.15328920905400958,
+      "grad_norm": 0.04670811295251141,
+      "learning_rate": 7.896120237399817e-06,
+      "loss": 0.8678,
+      "step": 262
+    },
+    {
+      "epoch": 0.1538742823710096,
+      "grad_norm": 0.03876277230266676,
+      "learning_rate": 7.895329621263945e-06,
+      "loss": 0.9465,
+      "step": 263
+    },
+    {
+      "epoch": 0.15445935568800964,
+      "grad_norm": 0.06917560168966953,
+      "learning_rate": 7.894536052262098e-06,
+      "loss": 0.9114,
+      "step": 264
+    },
+    {
+      "epoch": 0.1550444290050097,
+      "grad_norm": 0.052197549375990714,
+      "learning_rate": 7.893739531064688e-06,
+      "loss": 0.8966,
+      "step": 265
+    },
+    {
+      "epoch": 0.15562950232200973,
+      "grad_norm": 0.05089520469658166,
+      "learning_rate": 7.892940058344615e-06,
+      "loss": 0.8403,
+      "step": 266
+    },
+    {
+      "epoch": 0.15621457563900976,
+      "grad_norm": 0.04200303069403226,
+      "learning_rate": 7.89213763477728e-06,
+      "loss": 0.7954,
+      "step": 267
+    },
+    {
+      "epoch": 0.1567996489560098,
+      "grad_norm": 0.04045997821257577,
+      "learning_rate": 7.89133226104057e-06,
+      "loss": 0.9484,
+      "step": 268
+    },
+    {
+      "epoch": 0.15738472227300984,
+      "grad_norm": 0.04355833968928891,
+      "learning_rate": 7.890523937814872e-06,
+      "loss": 0.8871,
+      "step": 269
+    },
+    {
+      "epoch": 0.15796979559000987,
+      "grad_norm": 0.038980722774793516,
+      "learning_rate": 7.889712665783055e-06,
+      "loss": 0.8242,
+      "step": 270
+    },
+    {
+      "epoch": 0.1585548689070099,
+      "grad_norm": 0.0417431555190703,
+      "learning_rate": 7.888898445630486e-06,
+      "loss": 0.918,
+      "step": 271
+    },
+    {
+      "epoch": 0.15913994222400996,
+      "grad_norm": 0.04420422353440596,
+      "learning_rate": 7.888081278045022e-06,
+      "loss": 0.9345,
+      "step": 272
+    },
+    {
+      "epoch": 0.15972501554100998,
+      "grad_norm": 0.043453256463112454,
+      "learning_rate": 7.88726116371701e-06,
+      "loss": 0.8439,
+      "step": 273
+    },
+    {
+      "epoch": 0.16031008885801,
+      "grad_norm": 0.04018335492133053,
+      "learning_rate": 7.88643810333928e-06,
+      "loss": 0.9024,
+      "step": 274
+    },
+    {
+      "epoch": 0.16089516217501004,
+      "grad_norm": 0.03885288803364117,
+      "learning_rate": 7.885612097607161e-06,
+      "loss": 0.9005,
+      "step": 275
+    },
+    {
+      "epoch": 0.1614802354920101,
+      "grad_norm": 0.03940189643105726,
+      "learning_rate": 7.884783147218464e-06,
+      "loss": 0.8726,
+      "step": 276
+    },
+    {
+      "epoch": 0.16206530880901013,
+      "grad_norm": 0.04322545289358093,
+      "learning_rate": 7.88395125287349e-06,
+      "loss": 0.9309,
+      "step": 277
+    },
+    {
+      "epoch": 0.16265038212601016,
+      "grad_norm": 0.03991615308835092,
+      "learning_rate": 7.883116415275022e-06,
+      "loss": 0.9319,
+      "step": 278
+    },
+    {
+      "epoch": 0.1632354554430102,
+      "grad_norm": 0.04774591346437184,
+      "learning_rate": 7.882278635128339e-06,
+      "loss": 0.9976,
+      "step": 279
+    },
+    {
+      "epoch": 0.16382052876001024,
+      "grad_norm": 0.043726280435400645,
+      "learning_rate": 7.881437913141196e-06,
+      "loss": 0.9041,
+      "step": 280
+    },
+    {
+      "epoch": 0.16440560207701027,
+      "grad_norm": 0.05349577122745657,
+      "learning_rate": 7.880594250023842e-06,
+      "loss": 0.9109,
+      "step": 281
+    },
+    {
+      "epoch": 0.1649906753940103,
+      "grad_norm": 0.04664425873865413,
+      "learning_rate": 7.879747646489002e-06,
+      "loss": 0.8872,
+      "step": 282
+    },
+    {
+      "epoch": 0.16557574871101036,
+      "grad_norm": 0.04689991827127376,
+      "learning_rate": 7.878898103251891e-06,
+      "loss": 0.946,
+      "step": 283
+    },
+    {
+      "epoch": 0.16616082202801039,
+      "grad_norm": 0.04419788368438809,
+      "learning_rate": 7.87804562103021e-06,
+      "loss": 0.8699,
+      "step": 284
+    },
+    {
+      "epoch": 0.16674589534501041,
+      "grad_norm": 0.0498909584325992,
+      "learning_rate": 7.877190200544131e-06,
+      "loss": 0.8396,
+      "step": 285
+    },
+    {
+      "epoch": 0.16733096866201047,
+      "grad_norm": 0.04446094526551824,
+      "learning_rate": 7.876331842516323e-06,
+      "loss": 0.887,
+      "step": 286
+    },
+    {
+      "epoch": 0.1679160419790105,
+      "grad_norm": 0.06094680175561847,
+      "learning_rate": 7.875470547671926e-06,
+      "loss": 0.8834,
+      "step": 287
+    },
+    {
+      "epoch": 0.16850111529601053,
+      "grad_norm": 0.038876474999689326,
+      "learning_rate": 7.874606316738566e-06,
+      "loss": 0.8975,
+      "step": 288
+    },
+    {
+      "epoch": 0.16908618861301056,
+      "grad_norm": 0.04076135396799628,
+      "learning_rate": 7.873739150446349e-06,
+      "loss": 0.9094,
+      "step": 289
+    },
+    {
+      "epoch": 0.16967126193001061,
+      "grad_norm": 0.04242085203333459,
+      "learning_rate": 7.872869049527855e-06,
+      "loss": 0.9346,
+      "step": 290
+    },
+    {
+      "epoch": 0.17025633524701064,
+      "grad_norm": 0.04192270928126719,
+      "learning_rate": 7.871996014718154e-06,
+      "loss": 0.916,
+      "step": 291
+    },
+    {
+      "epoch": 0.17084140856401067,
+      "grad_norm": 0.06296131776401025,
+      "learning_rate": 7.871120046754787e-06,
+      "loss": 0.7869,
+      "step": 292
+    },
+    {
+      "epoch": 0.1714264818810107,
+      "grad_norm": 0.04208658542590707,
+      "learning_rate": 7.870241146377773e-06,
+      "loss": 0.863,
+      "step": 293
+    },
+    {
+      "epoch": 0.17201155519801076,
+      "grad_norm": 0.04221040890826715,
+      "learning_rate": 7.869359314329613e-06,
+      "loss": 0.8125,
+      "step": 294
+    },
+    {
+      "epoch": 0.17259662851501079,
+      "grad_norm": 0.044062682914531,
+      "learning_rate": 7.868474551355277e-06,
+      "loss": 0.8283,
+      "step": 295
+    },
+    {
+      "epoch": 0.17318170183201081,
+      "grad_norm": 0.053136044791769796,
+      "learning_rate": 7.867586858202221e-06,
+      "loss": 0.9321,
+      "step": 296
+    },
+    {
+      "epoch": 0.17376677514901087,
+      "grad_norm": 0.041998835388755755,
+      "learning_rate": 7.866696235620367e-06,
+      "loss": 0.9435,
+      "step": 297
+    },
+    {
+      "epoch": 0.1743518484660109,
+      "grad_norm": 0.04432061620173052,
+      "learning_rate": 7.865802684362119e-06,
+      "loss": 0.944,
+      "step": 298
+    },
+    {
+      "epoch": 0.17493692178301093,
+      "grad_norm": 0.03816132379303917,
+      "learning_rate": 7.864906205182347e-06,
+      "loss": 0.9222,
+      "step": 299
+    },
+    {
+      "epoch": 0.17552199510001096,
+      "grad_norm": 0.04061878988742196,
+      "learning_rate": 7.864006798838405e-06,
+      "loss": 0.9344,
+      "step": 300
+    },
+    {
+      "epoch": 0.17610706841701101,
+      "grad_norm": 0.038725999488975066,
+      "learning_rate": 7.863104466090113e-06,
+      "loss": 0.9477,
+      "step": 301
+    },
+    {
+      "epoch": 0.17669214173401104,
+      "grad_norm": 0.0675670307551766,
+      "learning_rate": 7.862199207699763e-06,
+      "loss": 0.8939,
+      "step": 302
+    },
+    {
+      "epoch": 0.17727721505101107,
+      "grad_norm": 0.04866290151842816,
+      "learning_rate": 7.861291024432122e-06,
+      "loss": 0.944,
+      "step": 303
+    },
+    {
+      "epoch": 0.17786228836801113,
+      "grad_norm": 0.04231401792052211,
+      "learning_rate": 7.860379917054426e-06,
+      "loss": 0.9108,
+      "step": 304
+    },
+    {
+      "epoch": 0.17844736168501116,
+      "grad_norm": 0.21645206187990054,
+      "learning_rate": 7.859465886336381e-06,
+      "loss": 0.9328,
+      "step": 305
+    },
+    {
+      "epoch": 0.1790324350020112,
+      "grad_norm": 0.04212212891416765,
+      "learning_rate": 7.858548933050162e-06,
+      "loss": 0.9755,
+      "step": 306
+    },
+    {
+      "epoch": 0.17961750831901122,
+      "grad_norm": 0.047331820432207364,
+      "learning_rate": 7.857629057970417e-06,
+      "loss": 0.8702,
+      "step": 307
+    },
+    {
+      "epoch": 0.18020258163601127,
+      "grad_norm": 0.040260553510288316,
+      "learning_rate": 7.856706261874258e-06,
+      "loss": 0.8934,
+      "step": 308
+    },
+    {
+      "epoch": 0.1807876549530113,
+      "grad_norm": 0.04326897093604986,
+      "learning_rate": 7.855780545541264e-06,
+      "loss": 0.877,
+      "step": 309
+    },
+    {
+      "epoch": 0.18137272827001133,
+      "grad_norm": 0.03936456606263684,
+      "learning_rate": 7.854851909753487e-06,
+      "loss": 0.9206,
+      "step": 310
+    },
+    {
+      "epoch": 0.18195780158701136,
+      "grad_norm": 0.040529920237504666,
+      "learning_rate": 7.853920355295438e-06,
+      "loss": 0.8469,
+      "step": 311
+    },
+    {
+      "epoch": 0.18254287490401142,
+      "grad_norm": 0.07984199172508148,
+      "learning_rate": 7.852985882954102e-06,
+      "loss": 0.856,
+      "step": 312
+    },
+    {
+      "epoch": 0.18312794822101144,
+      "grad_norm": 0.04341308255910565,
+      "learning_rate": 7.85204849351892e-06,
+      "loss": 0.8975,
+      "step": 313
+    },
+    {
+      "epoch": 0.18371302153801147,
+      "grad_norm": 0.05163482815007264,
+      "learning_rate": 7.851108187781802e-06,
+      "loss": 0.8516,
+      "step": 314
+    },
+    {
+      "epoch": 0.18429809485501153,
+      "grad_norm": 0.04363599571939765,
+      "learning_rate": 7.850164966537124e-06,
+      "loss": 0.9088,
+      "step": 315
+    },
+    {
+      "epoch": 0.18488316817201156,
+      "grad_norm": 0.043024652012164384,
+      "learning_rate": 7.84921883058172e-06,
+      "loss": 0.8291,
+      "step": 316
+    },
+    {
+      "epoch": 0.1854682414890116,
+      "grad_norm": 0.041659608271311335,
+      "learning_rate": 7.848269780714892e-06,
+      "loss": 0.9719,
+      "step": 317
+    },
+    {
+      "epoch": 0.18605331480601162,
+      "grad_norm": 0.04557805725835434,
+      "learning_rate": 7.847317817738394e-06,
+      "loss": 0.9638,
+      "step": 318
+    },
+    {
+      "epoch": 0.18663838812301167,
+      "grad_norm": 0.04388413396186285,
+      "learning_rate": 7.846362942456455e-06,
+      "loss": 0.93,
+      "step": 319
+    },
+    {
+      "epoch": 0.1872234614400117,
+      "grad_norm": 0.04052950822615268,
+      "learning_rate": 7.845405155675752e-06,
+      "loss": 0.8951,
+      "step": 320
+    },
+    {
+      "epoch": 0.18780853475701173,
+      "grad_norm": 0.03852369264523642,
+      "learning_rate": 7.844444458205428e-06,
+      "loss": 0.8521,
+      "step": 321
+    },
+    {
+      "epoch": 0.1883936080740118,
+      "grad_norm": 0.045799254500923765,
+      "learning_rate": 7.843480850857083e-06,
+      "loss": 0.8966,
+      "step": 322
+    },
+    {
+      "epoch": 0.18897868139101182,
+      "grad_norm": 0.04373024374645557,
+      "learning_rate": 7.842514334444776e-06,
+      "loss": 0.973,
+      "step": 323
+    },
+    {
+      "epoch": 0.18956375470801184,
+      "grad_norm": 0.037372310076302304,
+      "learning_rate": 7.841544909785022e-06,
+      "loss": 1.0232,
+      "step": 324
+    },
+    {
+      "epoch": 0.19014882802501187,
+      "grad_norm": 0.044911079932608254,
+      "learning_rate": 7.840572577696798e-06,
+      "loss": 0.8351,
+      "step": 325
+    },
+    {
+      "epoch": 0.19073390134201193,
+      "grad_norm": 0.04820487217400144,
+      "learning_rate": 7.839597339001529e-06,
+      "loss": 0.9381,
+      "step": 326
+    },
+    {
+      "epoch": 0.19131897465901196,
+      "grad_norm": 0.04460622903204633,
+      "learning_rate": 7.8386191945231e-06,
+      "loss": 0.9047,
+      "step": 327
+    },
+    {
+      "epoch": 0.191904047976012,
+      "grad_norm": 0.04344227987010105,
+      "learning_rate": 7.837638145087855e-06,
+      "loss": 0.8882,
+      "step": 328
+    },
+    {
+      "epoch": 0.19248912129301204,
+      "grad_norm": 0.041162516007716705,
+      "learning_rate": 7.836654191524583e-06,
+      "loss": 0.888,
+      "step": 329
+    },
+    {
+      "epoch": 0.19307419461001207,
+      "grad_norm": 0.050217278727892056,
+      "learning_rate": 7.835667334664533e-06,
+      "loss": 0.9425,
+      "step": 330
+    },
+    {
+      "epoch": 0.1936592679270121,
+      "grad_norm": 0.045239661384039016,
+      "learning_rate": 7.834677575341407e-06,
+      "loss": 0.845,
+      "step": 331
+    },
+    {
+      "epoch": 0.19424434124401213,
+      "grad_norm": 0.04069762643444013,
+      "learning_rate": 7.833684914391354e-06,
+      "loss": 0.9045,
+      "step": 332
+    },
+    {
+      "epoch": 0.1948294145610122,
+      "grad_norm": 0.03659391253836006,
+      "learning_rate": 7.832689352652978e-06,
+      "loss": 0.8415,
+      "step": 333
+    },
+    {
+      "epoch": 0.19541448787801222,
+      "grad_norm": 0.0478253523475305,
+      "learning_rate": 7.831690890967332e-06,
+      "loss": 0.9023,
+      "step": 334
+    },
+    {
+      "epoch": 0.19599956119501225,
+      "grad_norm": 0.03931532297283958,
+      "learning_rate": 7.830689530177923e-06,
+      "loss": 0.8757,
+      "step": 335
+    },
+    {
+      "epoch": 0.19658463451201227,
+      "grad_norm": 0.04480666786944768,
+      "learning_rate": 7.8296852711307e-06,
+      "loss": 0.8393,
+      "step": 336
+    },
+    {
+      "epoch": 0.19716970782901233,
+      "grad_norm": 0.0734058976406723,
+      "learning_rate": 7.828678114674066e-06,
+      "loss": 0.9038,
+      "step": 337
+    },
+    {
+      "epoch": 0.19775478114601236,
+      "grad_norm": 0.03967258990394233,
+      "learning_rate": 7.827668061658871e-06,
+      "loss": 0.8009,
+      "step": 338
+    },
+    {
+      "epoch": 0.1983398544630124,
+      "grad_norm": 0.0418553799297778,
+      "learning_rate": 7.82665511293841e-06,
+      "loss": 0.8865,
+      "step": 339
+    },
+    {
+      "epoch": 0.19892492778001244,
+      "grad_norm": 0.0384561013270465,
+      "learning_rate": 7.825639269368426e-06,
+      "loss": 0.872,
+      "step": 340
+    },
+    {
+      "epoch": 0.19951000109701247,
+      "grad_norm": 0.04182210062250734,
+      "learning_rate": 7.824620531807106e-06,
+      "loss": 0.8974,
+      "step": 341
+    },
+    {
+      "epoch": 0.2000950744140125,
+      "grad_norm": 0.0402445680829306,
+      "learning_rate": 7.823598901115085e-06,
+      "loss": 0.8017,
+      "step": 342
+    },
+    {
+      "epoch": 0.20068014773101253,
+      "grad_norm": 0.03976795416941979,
+      "learning_rate": 7.822574378155436e-06,
+      "loss": 0.9298,
+      "step": 343
+    },
+    {
+      "epoch": 0.2012652210480126,
+      "grad_norm": 0.043031163568613286,
+      "learning_rate": 7.821546963793683e-06,
+      "loss": 0.9508,
+      "step": 344
+    },
+    {
+      "epoch": 0.20185029436501262,
+      "grad_norm": 0.0485982687560341,
+      "learning_rate": 7.82051665889779e-06,
+      "loss": 0.8536,
+      "step": 345
+    },
+    {
+      "epoch": 0.20243536768201265,
+      "grad_norm": 0.04149899672912665,
+      "learning_rate": 7.819483464338156e-06,
+      "loss": 0.8767,
+      "step": 346
+    },
+    {
+      "epoch": 0.2030204409990127,
+      "grad_norm": 0.0971131140419449,
+      "learning_rate": 7.818447380987634e-06,
+      "loss": 0.9271,
+      "step": 347
+    },
+    {
+      "epoch": 0.20360551431601273,
+      "grad_norm": 0.04183099462603424,
+      "learning_rate": 7.817408409721506e-06,
+      "loss": 0.8362,
+      "step": 348
+    },
+    {
+      "epoch": 0.20419058763301276,
+      "grad_norm": 0.03719681766847752,
+      "learning_rate": 7.8163665514175e-06,
+      "loss": 0.8544,
+      "step": 349
+    },
+    {
+      "epoch": 0.2047756609500128,
+      "grad_norm": 0.08061763199476867,
+      "learning_rate": 7.815321806955782e-06,
+      "loss": 0.8335,
+      "step": 350
+    },
+    {
+      "epoch": 0.20536073426701285,
+      "grad_norm": 0.053441055551360056,
+      "learning_rate": 7.814274177218955e-06,
+      "loss": 0.8602,
+      "step": 351
+    },
+    {
+      "epoch": 0.20594580758401287,
+      "grad_norm": 0.1775803458323184,
+      "learning_rate": 7.81322366309206e-06,
+      "loss": 0.8998,
+      "step": 352
+    },
+    {
+      "epoch": 0.2065308809010129,
+      "grad_norm": 0.0637002971995377,
+      "learning_rate": 7.812170265462573e-06,
+      "loss": 0.9737,
+      "step": 353
+    },
+    {
+      "epoch": 0.20711595421801293,
+      "grad_norm": 0.04274639590829472,
+      "learning_rate": 7.81111398522041e-06,
+      "loss": 1.009,
+      "step": 354
+    },
+    {
+      "epoch": 0.207701027535013,
+      "grad_norm": 0.041282961278004064,
+      "learning_rate": 7.81005482325792e-06,
+      "loss": 0.9035,
+      "step": 355
+    },
+    {
+      "epoch": 0.20828610085201302,
+      "grad_norm": 0.04195399372218902,
+      "learning_rate": 7.808992780469889e-06,
+      "loss": 0.9128,
+      "step": 356
+    },
+    {
+      "epoch": 0.20887117416901305,
+      "grad_norm": 0.03698717701423449,
+      "learning_rate": 7.807927857753527e-06,
+      "loss": 0.8562,
+      "step": 357
+    },
+    {
+      "epoch": 0.2094562474860131,
+      "grad_norm": 0.1081591722204418,
+      "learning_rate": 7.80686005600849e-06,
+      "loss": 0.8931,
+      "step": 358
+    },
+    {
+      "epoch": 0.21004132080301313,
+      "grad_norm": 0.04152721891763337,
+      "learning_rate": 7.80578937613686e-06,
+      "loss": 0.8633,
+      "step": 359
+    },
+    {
+      "epoch": 0.21062639412001316,
+      "grad_norm": 0.04200660652374662,
+      "learning_rate": 7.804715819043148e-06,
+      "loss": 0.8773,
+      "step": 360
+    },
+    {
+      "epoch": 0.2112114674370132,
+      "grad_norm": 0.04405111681557889,
+      "learning_rate": 7.803639385634302e-06,
+      "loss": 0.8587,
+      "step": 361
+    },
+    {
+      "epoch": 0.21179654075401325,
+      "grad_norm": 0.04571477197647962,
+      "learning_rate": 7.802560076819694e-06,
+      "loss": 0.8334,
+      "step": 362
+    },
+    {
+      "epoch": 0.21238161407101327,
+      "grad_norm": 0.041607118224879065,
+      "learning_rate": 7.80147789351113e-06,
+      "loss": 0.8739,
+      "step": 363
+    },
+    {
+      "epoch": 0.2129666873880133,
+      "grad_norm": 0.06194034993642153,
+      "learning_rate": 7.800392836622838e-06,
+      "loss": 0.8956,
+      "step": 364
+    },
+    {
+      "epoch": 0.21355176070501336,
+      "grad_norm": 0.03798806008002444,
+      "learning_rate": 7.79930490707148e-06,
+      "loss": 0.8966,
+      "step": 365
+    },
+    {
+      "epoch": 0.2141368340220134,
+      "grad_norm": 0.04739784630899101,
+      "learning_rate": 7.798214105776146e-06,
+      "loss": 0.9552,
+      "step": 366
+    },
+    {
+      "epoch": 0.21472190733901342,
+      "grad_norm": 0.04497114482691456,
+      "learning_rate": 7.797120433658343e-06,
+      "loss": 0.8666,
+      "step": 367
+    },
+    {
+      "epoch": 0.21530698065601345,
+      "grad_norm": 0.04176901867071411,
+      "learning_rate": 7.796023891642011e-06,
+      "loss": 0.9051,
+      "step": 368
+    },
+    {
+      "epoch": 0.2158920539730135,
+      "grad_norm": 0.056698801623745465,
+      "learning_rate": 7.794924480653513e-06,
+      "loss": 0.8745,
+      "step": 369
+    },
+    {
+      "epoch": 0.21647712729001353,
+      "grad_norm": 0.04267067239376988,
+      "learning_rate": 7.793822201621633e-06,
+      "loss": 0.9129,
+      "step": 370
+    },
+    {
+      "epoch": 0.21706220060701356,
+      "grad_norm": 0.03999203881276761,
+      "learning_rate": 7.79271705547758e-06,
+      "loss": 0.8814,
+      "step": 371
+    },
+    {
+      "epoch": 0.2176472739240136,
+      "grad_norm": 0.04206496870855173,
+      "learning_rate": 7.79160904315499e-06,
+      "loss": 0.8936,
+      "step": 372
+    },
+    {
+      "epoch": 0.21823234724101365,
+      "grad_norm": 0.040567992793796616,
+      "learning_rate": 7.79049816558991e-06,
+      "loss": 0.8961,
+      "step": 373
+    },
+    {
+      "epoch": 0.21881742055801368,
+      "grad_norm": 0.04165915715538525,
+      "learning_rate": 7.789384423720815e-06,
+      "loss": 0.901,
+      "step": 374
+    },
+    {
+      "epoch": 0.2194024938750137,
+      "grad_norm": 0.04311161567240108,
+      "learning_rate": 7.788267818488597e-06,
+      "loss": 0.8571,
+      "step": 375
+    },
+    {
+      "epoch": 0.21998756719201376,
+      "grad_norm": 0.04090984120457054,
+      "learning_rate": 7.78714835083657e-06,
+      "loss": 0.879,
+      "step": 376
+    },
+    {
+      "epoch": 0.2205726405090138,
+      "grad_norm": 0.03723653818234615,
+      "learning_rate": 7.786026021710462e-06,
+      "loss": 0.8687,
+      "step": 377
+    },
+    {
+      "epoch": 0.22115771382601382,
+      "grad_norm": 0.040732056413017595,
+      "learning_rate": 7.78490083205842e-06,
+      "loss": 0.9033,
+      "step": 378
+    },
+    {
+      "epoch": 0.22174278714301385,
+      "grad_norm": 0.03755340315603773,
+      "learning_rate": 7.783772782831008e-06,
+      "loss": 0.8919,
+      "step": 379
+    },
+    {
+      "epoch": 0.2223278604600139,
+      "grad_norm": 0.04513035465018611,
+      "learning_rate": 7.782641874981207e-06,
+      "loss": 0.8766,
+      "step": 380
+    },
+    {
+      "epoch": 0.22291293377701393,
+      "grad_norm": 0.042927929340526826,
+      "learning_rate": 7.78150810946441e-06,
+      "loss": 0.8692,
+      "step": 381
+    },
+    {
+      "epoch": 0.22349800709401396,
+      "grad_norm": 0.03548281821425231,
+      "learning_rate": 7.780371487238428e-06,
+      "loss": 0.7295,
+      "step": 382
+    },
+    {
+      "epoch": 0.22408308041101402,
+      "grad_norm": 0.03978070402906236,
+      "learning_rate": 7.779232009263484e-06,
+      "loss": 0.8555,
+      "step": 383
+    },
+    {
+      "epoch": 0.22466815372801405,
+      "grad_norm": 0.036709565386030436,
+      "learning_rate": 7.778089676502209e-06,
+      "loss": 0.7492,
+      "step": 384
+    },
+    {
+      "epoch": 0.22525322704501408,
+      "grad_norm": 0.04547788495521431,
+      "learning_rate": 7.776944489919649e-06,
+      "loss": 0.8334,
+      "step": 385
+    },
+    {
+      "epoch": 0.2258383003620141,
+      "grad_norm": 0.04220442842369723,
+      "learning_rate": 7.775796450483267e-06,
+      "loss": 0.8244,
+      "step": 386
+    },
+    {
+      "epoch": 0.22642337367901416,
+      "grad_norm": 0.04778060193840243,
+      "learning_rate": 7.774645559162927e-06,
+      "loss": 0.8511,
+      "step": 387
+    },
+    {
+      "epoch": 0.2270084469960142,
+      "grad_norm": 0.05014682109980806,
+      "learning_rate": 7.773491816930904e-06,
+      "loss": 0.8334,
+      "step": 388
+    },
+    {
+      "epoch": 0.22759352031301422,
+      "grad_norm": 0.04001986651909544,
+      "learning_rate": 7.772335224761886e-06,
+      "loss": 0.8224,
+      "step": 389
+    },
+    {
+      "epoch": 0.22817859363001425,
+      "grad_norm": 0.040094874463681825,
+      "learning_rate": 7.771175783632966e-06,
+      "loss": 0.9069,
+      "step": 390
+    },
+    {
+      "epoch": 0.2287636669470143,
+      "grad_norm": 0.03678306586668835,
+      "learning_rate": 7.770013494523641e-06,
+      "loss": 0.8758,
+      "step": 391
+    },
+    {
+      "epoch": 0.22934874026401433,
+      "grad_norm": 0.04444193067206238,
+      "learning_rate": 7.768848358415819e-06,
+      "loss": 0.946,
+      "step": 392
+    },
+    {
+      "epoch": 0.22993381358101436,
+      "grad_norm": 0.042386218395158284,
+      "learning_rate": 7.767680376293811e-06,
+      "loss": 0.8395,
+      "step": 393
+    },
+    {
+      "epoch": 0.23051888689801442,
+      "grad_norm": 0.051874603825963005,
+      "learning_rate": 7.766509549144332e-06,
+      "loss": 0.8867,
+      "step": 394
+    },
+    {
+      "epoch": 0.23110396021501445,
+      "grad_norm": 0.04115935591406729,
+      "learning_rate": 7.765335877956498e-06,
+      "loss": 0.8509,
+      "step": 395
+    },
+    {
+      "epoch": 0.23168903353201448,
+      "grad_norm": 0.045377388296697053,
+      "learning_rate": 7.764159363721833e-06,
+      "loss": 0.8783,
+      "step": 396
+    },
+    {
+      "epoch": 0.2322741068490145,
+      "grad_norm": 0.03845331275197764,
+      "learning_rate": 7.762980007434261e-06,
+      "loss": 0.8721,
+      "step": 397
+    },
+    {
+      "epoch": 0.23285918016601456,
+      "grad_norm": 0.06130607399623932,
+      "learning_rate": 7.761797810090103e-06,
+      "loss": 0.896,
+      "step": 398
+    },
+    {
+      "epoch": 0.2334442534830146,
+      "grad_norm": 0.0653248890033106,
+      "learning_rate": 7.760612772688086e-06,
+      "loss": 0.9239,
+      "step": 399
+    },
+    {
+      "epoch": 0.23402932680001462,
+      "grad_norm": 0.04386903271065406,
+      "learning_rate": 7.759424896229329e-06,
+      "loss": 0.9055,
+      "step": 400
+    },
+    {
+      "epoch": 0.23461440011701468,
+      "grad_norm": 0.05112057938888221,
+      "learning_rate": 7.758234181717359e-06,
+      "loss": 0.8179,
+      "step": 401
+    },
+    {
+      "epoch": 0.2351994734340147,
+      "grad_norm": 0.03919834965990091,
+      "learning_rate": 7.757040630158094e-06,
+      "loss": 0.9131,
+      "step": 402
+    },
+    {
+      "epoch": 0.23578454675101473,
+      "grad_norm": 0.04080472273046829,
+      "learning_rate": 7.75584424255985e-06,
+      "loss": 0.8772,
+      "step": 403
+    },
+    {
+      "epoch": 0.23636962006801476,
+      "grad_norm": 0.036834620421617906,
+      "learning_rate": 7.754645019933338e-06,
+      "loss": 0.8155,
+      "step": 404
+    },
+    {
+      "epoch": 0.23695469338501482,
+      "grad_norm": 0.03654317750178369,
+      "learning_rate": 7.753442963291668e-06,
+      "loss": 0.8346,
+      "step": 405
+    },
+    {
+      "epoch": 0.23753976670201485,
+      "grad_norm": 0.04519798929105044,
+      "learning_rate": 7.752238073650339e-06,
+      "loss": 0.912,
+      "step": 406
+    },
+    {
+      "epoch": 0.23812484001901488,
+      "grad_norm": 0.03826695253269902,
+      "learning_rate": 7.751030352027246e-06,
+      "loss": 0.8772,
+      "step": 407
+    },
+    {
+      "epoch": 0.2387099133360149,
+      "grad_norm": 0.04486993387188878,
+      "learning_rate": 7.749819799442676e-06,
+      "loss": 0.8826,
+      "step": 408
+    },
+    {
+      "epoch": 0.23929498665301496,
+      "grad_norm": 0.0776681654995442,
+      "learning_rate": 7.74860641691931e-06,
+      "loss": 0.8987,
+      "step": 409
+    },
+    {
+      "epoch": 0.239880059970015,
+      "grad_norm": 0.05169098865704706,
+      "learning_rate": 7.747390205482216e-06,
+      "loss": 0.7904,
+      "step": 410
+    },
+    {
+      "epoch": 0.24046513328701502,
+      "grad_norm": 0.042053672534972886,
+      "learning_rate": 7.746171166158855e-06,
+      "loss": 0.9188,
+      "step": 411
+    },
+    {
+      "epoch": 0.24105020660401508,
+      "grad_norm": 0.044614916290635534,
+      "learning_rate": 7.744949299979071e-06,
+      "loss": 0.9118,
+      "step": 412
+    },
+    {
+      "epoch": 0.2416352799210151,
+      "grad_norm": 0.04594381480411999,
+      "learning_rate": 7.743724607975105e-06,
+      "loss": 0.8547,
+      "step": 413
+    },
+    {
+      "epoch": 0.24222035323801513,
+      "grad_norm": 0.037664202042716706,
+      "learning_rate": 7.742497091181578e-06,
+      "loss": 0.8446,
+      "step": 414
+    },
+    {
+      "epoch": 0.24280542655501516,
+      "grad_norm": 0.04794778502796113,
+      "learning_rate": 7.741266750635502e-06,
+      "loss": 0.897,
+      "step": 415
+    },
+    {
+      "epoch": 0.24339049987201522,
+      "grad_norm": 0.04188595026753968,
+      "learning_rate": 7.740033587376275e-06,
+      "loss": 0.9061,
+      "step": 416
+    },
+    {
+      "epoch": 0.24397557318901525,
+      "grad_norm": 0.04407359629305258,
+      "learning_rate": 7.738797602445671e-06,
+      "loss": 0.9146,
+      "step": 417
+    },
+    {
+      "epoch": 0.24456064650601528,
+      "grad_norm": 0.04077311126531583,
+      "learning_rate": 7.73755879688786e-06,
+      "loss": 0.8515,
+      "step": 418
+    },
+    {
+      "epoch": 0.24514571982301533,
+      "grad_norm": 0.055784116703384304,
+      "learning_rate": 7.736317171749385e-06,
+      "loss": 0.851,
+      "step": 419
+    },
+    {
+      "epoch": 0.24573079314001536,
+      "grad_norm": 0.049743142106565615,
+      "learning_rate": 7.735072728079179e-06,
+      "loss": 0.8718,
+      "step": 420
+    },
+    {
+      "epoch": 0.2463158664570154,
+      "grad_norm": 0.04470234941233142,
+      "learning_rate": 7.73382546692855e-06,
+      "loss": 0.9624,
+      "step": 421
+    },
+    {
+      "epoch": 0.24690093977401542,
+      "grad_norm": 0.040010409109375616,
+      "learning_rate": 7.732575389351187e-06,
+      "loss": 0.8925,
+      "step": 422
+    },
+    {
+      "epoch": 0.24748601309101548,
+      "grad_norm": 0.04513853855792064,
+      "learning_rate": 7.731322496403161e-06,
+      "loss": 0.8163,
+      "step": 423
+    },
+    {
+      "epoch": 0.2480710864080155,
+      "grad_norm": 0.04305001532204258,
+      "learning_rate": 7.730066789142922e-06,
+      "loss": 0.818,
+      "step": 424
+    },
+    {
+      "epoch": 0.24865615972501554,
+      "grad_norm": 0.0381328984157233,
+      "learning_rate": 7.728808268631291e-06,
+      "loss": 0.8655,
+      "step": 425
+    },
+    {
+      "epoch": 0.24924123304201556,
+      "grad_norm": 0.04141777979618345,
+      "learning_rate": 7.727546935931473e-06,
+      "loss": 0.8447,
+      "step": 426
+    },
+    {
+      "epoch": 0.24982630635901562,
+      "grad_norm": 0.0441532278076972,
+      "learning_rate": 7.726282792109049e-06,
+      "loss": 0.7839,
+      "step": 427
+    },
+    {
+      "epoch": 0.2504113796760157,
+      "grad_norm": 0.04369415131884431,
+      "learning_rate": 7.725015838231966e-06,
+      "loss": 0.8375,
+      "step": 428
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 3418,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 428,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1775486329946112.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

025/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af7282c8ed9263b59e5fec9eb2eb6dc8fdaa6726fe7a5737f67abf37af0cc28
+size 8440

025/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)