Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 050/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+150/tokenizer.json filter=lfs diff=lfs merge=lfs -text

150/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/raid/HUB_LLM/080225_vi_test_llama33_70b_instruct/checkpoint-2568/dpo32_epoch2/",
+  "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
+}

150/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.46.3"
+}

150/latest

@@ -0,0 +1 @@
+global_step297

150/model-00001-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bd8b50a77d5e52b5eddd2c1319a97c6d9633af77f2b1a1a43695c56350b0aa
+size 4584408808

150/model-00002-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af30af56129342a9b7fc8d772c7bf35a761f8b15653de600eec13f5ae35bdc0a
+size 4664167376

150/model-00003-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77d737622fbe68a664afcf1f6d42252e056fb268030571805fab49fc13367ffe
+size 4999711704

150/model-00004-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f5ef9fdf384c7557ce71739adb342da3b8c7b25d2f5666982766564638874bc
+size 4966157032

150/model-00005-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f8066e225268480e13605abe82c758fa4dcb34602dd96c2db2922b86607c85
+size 4664134408

150/model-00006-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f441c060cc96c61cfa7101db178f22574eb89b410b91630c7a0c614fbe4e9ff4
+size 4664167408

150/model-00007-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05346df513ec35072b152893adb50114678a2d5fa5e69ed8b3e4124c8a734ac2
+size 4664167408

150/model-00008-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef06b476f47a7f819519fbaf10f886be24b94201075747c1166aee538b3d0240
+size 4999711728

150/model-00009-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5837cc0befc2921e99ec4df43515e913ada2f5f6d4a5e64b4a3aa5442fb642
+size 4966157056

150/model-00010-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d276379e41cf966b74448612ed5cf7b353e0a26c1c01aad2f51810ea3153376
+size 4664134408

150/model-00011-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a5987e71d5ea99df8b1138394627b61a5a1d072ef1be4e7f9d5a86fe638d98
+size 4664167408

150/model-00012-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576c80a134b2536e880eb8c57c85182ebd431ee7f49c6d4f6e304df217dacf07
+size 4664167408

150/model-00013-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503cebc06bd7f947e94245505e4df1738753213d17f0b1813815787df2c26214
+size 4999711728

150/model-00014-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635c7698d4336d548bc33a73fe533ac80c037c3f7c726a93d7b46281feaa8e96
+size 4966157056

150/model-00015-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c74d8c55ec49a8f8e0ec4e33fe5c3b6717103bef13b8a60931929df9ae0a31a
+size 4664134408

150/model-00016-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34aeebdf5b8d3164d57925ef3d8c51c4ed0d6219b1f131cbb177ec9d2a2d4732
+size 4664167408

150/model-00017-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300be168b489f3b8e8efa17894a1b871ee4780ca333909319d01be61489a66fa
+size 4664167408

150/model-00018-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e976c229c4fa6f4a521da06c4660b914573d33d3299c29a96444a4f36b53392d
+size 4999711728

150/model-00019-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e27e16da30b347431570caae601492e53ea1b1a936e3dc2b381904c49a1b2dd
+size 4966157056

150/model-00020-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef4b96afb5c5eeb96d078cd6a6d18c538a70353003817fb31d8e1f4f1c22cb4
+size 4664134408

150/model-00021-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ca30ee76cf01188e1abfddd85771686fca029f63d80d30c7d5f6f72714b2a9
+size 4664167408

150/model-00022-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c33b6e368f17c99e2b75f7c0c14e6d29bb756a883294f9ad0a7d5965f461e5c
+size 4664167408

150/model-00023-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d80c68884f091806e181cd9b8d3076f7f0e20c31cb11594745a890a27c791d
+size 4999711728

150/model-00024-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43aed444d8ff89b5dc10b3d4e6cad8e9f047ef5404c44c2ab7fe20e8006976be
+size 4966157056

150/model-00025-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b2c71c79b766f177f76e3bc39fb15c4becb1cb8c59c13fe1d5984e8658b20e
+size 4664134408

150/model-00026-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f299314645cf2b31410e87fb4c815a2bf2c2cd121ed83417e3f9a991efed1a
+size 4664167408

150/model-00027-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4171efa4c35a15f8ab9f3a890bc1e42f703bc56962438e06f09d430422d414d
+size 4664167408

150/model-00028-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8b315ffad891cc41ae8b1907f7c5c04999a20aa67655b2a38e665d97f93549
+size 4999711728

150/model-00029-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee8f5428429b2a5a4f02e74414f9e12f62709c79eaa4e3d7678146cec7316fdc
+size 4966173536

150/model-00030-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c4494a5090f659874116494933fae691d2f8a806a6cfc666c29c2b06034d3b
+size 2101346432

150/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"
+  }
+}

150/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85
+size 15984

150/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73
+size 15984

150/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b
+size 15984

150/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc
+size 15984

150/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972
+size 15984

150/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60a1b40608e34bc801c8231f97b81c53b5290dfaed1b9cd0ccbeca29574a991
+size 15984

150/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad6a142a403eb9aafc4a3a9a856bca648fe31fd22d796867baca31fb13656aa
+size 15984

150/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bc23a138cc800b22881742c0f3f9a71731a9a7111c6058a0077e6274d21773
+size 15984

150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee6bb45db64a238048801013c8cfa9bbe1bc3c20b31f2d4cc5db65568b0cb46
+size 1064

150/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|eot_id|>",
+    "<|eom_id|>"
+  ],
+  "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
+  }
+}

150/tokenizer.json

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

150/tokenizer_config.json

@@ -0,0 +1,2070 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|eot_id|>",
+    "<|eom_id|>"
+  ],
+  "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|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

150/trainer_state.json

@@ -0,0 +1,2112 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4963733837906024,
+  "eval_steps": 500,
+  "global_step": 297,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005045726900031536,
+      "grad_norm": 0.16816571847556824,
+      "learning_rate": 2.9999839160139495e-06,
+      "loss": 0.7782,
+      "step": 1
+    },
+    {
+      "epoch": 0.010091453800063072,
+      "grad_norm": 0.1469143977253523,
+      "learning_rate": 2.9999356645057024e-06,
+      "loss": 0.6817,
+      "step": 2
+    },
+    {
+      "epoch": 0.015137180700094607,
+      "grad_norm": 0.07996774677933757,
+      "learning_rate": 2.9998552468249567e-06,
+      "loss": 0.6735,
+      "step": 3
+    },
+    {
+      "epoch": 0.020182907600126143,
+      "grad_norm": 0.0800127664777818,
+      "learning_rate": 2.999742665221167e-06,
+      "loss": 0.6569,
+      "step": 4
+    },
+    {
+      "epoch": 0.02522863450015768,
+      "grad_norm": 0.08070188267575489,
+      "learning_rate": 2.999597922843484e-06,
+      "loss": 0.6283,
+      "step": 5
+    },
+    {
+      "epoch": 0.030274361400189215,
+      "grad_norm": 0.06839180655145351,
+      "learning_rate": 2.999421023740663e-06,
+      "loss": 0.6446,
+      "step": 6
+    },
+    {
+      "epoch": 0.03532008830022075,
+      "grad_norm": 0.05534188923028301,
+      "learning_rate": 2.9992119728609516e-06,
+      "loss": 0.6371,
+      "step": 7
+    },
+    {
+      "epoch": 0.040365815200252286,
+      "grad_norm": 0.07094943987370793,
+      "learning_rate": 2.9989707760519526e-06,
+      "loss": 0.6111,
+      "step": 8
+    },
+    {
+      "epoch": 0.04541154210028382,
+      "grad_norm": 0.06436005389698786,
+      "learning_rate": 2.9986974400604593e-06,
+      "loss": 0.588,
+      "step": 9
+    },
+    {
+      "epoch": 0.05045726900031536,
+      "grad_norm": 0.05699223365274786,
+      "learning_rate": 2.9983919725322667e-06,
+      "loss": 0.6101,
+      "step": 10
+    },
+    {
+      "epoch": 0.055502995900346894,
+      "grad_norm": 0.058843386030182285,
+      "learning_rate": 2.9980543820119585e-06,
+      "loss": 0.6047,
+      "step": 11
+    },
+    {
+      "epoch": 0.06054872280037843,
+      "grad_norm": 0.047228554008764044,
+      "learning_rate": 2.997684677942667e-06,
+      "loss": 0.5937,
+      "step": 12
+    },
+    {
+      "epoch": 0.06559444970040997,
+      "grad_norm": 0.04830399085917525,
+      "learning_rate": 2.9972828706658102e-06,
+      "loss": 0.6448,
+      "step": 13
+    },
+    {
+      "epoch": 0.0706401766004415,
+      "grad_norm": 0.04469640349332499,
+      "learning_rate": 2.996848971420801e-06,
+      "loss": 0.6145,
+      "step": 14
+    },
+    {
+      "epoch": 0.07568590350047304,
+      "grad_norm": 0.048907003957727534,
+      "learning_rate": 2.996382992344734e-06,
+      "loss": 0.5755,
+      "step": 15
+    },
+    {
+      "epoch": 0.08073163040050457,
+      "grad_norm": 0.04502223888969105,
+      "learning_rate": 2.9958849464720457e-06,
+      "loss": 0.5765,
+      "step": 16
+    },
+    {
+      "epoch": 0.08577735730053611,
+      "grad_norm": 0.04485565875842678,
+      "learning_rate": 2.9953548477341497e-06,
+      "loss": 0.6364,
+      "step": 17
+    },
+    {
+      "epoch": 0.09082308420056764,
+      "grad_norm": 0.04319237430058616,
+      "learning_rate": 2.9947927109590477e-06,
+      "loss": 0.568,
+      "step": 18
+    },
+    {
+      "epoch": 0.09586881110059918,
+      "grad_norm": 0.042093297202993624,
+      "learning_rate": 2.994198551870913e-06,
+      "loss": 0.6184,
+      "step": 19
+    },
+    {
+      "epoch": 0.10091453800063072,
+      "grad_norm": 0.04087623899598573,
+      "learning_rate": 2.993572387089653e-06,
+      "loss": 0.5822,
+      "step": 20
+    },
+    {
+      "epoch": 0.10596026490066225,
+      "grad_norm": 0.042619877493329586,
+      "learning_rate": 2.992914234130442e-06,
+      "loss": 0.5983,
+      "step": 21
+    },
+    {
+      "epoch": 0.11100599180069379,
+      "grad_norm": 0.04314774114784986,
+      "learning_rate": 2.9922241114032345e-06,
+      "loss": 0.6058,
+      "step": 22
+    },
+    {
+      "epoch": 0.11605171870072532,
+      "grad_norm": 0.04125496902035363,
+      "learning_rate": 2.9915020382122458e-06,
+      "loss": 0.5741,
+      "step": 23
+    },
+    {
+      "epoch": 0.12109744560075686,
+      "grad_norm": 0.03985368427853683,
+      "learning_rate": 2.990748034755415e-06,
+      "loss": 0.6002,
+      "step": 24
+    },
+    {
+      "epoch": 0.1261431725007884,
+      "grad_norm": 0.04603566805698703,
+      "learning_rate": 2.9899621221238394e-06,
+      "loss": 0.5616,
+      "step": 25
+    },
+    {
+      "epoch": 0.13118889940081993,
+      "grad_norm": 0.033944581121186666,
+      "learning_rate": 2.989144322301186e-06,
+      "loss": 0.591,
+      "step": 26
+    },
+    {
+      "epoch": 0.13623462630085148,
+      "grad_norm": 0.0352127486146018,
+      "learning_rate": 2.988294658163073e-06,
+      "loss": 0.575,
+      "step": 27
+    },
+    {
+      "epoch": 0.141280353200883,
+      "grad_norm": 0.04026082684896548,
+      "learning_rate": 2.9874131534764325e-06,
+      "loss": 0.5783,
+      "step": 28
+    },
+    {
+      "epoch": 0.14632608010091455,
+      "grad_norm": 0.038584952671910096,
+      "learning_rate": 2.9864998328988463e-06,
+      "loss": 0.5814,
+      "step": 29
+    },
+    {
+      "epoch": 0.15137180700094607,
+      "grad_norm": 0.03294755370363045,
+      "learning_rate": 2.985554721977853e-06,
+      "loss": 0.5688,
+      "step": 30
+    },
+    {
+      "epoch": 0.15641753390097762,
+      "grad_norm": 0.035774614388450525,
+      "learning_rate": 2.984577847150239e-06,
+      "loss": 0.5914,
+      "step": 31
+    },
+    {
+      "epoch": 0.16146326080100915,
+      "grad_norm": 0.04512017281393784,
+      "learning_rate": 2.983569235741291e-06,
+      "loss": 0.557,
+      "step": 32
+    },
+    {
+      "epoch": 0.1665089877010407,
+      "grad_norm": 0.03447545680264101,
+      "learning_rate": 2.9825289159640397e-06,
+      "loss": 0.568,
+      "step": 33
+    },
+    {
+      "epoch": 0.17155471460107222,
+      "grad_norm": 0.033658505681229516,
+      "learning_rate": 2.9814569169184642e-06,
+      "loss": 0.5868,
+      "step": 34
+    },
+    {
+      "epoch": 0.17660044150110377,
+      "grad_norm": 0.03071546221735757,
+      "learning_rate": 2.980353268590683e-06,
+      "loss": 0.5487,
+      "step": 35
+    },
+    {
+      "epoch": 0.1816461684011353,
+      "grad_norm": 0.07417860742940319,
+      "learning_rate": 2.9792180018521128e-06,
+      "loss": 0.6099,
+      "step": 36
+    },
+    {
+      "epoch": 0.18669189530116684,
+      "grad_norm": 0.032180325133544276,
+      "learning_rate": 2.978051148458604e-06,
+      "loss": 0.5939,
+      "step": 37
+    },
+    {
+      "epoch": 0.19173762220119836,
+      "grad_norm": 0.031347752245340116,
+      "learning_rate": 2.976852741049554e-06,
+      "loss": 0.5764,
+      "step": 38
+    },
+    {
+      "epoch": 0.1967833491012299,
+      "grad_norm": 0.035873383222778825,
+      "learning_rate": 2.975622813146996e-06,
+      "loss": 0.57,
+      "step": 39
+    },
+    {
+      "epoch": 0.20182907600126143,
+      "grad_norm": 0.03130302787258777,
+      "learning_rate": 2.9743613991546548e-06,
+      "loss": 0.5503,
+      "step": 40
+    },
+    {
+      "epoch": 0.20687480290129298,
+      "grad_norm": 0.04111552220221803,
+      "learning_rate": 2.9730685343569934e-06,
+      "loss": 0.6028,
+      "step": 41
+    },
+    {
+      "epoch": 0.2119205298013245,
+      "grad_norm": 0.031561335436647305,
+      "learning_rate": 2.971744254918218e-06,
+      "loss": 0.5682,
+      "step": 42
+    },
+    {
+      "epoch": 0.21696625670135605,
+      "grad_norm": 0.03466870924962832,
+      "learning_rate": 2.9703885978812726e-06,
+      "loss": 0.55,
+      "step": 43
+    },
+    {
+      "epoch": 0.22201198360138757,
+      "grad_norm": 0.03396258277418921,
+      "learning_rate": 2.9690016011667974e-06,
+      "loss": 0.5953,
+      "step": 44
+    },
+    {
+      "epoch": 0.22705771050141912,
+      "grad_norm": 0.033463552224919146,
+      "learning_rate": 2.967583303572073e-06,
+      "loss": 0.6231,
+      "step": 45
+    },
+    {
+      "epoch": 0.23210343740145065,
+      "grad_norm": 0.03747113039368738,
+      "learning_rate": 2.9661337447699316e-06,
+      "loss": 0.5742,
+      "step": 46
+    },
+    {
+      "epoch": 0.2371491643014822,
+      "grad_norm": 0.04159182229285405,
+      "learning_rate": 2.9646529653076493e-06,
+      "loss": 0.5681,
+      "step": 47
+    },
+    {
+      "epoch": 0.24219489120151372,
+      "grad_norm": 0.032311171301265075,
+      "learning_rate": 2.9631410066058098e-06,
+      "loss": 0.5464,
+      "step": 48
+    },
+    {
+      "epoch": 0.24724061810154527,
+      "grad_norm": 0.035494911254562625,
+      "learning_rate": 2.9615979109571493e-06,
+      "loss": 0.5377,
+      "step": 49
+    },
+    {
+      "epoch": 0.2522863450015768,
+      "grad_norm": 0.032401750473671755,
+      "learning_rate": 2.9600237215253696e-06,
+      "loss": 0.6043,
+      "step": 50
+    },
+    {
+      "epoch": 0.25733207190160834,
+      "grad_norm": 0.03477400444401883,
+      "learning_rate": 2.9584184823439337e-06,
+      "loss": 0.6078,
+      "step": 51
+    },
+    {
+      "epoch": 0.26237779880163986,
+      "grad_norm": 0.03586539534553979,
+      "learning_rate": 2.9567822383148315e-06,
+      "loss": 0.5857,
+      "step": 52
+    },
+    {
+      "epoch": 0.2674235257016714,
+      "grad_norm": 0.034776366845092124,
+      "learning_rate": 2.955115035207326e-06,
+      "loss": 0.5652,
+      "step": 53
+    },
+    {
+      "epoch": 0.27246925260170296,
+      "grad_norm": 0.047916672806890825,
+      "learning_rate": 2.953416919656672e-06,
+      "loss": 0.529,
+      "step": 54
+    },
+    {
+      "epoch": 0.2775149795017345,
+      "grad_norm": 0.035512253032401846,
+      "learning_rate": 2.9516879391628125e-06,
+      "loss": 0.6018,
+      "step": 55
+    },
+    {
+      "epoch": 0.282560706401766,
+      "grad_norm": 0.0669654595534551,
+      "learning_rate": 2.9499281420890474e-06,
+      "loss": 0.5832,
+      "step": 56
+    },
+    {
+      "epoch": 0.2876064333017975,
+      "grad_norm": 0.04009377576904152,
+      "learning_rate": 2.948137577660685e-06,
+      "loss": 0.5376,
+      "step": 57
+    },
+    {
+      "epoch": 0.2926521602018291,
+      "grad_norm": 0.05517678453435375,
+      "learning_rate": 2.946316295963661e-06,
+      "loss": 0.5725,
+      "step": 58
+    },
+    {
+      "epoch": 0.2976978871018606,
+      "grad_norm": 0.040682905696082294,
+      "learning_rate": 2.9444643479431393e-06,
+      "loss": 0.5887,
+      "step": 59
+    },
+    {
+      "epoch": 0.30274361400189215,
+      "grad_norm": 0.044774454426992336,
+      "learning_rate": 2.9425817854020873e-06,
+      "loss": 0.5756,
+      "step": 60
+    },
+    {
+      "epoch": 0.30778934090192367,
+      "grad_norm": 0.03263011910584542,
+      "learning_rate": 2.940668660999826e-06,
+      "loss": 0.5693,
+      "step": 61
+    },
+    {
+      "epoch": 0.31283506780195525,
+      "grad_norm": 0.032496230797448664,
+      "learning_rate": 2.9387250282505583e-06,
+      "loss": 0.586,
+      "step": 62
+    },
+    {
+      "epoch": 0.31788079470198677,
+      "grad_norm": 0.03310861754959189,
+      "learning_rate": 2.9367509415218687e-06,
+      "loss": 0.5548,
+      "step": 63
+    },
+    {
+      "epoch": 0.3229265216020183,
+      "grad_norm": 0.031816229512850104,
+      "learning_rate": 2.9347464560332084e-06,
+      "loss": 0.6,
+      "step": 64
+    },
+    {
+      "epoch": 0.3279722485020498,
+      "grad_norm": 0.036465675122600016,
+      "learning_rate": 2.932711627854344e-06,
+      "loss": 0.5613,
+      "step": 65
+    },
+    {
+      "epoch": 0.3330179754020814,
+      "grad_norm": 0.03107217546123426,
+      "learning_rate": 2.9306465139037947e-06,
+      "loss": 0.5421,
+      "step": 66
+    },
+    {
+      "epoch": 0.3380637023021129,
+      "grad_norm": 0.031633841290591734,
+      "learning_rate": 2.9285511719472367e-06,
+      "loss": 0.58,
+      "step": 67
+    },
+    {
+      "epoch": 0.34310942920214443,
+      "grad_norm": 0.030853855883844275,
+      "learning_rate": 2.9264256605958885e-06,
+      "loss": 0.5496,
+      "step": 68
+    },
+    {
+      "epoch": 0.34815515610217596,
+      "grad_norm": 0.036265638918391636,
+      "learning_rate": 2.924270039304873e-06,
+      "loss": 0.5939,
+      "step": 69
+    },
+    {
+      "epoch": 0.35320088300220753,
+      "grad_norm": 0.03703293289195566,
+      "learning_rate": 2.9220843683715497e-06,
+      "loss": 0.5311,
+      "step": 70
+    },
+    {
+      "epoch": 0.35824660990223905,
+      "grad_norm": 0.07682301940151573,
+      "learning_rate": 2.9198687089338345e-06,
+      "loss": 0.5655,
+      "step": 71
+    },
+    {
+      "epoch": 0.3632923368022706,
+      "grad_norm": 0.03240731857642153,
+      "learning_rate": 2.9176231229684835e-06,
+      "loss": 0.5436,
+      "step": 72
+    },
+    {
+      "epoch": 0.3683380637023021,
+      "grad_norm": 0.03550209155305971,
+      "learning_rate": 2.9153476732893646e-06,
+      "loss": 0.5529,
+      "step": 73
+    },
+    {
+      "epoch": 0.3733837906023337,
+      "grad_norm": 0.03572110732287988,
+      "learning_rate": 2.913042423545696e-06,
+      "loss": 0.5601,
+      "step": 74
+    },
+    {
+      "epoch": 0.3784295175023652,
+      "grad_norm": 0.030318267187340705,
+      "learning_rate": 2.910707438220269e-06,
+      "loss": 0.5827,
+      "step": 75
+    },
+    {
+      "epoch": 0.3834752444023967,
+      "grad_norm": 0.030779462298936085,
+      "learning_rate": 2.9083427826276414e-06,
+      "loss": 0.5366,
+      "step": 76
+    },
+    {
+      "epoch": 0.38852097130242824,
+      "grad_norm": 0.033078267956613755,
+      "learning_rate": 2.905948522912315e-06,
+      "loss": 0.5769,
+      "step": 77
+    },
+    {
+      "epoch": 0.3935666982024598,
+      "grad_norm": 0.032022182515529865,
+      "learning_rate": 2.90352472604688e-06,
+      "loss": 0.6059,
+      "step": 78
+    },
+    {
+      "epoch": 0.39861242510249134,
+      "grad_norm": 0.032572741826790486,
+      "learning_rate": 2.901071459830145e-06,
+      "loss": 0.5325,
+      "step": 79
+    },
+    {
+      "epoch": 0.40365815200252286,
+      "grad_norm": 0.03322477222052267,
+      "learning_rate": 2.89858879288524e-06,
+      "loss": 0.6102,
+      "step": 80
+    },
+    {
+      "epoch": 0.4087038789025544,
+      "grad_norm": 0.03290381540817977,
+      "learning_rate": 2.896076794657696e-06,
+      "loss": 0.5297,
+      "step": 81
+    },
+    {
+      "epoch": 0.41374960580258596,
+      "grad_norm": 0.02986308712893659,
+      "learning_rate": 2.893535535413504e-06,
+      "loss": 0.6016,
+      "step": 82
+    },
+    {
+      "epoch": 0.4187953327026175,
+      "grad_norm": 0.03708195442407903,
+      "learning_rate": 2.8909650862371465e-06,
+      "loss": 0.5644,
+      "step": 83
+    },
+    {
+      "epoch": 0.423841059602649,
+      "grad_norm": 0.05585756602200335,
+      "learning_rate": 2.888365519029615e-06,
+      "loss": 0.5645,
+      "step": 84
+    },
+    {
+      "epoch": 0.42888678650268053,
+      "grad_norm": 0.03232081336561299,
+      "learning_rate": 2.8857369065063893e-06,
+      "loss": 0.5492,
+      "step": 85
+    },
+    {
+      "epoch": 0.4339325134027121,
+      "grad_norm": 0.03807439954613977,
+      "learning_rate": 2.883079322195415e-06,
+      "loss": 0.5694,
+      "step": 86
+    },
+    {
+      "epoch": 0.4389782403027436,
+      "grad_norm": 0.03718669059491054,
+      "learning_rate": 2.880392840435036e-06,
+      "loss": 0.5603,
+      "step": 87
+    },
+    {
+      "epoch": 0.44402396720277515,
+      "grad_norm": 0.02993361885707706,
+      "learning_rate": 2.8776775363719244e-06,
+      "loss": 0.5193,
+      "step": 88
+    },
+    {
+      "epoch": 0.44906969410280667,
+      "grad_norm": 0.03471859873605538,
+      "learning_rate": 2.8749334859589696e-06,
+      "loss": 0.5195,
+      "step": 89
+    },
+    {
+      "epoch": 0.45411542100283825,
+      "grad_norm": 0.03468783264087511,
+      "learning_rate": 2.872160765953162e-06,
+      "loss": 0.5685,
+      "step": 90
+    },
+    {
+      "epoch": 0.45916114790286977,
+      "grad_norm": 0.06028818099354049,
+      "learning_rate": 2.86935945391344e-06,
+      "loss": 0.5875,
+      "step": 91
+    },
+    {
+      "epoch": 0.4642068748029013,
+      "grad_norm": 0.03189592063110031,
+      "learning_rate": 2.8665296281985232e-06,
+      "loss": 0.5627,
+      "step": 92
+    },
+    {
+      "epoch": 0.4692526017029328,
+      "grad_norm": 0.032489964455779306,
+      "learning_rate": 2.8636713679647195e-06,
+      "loss": 0.5398,
+      "step": 93
+    },
+    {
+      "epoch": 0.4742983286029644,
+      "grad_norm": 0.03300509062363307,
+      "learning_rate": 2.8607847531637127e-06,
+      "loss": 0.5675,
+      "step": 94
+    },
+    {
+      "epoch": 0.4793440555029959,
+      "grad_norm": 0.034805575232998785,
+      "learning_rate": 2.857869864540323e-06,
+      "loss": 0.5526,
+      "step": 95
+    },
+    {
+      "epoch": 0.48438978240302744,
+      "grad_norm": 0.03304213276713402,
+      "learning_rate": 2.854926783630253e-06,
+      "loss": 0.5475,
+      "step": 96
+    },
+    {
+      "epoch": 0.48943550930305896,
+      "grad_norm": 0.03753659611183512,
+      "learning_rate": 2.851955592757801e-06,
+      "loss": 0.5511,
+      "step": 97
+    },
+    {
+      "epoch": 0.49448123620309054,
+      "grad_norm": 0.033892234979303396,
+      "learning_rate": 2.848956375033562e-06,
+      "loss": 0.5232,
+      "step": 98
+    },
+    {
+      "epoch": 0.49952696310312206,
+      "grad_norm": 0.037074509268233,
+      "learning_rate": 2.845929214352105e-06,
+      "loss": 0.5655,
+      "step": 99
+    },
+    {
+      "epoch": 0.5045726900031536,
+      "grad_norm": 0.03224402404614455,
+      "learning_rate": 2.8428741953896195e-06,
+      "loss": 0.5556,
+      "step": 100
+    },
+    {
+      "epoch": 0.5096184169031851,
+      "grad_norm": 0.03072821069928307,
+      "learning_rate": 2.839791403601555e-06,
+      "loss": 0.5472,
+      "step": 101
+    },
+    {
+      "epoch": 0.5146641438032167,
+      "grad_norm": 0.03380249813156003,
+      "learning_rate": 2.8366809252202235e-06,
+      "loss": 0.5413,
+      "step": 102
+    },
+    {
+      "epoch": 0.5197098707032481,
+      "grad_norm": 0.0335216929092493,
+      "learning_rate": 2.8335428472523927e-06,
+      "loss": 0.5479,
+      "step": 103
+    },
+    {
+      "epoch": 0.5247555976032797,
+      "grad_norm": 0.030808915999862914,
+      "learning_rate": 2.8303772574768482e-06,
+      "loss": 0.548,
+      "step": 104
+    },
+    {
+      "epoch": 0.5298013245033113,
+      "grad_norm": 0.02912454306651085,
+      "learning_rate": 2.8271842444419414e-06,
+      "loss": 0.548,
+      "step": 105
+    },
+    {
+      "epoch": 0.5348470514033428,
+      "grad_norm": 0.05012632142858796,
+      "learning_rate": 2.8239638974631112e-06,
+      "loss": 0.5152,
+      "step": 106
+    },
+    {
+      "epoch": 0.5398927783033743,
+      "grad_norm": 0.0344361048789296,
+      "learning_rate": 2.8207163066203843e-06,
+      "loss": 0.5698,
+      "step": 107
+    },
+    {
+      "epoch": 0.5449385052034059,
+      "grad_norm": 0.10550189124699653,
+      "learning_rate": 2.8174415627558584e-06,
+      "loss": 0.522,
+      "step": 108
+    },
+    {
+      "epoch": 0.5499842321034374,
+      "grad_norm": 0.0323910546595259,
+      "learning_rate": 2.8141397574711587e-06,
+      "loss": 0.5518,
+      "step": 109
+    },
+    {
+      "epoch": 0.555029959003469,
+      "grad_norm": 0.032448012717327133,
+      "learning_rate": 2.810810983124877e-06,
+      "loss": 0.5839,
+      "step": 110
+    },
+    {
+      "epoch": 0.5600756859035004,
+      "grad_norm": 0.03112632332891334,
+      "learning_rate": 2.807455332829987e-06,
+      "loss": 0.5635,
+      "step": 111
+    },
+    {
+      "epoch": 0.565121412803532,
+      "grad_norm": 0.035282498495490644,
+      "learning_rate": 2.8040729004512415e-06,
+      "loss": 0.535,
+      "step": 112
+    },
+    {
+      "epoch": 0.5701671397035636,
+      "grad_norm": 0.02966255382156268,
+      "learning_rate": 2.800663780602545e-06,
+      "loss": 0.5492,
+      "step": 113
+    },
+    {
+      "epoch": 0.575212866603595,
+      "grad_norm": 0.03707668859813438,
+      "learning_rate": 2.7972280686443077e-06,
+      "loss": 0.5663,
+      "step": 114
+    },
+    {
+      "epoch": 0.5802585935036266,
+      "grad_norm": 0.03659428904439035,
+      "learning_rate": 2.793765860680779e-06,
+      "loss": 0.542,
+      "step": 115
+    },
+    {
+      "epoch": 0.5853043204036582,
+      "grad_norm": 0.035159210590374,
+      "learning_rate": 2.790277253557359e-06,
+      "loss": 0.5738,
+      "step": 116
+    },
+    {
+      "epoch": 0.5903500473036897,
+      "grad_norm": 0.030990014790480254,
+      "learning_rate": 2.7867623448578863e-06,
+      "loss": 0.5892,
+      "step": 117
+    },
+    {
+      "epoch": 0.5953957742037213,
+      "grad_norm": 0.03399071129755366,
+      "learning_rate": 2.783221232901914e-06,
+      "loss": 0.5677,
+      "step": 118
+    },
+    {
+      "epoch": 0.6004415011037527,
+      "grad_norm": 0.03247591991435437,
+      "learning_rate": 2.7796540167419567e-06,
+      "loss": 0.5412,
+      "step": 119
+    },
+    {
+      "epoch": 0.6054872280037843,
+      "grad_norm": 0.032370031907677656,
+      "learning_rate": 2.7760607961607174e-06,
+      "loss": 0.5556,
+      "step": 120
+    },
+    {
+      "epoch": 0.6105329549038159,
+      "grad_norm": 0.033174635710333106,
+      "learning_rate": 2.7724416716683005e-06,
+      "loss": 0.5668,
+      "step": 121
+    },
+    {
+      "epoch": 0.6155786818038473,
+      "grad_norm": 0.03148435780507138,
+      "learning_rate": 2.7687967444993976e-06,
+      "loss": 0.5205,
+      "step": 122
+    },
+    {
+      "epoch": 0.6206244087038789,
+      "grad_norm": 0.03187378459330813,
+      "learning_rate": 2.7651261166104574e-06,
+      "loss": 0.5563,
+      "step": 123
+    },
+    {
+      "epoch": 0.6256701356039105,
+      "grad_norm": 0.03429711811644175,
+      "learning_rate": 2.7614298906768316e-06,
+      "loss": 0.5167,
+      "step": 124
+    },
+    {
+      "epoch": 0.630715862503942,
+      "grad_norm": 0.03859718827910278,
+      "learning_rate": 2.757708170089906e-06,
+      "loss": 0.559,
+      "step": 125
+    },
+    {
+      "epoch": 0.6357615894039735,
+      "grad_norm": 0.03623858619383074,
+      "learning_rate": 2.7539610589542057e-06,
+      "loss": 0.5795,
+      "step": 126
+    },
+    {
+      "epoch": 0.640807316304005,
+      "grad_norm": 0.03263585179382894,
+      "learning_rate": 2.750188662084484e-06,
+      "loss": 0.5566,
+      "step": 127
+    },
+    {
+      "epoch": 0.6458530432040366,
+      "grad_norm": 0.03877113662246629,
+      "learning_rate": 2.746391085002791e-06,
+      "loss": 0.6018,
+      "step": 128
+    },
+    {
+      "epoch": 0.6508987701040682,
+      "grad_norm": 0.03400954730094289,
+      "learning_rate": 2.7425684339355203e-06,
+      "loss": 0.5438,
+      "step": 129
+    },
+    {
+      "epoch": 0.6559444970040996,
+      "grad_norm": 0.03140528838198611,
+      "learning_rate": 2.7387208158104406e-06,
+      "loss": 0.5554,
+      "step": 130
+    },
+    {
+      "epoch": 0.6609902239041312,
+      "grad_norm": 0.037206585802644396,
+      "learning_rate": 2.7348483382537015e-06,
+      "loss": 0.5634,
+      "step": 131
+    },
+    {
+      "epoch": 0.6660359508041628,
+      "grad_norm": 0.03211586967766076,
+      "learning_rate": 2.7309511095868246e-06,
+      "loss": 0.5391,
+      "step": 132
+    },
+    {
+      "epoch": 0.6710816777041942,
+      "grad_norm": 0.03396187095971342,
+      "learning_rate": 2.727029238823674e-06,
+      "loss": 0.5406,
+      "step": 133
+    },
+    {
+      "epoch": 0.6761274046042258,
+      "grad_norm": 0.03502286862929664,
+      "learning_rate": 2.7230828356674047e-06,
+      "loss": 0.5753,
+      "step": 134
+    },
+    {
+      "epoch": 0.6811731315042573,
+      "grad_norm": 0.03214739270222773,
+      "learning_rate": 2.7191120105073974e-06,
+      "loss": 0.5245,
+      "step": 135
+    },
+    {
+      "epoch": 0.6862188584042889,
+      "grad_norm": 0.03387635714681519,
+      "learning_rate": 2.7151168744161664e-06,
+      "loss": 0.54,
+      "step": 136
+    },
+    {
+      "epoch": 0.6912645853043204,
+      "grad_norm": 0.032951263305626276,
+      "learning_rate": 2.7110975391462574e-06,
+      "loss": 0.5259,
+      "step": 137
+    },
+    {
+      "epoch": 0.6963103122043519,
+      "grad_norm": 0.05015537211126262,
+      "learning_rate": 2.707054117127118e-06,
+      "loss": 0.5267,
+      "step": 138
+    },
+    {
+      "epoch": 0.7013560391043835,
+      "grad_norm": 0.035135429069184716,
+      "learning_rate": 2.7029867214619533e-06,
+      "loss": 0.5518,
+      "step": 139
+    },
+    {
+      "epoch": 0.7064017660044151,
+      "grad_norm": 0.0320337788657044,
+      "learning_rate": 2.698895465924565e-06,
+      "loss": 0.5555,
+      "step": 140
+    },
+    {
+      "epoch": 0.7114474929044465,
+      "grad_norm": 0.03645990761972981,
+      "learning_rate": 2.6947804649561633e-06,
+      "loss": 0.572,
+      "step": 141
+    },
+    {
+      "epoch": 0.7164932198044781,
+      "grad_norm": 0.03470519450277183,
+      "learning_rate": 2.6906418336621724e-06,
+      "loss": 0.5505,
+      "step": 142
+    },
+    {
+      "epoch": 0.7215389467045096,
+      "grad_norm": 0.031235480044832488,
+      "learning_rate": 2.686479687809006e-06,
+      "loss": 0.5377,
+      "step": 143
+    },
+    {
+      "epoch": 0.7265846736045412,
+      "grad_norm": 0.029941451042590675,
+      "learning_rate": 2.6822941438208306e-06,
+      "loss": 0.5381,
+      "step": 144
+    },
+    {
+      "epoch": 0.7316304005045727,
+      "grad_norm": 0.035617952049989555,
+      "learning_rate": 2.6780853187763096e-06,
+      "loss": 0.5546,
+      "step": 145
+    },
+    {
+      "epoch": 0.7366761274046042,
+      "grad_norm": 0.03343536591046196,
+      "learning_rate": 2.673853330405326e-06,
+      "loss": 0.5519,
+      "step": 146
+    },
+    {
+      "epoch": 0.7417218543046358,
+      "grad_norm": 0.03110711029893078,
+      "learning_rate": 2.6695982970856925e-06,
+      "loss": 0.5744,
+      "step": 147
+    },
+    {
+      "epoch": 0.7467675812046674,
+      "grad_norm": 0.030535258085941947,
+      "learning_rate": 2.6653203378398375e-06,
+      "loss": 0.5239,
+      "step": 148
+    },
+    {
+      "epoch": 0.7518133081046988,
+      "grad_norm": 0.06889481171001853,
+      "learning_rate": 2.661019572331478e-06,
+      "loss": 0.5445,
+      "step": 149
+    },
+    {
+      "epoch": 0.7568590350047304,
+      "grad_norm": 0.034136168134648794,
+      "learning_rate": 2.6566961208622696e-06,
+      "loss": 0.5403,
+      "step": 150
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.03361146386829785,
+      "learning_rate": 2.652350104368444e-06,
+      "loss": 0.5252,
+      "step": 151
+    },
+    {
+      "epoch": 0.7669504888047934,
+      "grad_norm": 0.03232558697340943,
+      "learning_rate": 2.6479816444174253e-06,
+      "loss": 0.5537,
+      "step": 152
+    },
+    {
+      "epoch": 0.771996215704825,
+      "grad_norm": 0.031246440682898686,
+      "learning_rate": 2.643590863204429e-06,
+      "loss": 0.5358,
+      "step": 153
+    },
+    {
+      "epoch": 0.7770419426048565,
+      "grad_norm": 0.03123193076665316,
+      "learning_rate": 2.6391778835490438e-06,
+      "loss": 0.5162,
+      "step": 154
+    },
+    {
+      "epoch": 0.7820876695048881,
+      "grad_norm": 0.042414916882850415,
+      "learning_rate": 2.6347428288917972e-06,
+      "loss": 0.5522,
+      "step": 155
+    },
+    {
+      "epoch": 0.7871333964049196,
+      "grad_norm": 0.03663820317771632,
+      "learning_rate": 2.630285823290702e-06,
+      "loss": 0.5395,
+      "step": 156
+    },
+    {
+      "epoch": 0.7921791233049511,
+      "grad_norm": 0.0323447950510978,
+      "learning_rate": 2.625806991417786e-06,
+      "loss": 0.5471,
+      "step": 157
+    },
+    {
+      "epoch": 0.7972248502049827,
+      "grad_norm": 0.03301071769705723,
+      "learning_rate": 2.621306458555604e-06,
+      "loss": 0.5529,
+      "step": 158
+    },
+    {
+      "epoch": 0.8022705771050141,
+      "grad_norm": 0.03261309640826233,
+      "learning_rate": 2.6167843505937356e-06,
+      "loss": 0.5507,
+      "step": 159
+    },
+    {
+      "epoch": 0.8073163040050457,
+      "grad_norm": 0.03240576468524181,
+      "learning_rate": 2.6122407940252608e-06,
+      "loss": 0.5468,
+      "step": 160
+    },
+    {
+      "epoch": 0.8123620309050773,
+      "grad_norm": 0.03018210963467149,
+      "learning_rate": 2.6076759159432237e-06,
+      "loss": 0.5583,
+      "step": 161
+    },
+    {
+      "epoch": 0.8174077578051088,
+      "grad_norm": 0.031036132663069035,
+      "learning_rate": 2.603089844037078e-06,
+      "loss": 0.5226,
+      "step": 162
+    },
+    {
+      "epoch": 0.8224534847051403,
+      "grad_norm": 0.0347386534073021,
+      "learning_rate": 2.5984827065891126e-06,
+      "loss": 0.5529,
+      "step": 163
+    },
+    {
+      "epoch": 0.8274992116051719,
+      "grad_norm": 0.044827581860260125,
+      "learning_rate": 2.593854632470866e-06,
+      "loss": 0.6117,
+      "step": 164
+    },
+    {
+      "epoch": 0.8325449385052034,
+      "grad_norm": 0.030210519399600917,
+      "learning_rate": 2.5892057511395202e-06,
+      "loss": 0.5436,
+      "step": 165
+    },
+    {
+      "epoch": 0.837590665405235,
+      "grad_norm": 0.031447473869825514,
+      "learning_rate": 2.5845361926342794e-06,
+      "loss": 0.5228,
+      "step": 166
+    },
+    {
+      "epoch": 0.8426363923052664,
+      "grad_norm": 0.035332567006398724,
+      "learning_rate": 2.5798460875727326e-06,
+      "loss": 0.5478,
+      "step": 167
+    },
+    {
+      "epoch": 0.847682119205298,
+      "grad_norm": 0.02886367248116525,
+      "learning_rate": 2.575135567147201e-06,
+      "loss": 0.5114,
+      "step": 168
+    },
+    {
+      "epoch": 0.8527278461053296,
+      "grad_norm": 0.031532384271644245,
+      "learning_rate": 2.5704047631210664e-06,
+      "loss": 0.5623,
+      "step": 169
+    },
+    {
+      "epoch": 0.8577735730053611,
+      "grad_norm": 0.034567108800704585,
+      "learning_rate": 2.5656538078250873e-06,
+      "loss": 0.5657,
+      "step": 170
+    },
+    {
+      "epoch": 0.8628192999053926,
+      "grad_norm": 0.03160145253530057,
+      "learning_rate": 2.560882834153696e-06,
+      "loss": 0.5136,
+      "step": 171
+    },
+    {
+      "epoch": 0.8678650268054242,
+      "grad_norm": 0.03135869657202659,
+      "learning_rate": 2.5560919755612823e-06,
+      "loss": 0.544,
+      "step": 172
+    },
+    {
+      "epoch": 0.8729107537054557,
+      "grad_norm": 0.03597121576219098,
+      "learning_rate": 2.5512813660584597e-06,
+      "loss": 0.5152,
+      "step": 173
+    },
+    {
+      "epoch": 0.8779564806054873,
+      "grad_norm": 0.030221173382051915,
+      "learning_rate": 2.5464511402083166e-06,
+      "loss": 0.5251,
+      "step": 174
+    },
+    {
+      "epoch": 0.8830022075055187,
+      "grad_norm": 0.030000072996604673,
+      "learning_rate": 2.541601433122654e-06,
+      "loss": 0.5186,
+      "step": 175
+    },
+    {
+      "epoch": 0.8880479344055503,
+      "grad_norm": 0.03376922343601561,
+      "learning_rate": 2.536732380458204e-06,
+      "loss": 0.5164,
+      "step": 176
+    },
+    {
+      "epoch": 0.8930936613055819,
+      "grad_norm": 0.03156034083736404,
+      "learning_rate": 2.531844118412837e-06,
+      "loss": 0.5316,
+      "step": 177
+    },
+    {
+      "epoch": 0.8981393882056133,
+      "grad_norm": 0.03377666641180589,
+      "learning_rate": 2.5269367837217488e-06,
+      "loss": 0.5054,
+      "step": 178
+    },
+    {
+      "epoch": 0.9031851151056449,
+      "grad_norm": 0.030954166615192916,
+      "learning_rate": 2.522010513653642e-06,
+      "loss": 0.5256,
+      "step": 179
+    },
+    {
+      "epoch": 0.9082308420056765,
+      "grad_norm": 0.03484714660203487,
+      "learning_rate": 2.517065446006878e-06,
+      "loss": 0.5225,
+      "step": 180
+    },
+    {
+      "epoch": 0.913276568905708,
+      "grad_norm": 0.06223673456920668,
+      "learning_rate": 2.5121017191056306e-06,
+      "loss": 0.5207,
+      "step": 181
+    },
+    {
+      "epoch": 0.9183222958057395,
+      "grad_norm": 0.04079770792332633,
+      "learning_rate": 2.507119471796011e-06,
+      "loss": 0.555,
+      "step": 182
+    },
+    {
+      "epoch": 0.923368022705771,
+      "grad_norm": 0.030029925631475055,
+      "learning_rate": 2.5021188434421863e-06,
+      "loss": 0.5435,
+      "step": 183
+    },
+    {
+      "epoch": 0.9284137496058026,
+      "grad_norm": 0.03519161994895625,
+      "learning_rate": 2.4970999739224816e-06,
+      "loss": 0.5817,
+      "step": 184
+    },
+    {
+      "epoch": 0.9334594765058342,
+      "grad_norm": 0.03194895322649527,
+      "learning_rate": 2.492063003625466e-06,
+      "loss": 0.5288,
+      "step": 185
+    },
+    {
+      "epoch": 0.9385052034058656,
+      "grad_norm": 0.03862824281648028,
+      "learning_rate": 2.487008073446027e-06,
+      "loss": 0.5428,
+      "step": 186
+    },
+    {
+      "epoch": 0.9435509303058972,
+      "grad_norm": 0.040703435887500077,
+      "learning_rate": 2.481935324781427e-06,
+      "loss": 0.5407,
+      "step": 187
+    },
+    {
+      "epoch": 0.9485966572059288,
+      "grad_norm": 0.03251789567309417,
+      "learning_rate": 2.4768448995273514e-06,
+      "loss": 0.5305,
+      "step": 188
+    },
+    {
+      "epoch": 0.9536423841059603,
+      "grad_norm": 0.031182531135357086,
+      "learning_rate": 2.4717369400739372e-06,
+      "loss": 0.5436,
+      "step": 189
+    },
+    {
+      "epoch": 0.9586881110059918,
+      "grad_norm": 0.033544076361382125,
+      "learning_rate": 2.466611589301791e-06,
+      "loss": 0.5849,
+      "step": 190
+    },
+    {
+      "epoch": 0.9637338379060233,
+      "grad_norm": 0.03146239237618079,
+      "learning_rate": 2.4614689905779907e-06,
+      "loss": 0.5424,
+      "step": 191
+    },
+    {
+      "epoch": 0.9687795648060549,
+      "grad_norm": 0.031938896005507596,
+      "learning_rate": 2.4563092877520776e-06,
+      "loss": 0.5541,
+      "step": 192
+    },
+    {
+      "epoch": 0.9738252917060864,
+      "grad_norm": 0.031136299616893074,
+      "learning_rate": 2.4511326251520325e-06,
+      "loss": 0.58,
+      "step": 193
+    },
+    {
+      "epoch": 0.9788710186061179,
+      "grad_norm": 0.03323472651029714,
+      "learning_rate": 2.445939147580235e-06,
+      "loss": 0.5073,
+      "step": 194
+    },
+    {
+      "epoch": 0.9839167455061495,
+      "grad_norm": 0.03213726601057571,
+      "learning_rate": 2.4407290003094177e-06,
+      "loss": 0.5758,
+      "step": 195
+    },
+    {
+      "epoch": 0.9889624724061811,
+      "grad_norm": 0.032768188978415214,
+      "learning_rate": 2.4355023290785993e-06,
+      "loss": 0.5354,
+      "step": 196
+    },
+    {
+      "epoch": 0.9940081993062125,
+      "grad_norm": 0.10156434597935675,
+      "learning_rate": 2.4302592800890095e-06,
+      "loss": 0.5784,
+      "step": 197
+    },
+    {
+      "epoch": 0.9990539262062441,
+      "grad_norm": 0.03993430739998164,
+      "learning_rate": 2.425e-06,
+      "loss": 0.532,
+      "step": 198
+    },
+    {
+      "epoch": 1.0018921475875118,
+      "grad_norm": 0.14663213929873462,
+      "learning_rate": 2.4197246359249405e-06,
+      "loss": 0.7106,
+      "step": 199
+    },
+    {
+      "epoch": 1.0069378744875435,
+      "grad_norm": 0.03682337094632227,
+      "learning_rate": 2.4144333354271033e-06,
+      "loss": 0.4702,
+      "step": 200
+    },
+    {
+      "epoch": 1.011983601387575,
+      "grad_norm": 0.04044872570852846,
+      "learning_rate": 2.4091262465155386e-06,
+      "loss": 0.5213,
+      "step": 201
+    },
+    {
+      "epoch": 1.0170293282876064,
+      "grad_norm": 0.03956345299513896,
+      "learning_rate": 2.403803517640932e-06,
+      "loss": 0.488,
+      "step": 202
+    },
+    {
+      "epoch": 1.022075055187638,
+      "grad_norm": 0.035011481501724055,
+      "learning_rate": 2.398465297691452e-06,
+      "loss": 0.4754,
+      "step": 203
+    },
+    {
+      "epoch": 1.0271207820876695,
+      "grad_norm": 0.033861610990122235,
+      "learning_rate": 2.393111735988585e-06,
+      "loss": 0.4782,
+      "step": 204
+    },
+    {
+      "epoch": 1.032166508987701,
+      "grad_norm": 0.055350616536286666,
+      "learning_rate": 2.387742982282961e-06,
+      "loss": 0.479,
+      "step": 205
+    },
+    {
+      "epoch": 1.0372122358877325,
+      "grad_norm": 0.031693846556977066,
+      "learning_rate": 2.3823591867501623e-06,
+      "loss": 0.4708,
+      "step": 206
+    },
+    {
+      "epoch": 1.0422579627877642,
+      "grad_norm": 0.03527666796296507,
+      "learning_rate": 2.376960499986522e-06,
+      "loss": 0.504,
+      "step": 207
+    },
+    {
+      "epoch": 1.0473036896877956,
+      "grad_norm": 0.03114715236687362,
+      "learning_rate": 2.3715470730049154e-06,
+      "loss": 0.4656,
+      "step": 208
+    },
+    {
+      "epoch": 1.052349416587827,
+      "grad_norm": 0.03195304059581202,
+      "learning_rate": 2.3661190572305315e-06,
+      "loss": 0.5021,
+      "step": 209
+    },
+    {
+      "epoch": 1.0573951434878588,
+      "grad_norm": 0.041909938570619656,
+      "learning_rate": 2.3606766044966404e-06,
+      "loss": 0.4477,
+      "step": 210
+    },
+    {
+      "epoch": 1.0624408703878903,
+      "grad_norm": 0.031765017759599695,
+      "learning_rate": 2.355219867040344e-06,
+      "loss": 0.4852,
+      "step": 211
+    },
+    {
+      "epoch": 1.0674865972879217,
+      "grad_norm": 0.03226173748335202,
+      "learning_rate": 2.3497489974983195e-06,
+      "loss": 0.4499,
+      "step": 212
+    },
+    {
+      "epoch": 1.0725323241879534,
+      "grad_norm": 0.04089170994785027,
+      "learning_rate": 2.3442641489025476e-06,
+      "loss": 0.4763,
+      "step": 213
+    },
+    {
+      "epoch": 1.0775780510879849,
+      "grad_norm": 0.03266826231646906,
+      "learning_rate": 2.3387654746760346e-06,
+      "loss": 0.5058,
+      "step": 214
+    },
+    {
+      "epoch": 1.0826237779880163,
+      "grad_norm": 0.031198910926951966,
+      "learning_rate": 2.333253128628519e-06,
+      "loss": 0.4761,
+      "step": 215
+    },
+    {
+      "epoch": 1.087669504888048,
+      "grad_norm": 0.03390455032734163,
+      "learning_rate": 2.3277272649521696e-06,
+      "loss": 0.5087,
+      "step": 216
+    },
+    {
+      "epoch": 1.0927152317880795,
+      "grad_norm": 0.03890356772507247,
+      "learning_rate": 2.3221880382172716e-06,
+      "loss": 0.4581,
+      "step": 217
+    },
+    {
+      "epoch": 1.097760958688111,
+      "grad_norm": 0.03659037349548446,
+      "learning_rate": 2.3166356033679037e-06,
+      "loss": 0.4924,
+      "step": 218
+    },
+    {
+      "epoch": 1.1028066855881424,
+      "grad_norm": 0.03393150371468798,
+      "learning_rate": 2.3110701157176058e-06,
+      "loss": 0.467,
+      "step": 219
+    },
+    {
+      "epoch": 1.1078524124881741,
+      "grad_norm": 0.03457204743267538,
+      "learning_rate": 2.3054917309450305e-06,
+      "loss": 0.4769,
+      "step": 220
+    },
+    {
+      "epoch": 1.1128981393882056,
+      "grad_norm": 0.032520047837292926,
+      "learning_rate": 2.2999006050895913e-06,
+      "loss": 0.5045,
+      "step": 221
+    },
+    {
+      "epoch": 1.117943866288237,
+      "grad_norm": 0.031699959269331585,
+      "learning_rate": 2.2942968945470975e-06,
+      "loss": 0.4459,
+      "step": 222
+    },
+    {
+      "epoch": 1.1229895931882687,
+      "grad_norm": 0.03425055841117851,
+      "learning_rate": 2.28868075606538e-06,
+      "loss": 0.45,
+      "step": 223
+    },
+    {
+      "epoch": 1.1280353200883002,
+      "grad_norm": 0.031848100692100624,
+      "learning_rate": 2.2830523467399035e-06,
+      "loss": 0.483,
+      "step": 224
+    },
+    {
+      "epoch": 1.1330810469883317,
+      "grad_norm": 0.030558054743067897,
+      "learning_rate": 2.2774118240093768e-06,
+      "loss": 0.4711,
+      "step": 225
+    },
+    {
+      "epoch": 1.1381267738883634,
+      "grad_norm": 0.0348970127065318,
+      "learning_rate": 2.2717593456513453e-06,
+      "loss": 0.4469,
+      "step": 226
+    },
+    {
+      "epoch": 1.1431725007883948,
+      "grad_norm": 0.0374572663863973,
+      "learning_rate": 2.26609506977778e-06,
+      "loss": 0.4781,
+      "step": 227
+    },
+    {
+      "epoch": 1.1482182276884263,
+      "grad_norm": 0.03510434827876549,
+      "learning_rate": 2.2604191548306524e-06,
+      "loss": 0.4833,
+      "step": 228
+    },
+    {
+      "epoch": 1.153263954588458,
+      "grad_norm": 0.030172104427951332,
+      "learning_rate": 2.2547317595775065e-06,
+      "loss": 0.4599,
+      "step": 229
+    },
+    {
+      "epoch": 1.1583096814884895,
+      "grad_norm": 0.046734886663062365,
+      "learning_rate": 2.2490330431070117e-06,
+      "loss": 0.4527,
+      "step": 230
+    },
+    {
+      "epoch": 1.163355408388521,
+      "grad_norm": 0.03666142541656924,
+      "learning_rate": 2.243323164824519e-06,
+      "loss": 0.5086,
+      "step": 231
+    },
+    {
+      "epoch": 1.1684011352885526,
+      "grad_norm": 0.03333582987080111,
+      "learning_rate": 2.2376022844475983e-06,
+      "loss": 0.4892,
+      "step": 232
+    },
+    {
+      "epoch": 1.173446862188584,
+      "grad_norm": 0.044806971398086565,
+      "learning_rate": 2.2318705620015707e-06,
+      "loss": 0.5171,
+      "step": 233
+    },
+    {
+      "epoch": 1.1784925890886155,
+      "grad_norm": 0.02976391238091838,
+      "learning_rate": 2.226128157815035e-06,
+      "loss": 0.473,
+      "step": 234
+    },
+    {
+      "epoch": 1.1835383159886472,
+      "grad_norm": 0.032855191116779925,
+      "learning_rate": 2.2203752325153805e-06,
+      "loss": 0.4622,
+      "step": 235
+    },
+    {
+      "epoch": 1.1885840428886787,
+      "grad_norm": 0.030746957757418838,
+      "learning_rate": 2.214611947024294e-06,
+      "loss": 0.5058,
+      "step": 236
+    },
+    {
+      "epoch": 1.1936297697887102,
+      "grad_norm": 0.04025604127464795,
+      "learning_rate": 2.20883846255326e-06,
+      "loss": 0.4532,
+      "step": 237
+    },
+    {
+      "epoch": 1.1986754966887416,
+      "grad_norm": 0.038162603936688196,
+      "learning_rate": 2.2030549405990507e-06,
+      "loss": 0.4807,
+      "step": 238
+    },
+    {
+      "epoch": 1.2037212235887733,
+      "grad_norm": 0.032258710879740395,
+      "learning_rate": 2.1972615429392072e-06,
+      "loss": 0.4641,
+      "step": 239
+    },
+    {
+      "epoch": 1.2087669504888048,
+      "grad_norm": 0.04981629781222614,
+      "learning_rate": 2.1914584316275165e-06,
+      "loss": 0.5017,
+      "step": 240
+    },
+    {
+      "epoch": 1.2138126773888362,
+      "grad_norm": 0.04243199718669605,
+      "learning_rate": 2.1856457689894754e-06,
+      "loss": 0.4902,
+      "step": 241
+    },
+    {
+      "epoch": 1.218858404288868,
+      "grad_norm": 0.0342114934326818,
+      "learning_rate": 2.179823717617754e-06,
+      "loss": 0.5117,
+      "step": 242
+    },
+    {
+      "epoch": 1.2239041311888994,
+      "grad_norm": 0.035548749332123104,
+      "learning_rate": 2.1739924403676444e-06,
+      "loss": 0.4381,
+      "step": 243
+    },
+    {
+      "epoch": 1.2289498580889309,
+      "grad_norm": 0.034760487487630214,
+      "learning_rate": 2.168152100352506e-06,
+      "loss": 0.4591,
+      "step": 244
+    },
+    {
+      "epoch": 1.2339955849889626,
+      "grad_norm": 0.03546769169516817,
+      "learning_rate": 2.1623028609392048e-06,
+      "loss": 0.5399,
+      "step": 245
+    },
+    {
+      "epoch": 1.239041311888994,
+      "grad_norm": 0.030499056297799327,
+      "learning_rate": 2.1564448857435402e-06,
+      "loss": 0.4359,
+      "step": 246
+    },
+    {
+      "epoch": 1.2440870387890255,
+      "grad_norm": 0.0347599990737736,
+      "learning_rate": 2.1505783386256712e-06,
+      "loss": 0.4812,
+      "step": 247
+    },
+    {
+      "epoch": 1.249132765689057,
+      "grad_norm": 0.033702971243902105,
+      "learning_rate": 2.1447033836855322e-06,
+      "loss": 0.4722,
+      "step": 248
+    },
+    {
+      "epoch": 1.2541784925890886,
+      "grad_norm": 0.032222809178112814,
+      "learning_rate": 2.1388201852582413e-06,
+      "loss": 0.4685,
+      "step": 249
+    },
+    {
+      "epoch": 1.2592242194891201,
+      "grad_norm": 0.03251536305035892,
+      "learning_rate": 2.1329289079095053e-06,
+      "loss": 0.4863,
+      "step": 250
+    },
+    {
+      "epoch": 1.2642699463891516,
+      "grad_norm": 0.03032333505076748,
+      "learning_rate": 2.127029716431017e-06,
+      "loss": 0.4904,
+      "step": 251
+    },
+    {
+      "epoch": 1.2693156732891833,
+      "grad_norm": 0.03243078647811712,
+      "learning_rate": 2.1211227758358416e-06,
+      "loss": 0.4489,
+      "step": 252
+    },
+    {
+      "epoch": 1.2743614001892147,
+      "grad_norm": 0.029896600919276654,
+      "learning_rate": 2.115208251353806e-06,
+      "loss": 0.44,
+      "step": 253
+    },
+    {
+      "epoch": 1.2794071270892462,
+      "grad_norm": 0.03513886472785278,
+      "learning_rate": 2.109286308426875e-06,
+      "loss": 0.4469,
+      "step": 254
+    },
+    {
+      "epoch": 1.2844528539892779,
+      "grad_norm": 0.034551710763168,
+      "learning_rate": 2.103357112704522e-06,
+      "loss": 0.4679,
+      "step": 255
+    },
+    {
+      "epoch": 1.2894985808893094,
+      "grad_norm": 0.03318123641296534,
+      "learning_rate": 2.0974208300390965e-06,
+      "loss": 0.5459,
+      "step": 256
+    },
+    {
+      "epoch": 1.2945443077893408,
+      "grad_norm": 0.03692313739508695,
+      "learning_rate": 2.0914776264811856e-06,
+      "loss": 0.4515,
+      "step": 257
+    },
+    {
+      "epoch": 1.2995900346893725,
+      "grad_norm": 0.045176468474857956,
+      "learning_rate": 2.0855276682749695e-06,
+      "loss": 0.5145,
+      "step": 258
+    },
+    {
+      "epoch": 1.304635761589404,
+      "grad_norm": 0.031189748556156745,
+      "learning_rate": 2.0795711218535688e-06,
+      "loss": 0.4604,
+      "step": 259
+    },
+    {
+      "epoch": 1.3096814884894354,
+      "grad_norm": 0.03325438648076318,
+      "learning_rate": 2.0736081538343916e-06,
+      "loss": 0.4993,
+      "step": 260
+    },
+    {
+      "epoch": 1.3147272153894671,
+      "grad_norm": 0.031199262961620483,
+      "learning_rate": 2.0676389310144718e-06,
+      "loss": 0.4362,
+      "step": 261
+    },
+    {
+      "epoch": 1.3197729422894986,
+      "grad_norm": 0.031944131266326836,
+      "learning_rate": 2.0616636203658033e-06,
+      "loss": 0.4564,
+      "step": 262
+    },
+    {
+      "epoch": 1.32481866918953,
+      "grad_norm": 0.03473404208713477,
+      "learning_rate": 2.0556823890306702e-06,
+      "loss": 0.4812,
+      "step": 263
+    },
+    {
+      "epoch": 1.3298643960895618,
+      "grad_norm": 0.036841604651030695,
+      "learning_rate": 2.04969540431697e-06,
+      "loss": 0.473,
+      "step": 264
+    },
+    {
+      "epoch": 1.3349101229895932,
+      "grad_norm": 0.033301870334618816,
+      "learning_rate": 2.0437028336935354e-06,
+      "loss": 0.5129,
+      "step": 265
+    },
+    {
+      "epoch": 1.3399558498896247,
+      "grad_norm": 0.03157054955686288,
+      "learning_rate": 2.0377048447854483e-06,
+      "loss": 0.4497,
+      "step": 266
+    },
+    {
+      "epoch": 1.3450015767896564,
+      "grad_norm": 0.031056401843407105,
+      "learning_rate": 2.0317016053693527e-06,
+      "loss": 0.4971,
+      "step": 267
+    },
+    {
+      "epoch": 1.3500473036896878,
+      "grad_norm": 0.031039315725744067,
+      "learning_rate": 2.0256932833687594e-06,
+      "loss": 0.4729,
+      "step": 268
+    },
+    {
+      "epoch": 1.3550930305897193,
+      "grad_norm": 0.030343085739004155,
+      "learning_rate": 2.01968004684935e-06,
+      "loss": 0.4571,
+      "step": 269
+    },
+    {
+      "epoch": 1.360138757489751,
+      "grad_norm": 0.03216221791171112,
+      "learning_rate": 2.013662064014278e-06,
+      "loss": 0.4892,
+      "step": 270
+    },
+    {
+      "epoch": 1.3651844843897825,
+      "grad_norm": 0.030997748793028454,
+      "learning_rate": 2.0076395031994588e-06,
+      "loss": 0.4853,
+      "step": 271
+    },
+    {
+      "epoch": 1.370230211289814,
+      "grad_norm": 0.03051181164140716,
+      "learning_rate": 2.0016125328688645e-06,
+      "loss": 0.4712,
+      "step": 272
+    },
+    {
+      "epoch": 1.3752759381898454,
+      "grad_norm": 0.033819677864526616,
+      "learning_rate": 1.995581321609812e-06,
+      "loss": 0.4936,
+      "step": 273
+    },
+    {
+      "epoch": 1.380321665089877,
+      "grad_norm": 0.03283516748621975,
+      "learning_rate": 1.9895460381282443e-06,
+      "loss": 0.4671,
+      "step": 274
+    },
+    {
+      "epoch": 1.3853673919899085,
+      "grad_norm": 0.0360523107800218,
+      "learning_rate": 1.983506851244015e-06,
+      "loss": 0.4313,
+      "step": 275
+    },
+    {
+      "epoch": 1.39041311888994,
+      "grad_norm": 0.033433849463724505,
+      "learning_rate": 1.9774639298861625e-06,
+      "loss": 0.4823,
+      "step": 276
+    },
+    {
+      "epoch": 1.3954588457899715,
+      "grad_norm": 0.03465852287263857,
+      "learning_rate": 1.9714174430881886e-06,
+      "loss": 0.4619,
+      "step": 277
+    },
+    {
+      "epoch": 1.4005045726900032,
+      "grad_norm": 0.036080701809884305,
+      "learning_rate": 1.9653675599833256e-06,
+      "loss": 0.4878,
+      "step": 278
+    },
+    {
+      "epoch": 1.4055502995900346,
+      "grad_norm": 0.030820007521684834,
+      "learning_rate": 1.95931444979981e-06,
+      "loss": 0.4698,
+      "step": 279
+    },
+    {
+      "epoch": 1.410596026490066,
+      "grad_norm": 0.04113205730752187,
+      "learning_rate": 1.9532582818561455e-06,
+      "loss": 0.4728,
+      "step": 280
+    },
+    {
+      "epoch": 1.4156417533900978,
+      "grad_norm": 0.04806829892661083,
+      "learning_rate": 1.9471992255563675e-06,
+      "loss": 0.4906,
+      "step": 281
+    },
+    {
+      "epoch": 1.4206874802901293,
+      "grad_norm": 0.03503516935353285,
+      "learning_rate": 1.941137450385307e-06,
+      "loss": 0.4356,
+      "step": 282
+    },
+    {
+      "epoch": 1.4257332071901607,
+      "grad_norm": 0.030864677107393407,
+      "learning_rate": 1.935073125903845e-06,
+      "loss": 0.4418,
+      "step": 283
+    },
+    {
+      "epoch": 1.4307789340901924,
+      "grad_norm": 0.031871510937479065,
+      "learning_rate": 1.929006421744173e-06,
+      "loss": 0.4897,
+      "step": 284
+    },
+    {
+      "epoch": 1.4358246609902239,
+      "grad_norm": 0.040994048526582366,
+      "learning_rate": 1.9229375076050492e-06,
+      "loss": 0.4109,
+      "step": 285
+    },
+    {
+      "epoch": 1.4408703878902553,
+      "grad_norm": 0.04141601982962323,
+      "learning_rate": 1.9168665532470472e-06,
+      "loss": 0.466,
+      "step": 286
+    },
+    {
+      "epoch": 1.445916114790287,
+      "grad_norm": 0.03049794074820137,
+      "learning_rate": 1.910793728487811e-06,
+      "loss": 0.4316,
+      "step": 287
+    },
+    {
+      "epoch": 1.4509618416903185,
+      "grad_norm": 0.031744519891624884,
+      "learning_rate": 1.904719203197304e-06,
+      "loss": 0.479,
+      "step": 288
+    },
+    {
+      "epoch": 1.45600756859035,
+      "grad_norm": 0.029790700550052368,
+      "learning_rate": 1.8986431472930554e-06,
+      "loss": 0.4379,
+      "step": 289
+    },
+    {
+      "epoch": 1.4610532954903817,
+      "grad_norm": 0.029483006697427174,
+      "learning_rate": 1.8925657307354117e-06,
+      "loss": 0.4747,
+      "step": 290
+    },
+    {
+      "epoch": 1.4660990223904131,
+      "grad_norm": 0.0324936518347741,
+      "learning_rate": 1.886487123522778e-06,
+      "loss": 0.4777,
+      "step": 291
+    },
+    {
+      "epoch": 1.4711447492904446,
+      "grad_norm": 0.033649363452982924,
+      "learning_rate": 1.8804074956868647e-06,
+      "loss": 0.4891,
+      "step": 292
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 0.029439747594352722,
+      "learning_rate": 1.874327017287931e-06,
+      "loss": 0.4393,
+      "step": 293
+    },
+    {
+      "epoch": 1.4812362030905077,
+      "grad_norm": 0.03233846484977382,
+      "learning_rate": 1.8682458584100292e-06,
+      "loss": 0.4841,
+      "step": 294
+    },
+    {
+      "epoch": 1.4862819299905392,
+      "grad_norm": 0.03555793172558539,
+      "learning_rate": 1.8621641891562458e-06,
+      "loss": 0.4718,
+      "step": 295
+    },
+    {
+      "epoch": 1.491327656890571,
+      "grad_norm": 0.03769744501026416,
+      "learning_rate": 1.8560821796439423e-06,
+      "loss": 0.457,
+      "step": 296
+    },
+    {
+      "epoch": 1.4963733837906024,
+      "grad_norm": 0.031502776602075996,
+      "learning_rate": 1.85e-06,
+      "loss": 0.4982,
+      "step": 297
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 594,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 99,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1231975398506496.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0968b7e60c915735f9ede99196db9a2d6628333f8558d1383b92bb4d4706f8
+size 8376

150/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)