Training in progress, step 250, checkpoint

checkpoint-250/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-250/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "NewEden/Hamanasu-32B-V1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-250/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "transformers_version": "4.49.0"
+}

checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8715ab96fb2757c9a9161ad69a3ad339b9ff42d41083018d6568a4eadd0495d4
+size 24702839719

checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d44480a08a85b5bbf0935c2af4917ad41fd1cee1d9225de9228afffaaf66ce
+size 24702839719

checkpoint-250/global_step250/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0432a1725b6883464cb192549aae686cc66ee60b1497be4e200a79ed44feb0
+size 24702839719

checkpoint-250/global_step250/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fda7a7b657de4b6d7778b9d822b7bcec54844d7b31b0ed8d9a188beeefd5b79
+size 24702839719

checkpoint-250/global_step250/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78046d7bcaa8ad96261364f0742f2cccf82b49b5659d36c9da826df3fc4e6d3d
+size 24702839719

checkpoint-250/global_step250/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50469972ea9985065cb1d3452cf5bd069cecbe92864487e5810451a7cfafaf01
+size 24702839719

checkpoint-250/global_step250/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c77fa6a95832d666020a4ac65f01ee2e202fcc41a6a80010018f038bb49a9f3
+size 24702839719

checkpoint-250/global_step250/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0910a2f155baf9e25d9a0be04e3c2dd3e835027f04bd2c181027015b97f23121
+size 24702839719

checkpoint-250/global_step250/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6030d863ea1691a486f4962f35d7ff4af384bc1ab420021060f9f7da2290bacd
+size 381701

checkpoint-250/global_step250/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff3e3d2cb9dc630bdf8c21c4430b083d902f0da4c2e70ac728093a7e88c91b3
+size 381701

checkpoint-250/global_step250/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1136af498588290e3c3c78cb0f7a7f29be260d69375b0c9a0b879b33458ab859
+size 381701

checkpoint-250/global_step250/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a0a80d18064bdf852022c4795a19c5f201791a4f3188e2f6ee0d8d98519e8f
+size 381701

checkpoint-250/global_step250/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:899daf1106c989340e583ac93a79bdf208e508ef59dd9c552f72526f9410f9de
+size 381701

checkpoint-250/global_step250/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0cf44053d52638024bba882c1c53865ab36436e3db6d3775d2ef5333e5ea86
+size 381701

checkpoint-250/global_step250/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a568504a7f3a7a3e6dced72d63a6d93bd1b6015bfdc542350ff091f0cded0926
+size 381701

checkpoint-250/global_step250/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d909f38dc3ea5b0fd6133a8448e2979eb98de83931b6bcae1979cae2f95e14e
+size 381701

checkpoint-250/latest

@@ -0,0 +1 @@
+global_step250

checkpoint-250/model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e52936eb974afcc7f4dc713fbbd26e23f3a13055677127a1464f340cb918c6
+size 4891730992

checkpoint-250/model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567b9bab0686acf0bd24bd261f1e2e6a23fdc21bbf418bbe965fb899d8e4ae97
+size 4876059352

checkpoint-250/model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad315f9c8b5432f4f08080d640a23d46aa146e000c2120a513dd7855dc1e4571
+size 4876059384

checkpoint-250/model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d94d326f4d57e36bc711891b96455655112a1985ef11f292027802e255f5538
+size 4876059416

checkpoint-250/model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dbb12573bcec5558da125128986961852ae75bd288f7f653931c75ea519e742
+size 4876059416

checkpoint-250/model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f734096cfc3fa801c354b2c1b9c86f22cf634e45dfa506b7a4eb85725c8856e
+size 4876059416

checkpoint-250/model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6450520686a875a9a0f0e6976bb3fdaaa1afa737128b10c5d44e7020ec21d487
+size 4876059416

checkpoint-250/model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56785b9e8f70e44ef2793081312fdbcc351faac720f28c15c6408b67c73591f3
+size 4876059416

checkpoint-250/model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090d277833e85f5c35fc18e1cacbc7f4f99a2e1cb63c0380b7edee5c4e79bb9d
+size 4876059416

checkpoint-250/model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589ef42fa4cd1594054d7b7bad34d227070dcb5ce93c139bdfbe4c0446109e80
+size 4876059416

checkpoint-250/model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27907b7cde9bea76908f1543005ff7a083f5352b88a6e536e382a149bcd8e6e
+size 4876059416

checkpoint-250/model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b66228c56e0eec755528b88b8b82065e46b54c41a2b08d291cee1617097c7e9
+size 4876059416

checkpoint-250/model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ce5d7d3bf30e6df4b6c0d7822ac5a1c8f05f2242c9624a1c6f91123bf68b84
+size 4876059416

checkpoint-250/model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ffd4f268b1ffc3047ce0114758d06b855288aa68d60e9f387d0f93191ebc17
+size 2123397800

checkpoint-250/model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

checkpoint-250/rng_state_0.pth

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

checkpoint-250/rng_state_1.pth

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

checkpoint-250/rng_state_2.pth

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

checkpoint-250/rng_state_3.pth

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

checkpoint-250/rng_state_4.pth

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

checkpoint-250/rng_state_5.pth

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

checkpoint-250/rng_state_6.pth

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

checkpoint-250/rng_state_7.pth

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

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a51e6dad7e652ddb9548cd3fbf1e1a7ae8a859f32ba1a2a26d2780ed8b3c6c
+size 1064

checkpoint-250/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-250/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-250/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- '' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n  {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" and not message.tool_calls %}\n        {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-250/trainer_state.json

@@ -0,0 +1,1783 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004,
+      "grad_norm": 2.7120276745865266,
+      "learning_rate": 1.2500000000000002e-07,
+      "loss": 0.9478,
+      "step": 1
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 2.5535110233770237,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 0.962,
+      "step": 2
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 2.6421564999361533,
+      "learning_rate": 3.75e-07,
+      "loss": 0.9483,
+      "step": 3
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 2.5842713407482596,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.9484,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.5281267639976615,
+      "learning_rate": 6.25e-07,
+      "loss": 0.9512,
+      "step": 5
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 2.55003561639048,
+      "learning_rate": 7.5e-07,
+      "loss": 0.9185,
+      "step": 6
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 2.5014092783190947,
+      "learning_rate": 8.75e-07,
+      "loss": 0.9411,
+      "step": 7
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 2.5247715994428046,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.9474,
+      "step": 8
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 2.564090844776098,
+      "learning_rate": 1.125e-06,
+      "loss": 0.9246,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.5258707026382154,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9078,
+      "step": 10
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 2.5471156175078464,
+      "learning_rate": 1.3750000000000002e-06,
+      "loss": 0.9134,
+      "step": 11
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 2.7125301372042467,
+      "learning_rate": 1.5e-06,
+      "loss": 0.8776,
+      "step": 12
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 2.150392048325219,
+      "learning_rate": 1.6250000000000001e-06,
+      "loss": 0.8549,
+      "step": 13
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 1.8184980673856375,
+      "learning_rate": 1.75e-06,
+      "loss": 0.8169,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.7529184087805771,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 0.7975,
+      "step": 15
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 1.7474840928555682,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.8204,
+      "step": 16
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 1.522251241150409,
+      "learning_rate": 2.125e-06,
+      "loss": 0.8301,
+      "step": 17
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.9782588646220091,
+      "learning_rate": 2.25e-06,
+      "loss": 0.7839,
+      "step": 18
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.975162832649703,
+      "learning_rate": 2.375e-06,
+      "loss": 0.7876,
+      "step": 19
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.8952616849532462,
+      "learning_rate": 2.5e-06,
+      "loss": 0.7589,
+      "step": 20
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.8469187411478404,
+      "learning_rate": 2.6250000000000003e-06,
+      "loss": 0.7567,
+      "step": 21
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.7683035597272257,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.7598,
+      "step": 22
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.6779719620181055,
+      "learning_rate": 2.875e-06,
+      "loss": 0.7431,
+      "step": 23
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.5998651036445499,
+      "learning_rate": 3e-06,
+      "loss": 0.7348,
+      "step": 24
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.6798779251188986,
+      "learning_rate": 3.125e-06,
+      "loss": 0.7271,
+      "step": 25
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.7459028436934305,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.7011,
+      "step": 26
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.7661666147630528,
+      "learning_rate": 3.3750000000000003e-06,
+      "loss": 0.7209,
+      "step": 27
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.7109730987249342,
+      "learning_rate": 3.5e-06,
+      "loss": 0.7118,
+      "step": 28
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.6778217985942258,
+      "learning_rate": 3.625e-06,
+      "loss": 0.7295,
+      "step": 29
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.6073429084137083,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.7114,
+      "step": 30
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 0.5325413632521706,
+      "learning_rate": 3.875e-06,
+      "loss": 0.7117,
+      "step": 31
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.5170445125401208,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.7132,
+      "step": 32
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 0.47459002896590347,
+      "learning_rate": 4.125e-06,
+      "loss": 0.6913,
+      "step": 33
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.46611890152884594,
+      "learning_rate": 4.25e-06,
+      "loss": 0.6893,
+      "step": 34
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5282002224942279,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.7059,
+      "step": 35
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.516098581069478,
+      "learning_rate": 4.5e-06,
+      "loss": 0.7068,
+      "step": 36
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 0.4946613953020982,
+      "learning_rate": 4.625000000000001e-06,
+      "loss": 0.6854,
+      "step": 37
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.45539519616935026,
+      "learning_rate": 4.75e-06,
+      "loss": 0.689,
+      "step": 38
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 0.43098619176364883,
+      "learning_rate": 4.875e-06,
+      "loss": 0.6904,
+      "step": 39
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.42693567901762375,
+      "learning_rate": 5e-06,
+      "loss": 0.6713,
+      "step": 40
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 0.42916236211888303,
+      "learning_rate": 4.999941696797974e-06,
+      "loss": 0.6929,
+      "step": 41
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.46320958381108696,
+      "learning_rate": 4.9997667899113055e-06,
+      "loss": 0.6601,
+      "step": 42
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 0.4650598350234117,
+      "learning_rate": 4.9994752874981e-06,
+      "loss": 0.6627,
+      "step": 43
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4899967026584299,
+      "learning_rate": 4.999067203154777e-06,
+      "loss": 0.6583,
+      "step": 44
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.4562804538758281,
+      "learning_rate": 4.998542555915435e-06,
+      "loss": 0.6712,
+      "step": 45
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.36547047335003885,
+      "learning_rate": 4.997901370250966e-06,
+      "loss": 0.6495,
+      "step": 46
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 0.37624066260466155,
+      "learning_rate": 4.997143676067913e-06,
+      "loss": 0.6703,
+      "step": 47
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.36653954523845933,
+      "learning_rate": 4.99626950870707e-06,
+      "loss": 0.6781,
+      "step": 48
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 0.3477765639450634,
+      "learning_rate": 4.995278908941845e-06,
+      "loss": 0.6745,
+      "step": 49
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.3342296714847872,
+      "learning_rate": 4.994171922976349e-06,
+      "loss": 0.6771,
+      "step": 50
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 0.37958792690250714,
+      "learning_rate": 4.9929486024432405e-06,
+      "loss": 0.6546,
+      "step": 51
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.40870653964939113,
+      "learning_rate": 4.991609004401324e-06,
+      "loss": 0.6528,
+      "step": 52
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 0.364192633459814,
+      "learning_rate": 4.990153191332885e-06,
+      "loss": 0.6458,
+      "step": 53
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.30668416089546924,
+      "learning_rate": 4.988581231140772e-06,
+      "loss": 0.672,
+      "step": 54
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.33255921507240616,
+      "learning_rate": 4.986893197145238e-06,
+      "loss": 0.6575,
+      "step": 55
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.312428536241603,
+      "learning_rate": 4.985089168080509e-06,
+      "loss": 0.6629,
+      "step": 56
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.2961748326875195,
+      "learning_rate": 4.983169228091125e-06,
+      "loss": 0.6514,
+      "step": 57
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.30513153025857964,
+      "learning_rate": 4.981133466728004e-06,
+      "loss": 0.6547,
+      "step": 58
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 0.3274000044829569,
+      "learning_rate": 4.978981978944271e-06,
+      "loss": 0.6514,
+      "step": 59
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.3083977406610579,
+      "learning_rate": 4.976714865090827e-06,
+      "loss": 0.6422,
+      "step": 60
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 0.3052292638265554,
+      "learning_rate": 4.97433223091167e-06,
+      "loss": 0.6355,
+      "step": 61
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.2959593176715387,
+      "learning_rate": 4.971834187538963e-06,
+      "loss": 0.6551,
+      "step": 62
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 0.29042322618949995,
+      "learning_rate": 4.9692208514878445e-06,
+      "loss": 0.6581,
+      "step": 63
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.3149031676109748,
+      "learning_rate": 4.966492344651006e-06,
+      "loss": 0.6594,
+      "step": 64
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.2874450280533471,
+      "learning_rate": 4.963648794292992e-06,
+      "loss": 0.6488,
+      "step": 65
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.27325192501172824,
+      "learning_rate": 4.960690333044279e-06,
+      "loss": 0.6351,
+      "step": 66
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 0.2817944445002008,
+      "learning_rate": 4.957617098895076e-06,
+      "loss": 0.6265,
+      "step": 67
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.281980621240097,
+      "learning_rate": 4.954429235188897e-06,
+      "loss": 0.6432,
+      "step": 68
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 0.2962526841715817,
+      "learning_rate": 4.951126890615871e-06,
+      "loss": 0.6354,
+      "step": 69
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.28005347365677186,
+      "learning_rate": 4.947710219205808e-06,
+      "loss": 0.6548,
+      "step": 70
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 0.26960325063378,
+      "learning_rate": 4.944179380321015e-06,
+      "loss": 0.6125,
+      "step": 71
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.2848666105192882,
+      "learning_rate": 4.940534538648862e-06,
+      "loss": 0.6078,
+      "step": 72
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 0.276353304899713,
+      "learning_rate": 4.936775864194101e-06,
+      "loss": 0.6524,
+      "step": 73
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.27790715839174,
+      "learning_rate": 4.932903532270939e-06,
+      "loss": 0.6275,
+      "step": 74
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2636499704034946,
+      "learning_rate": 4.928917723494854e-06,
+      "loss": 0.6422,
+      "step": 75
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.28133008746598603,
+      "learning_rate": 4.924818623774178e-06,
+      "loss": 0.6355,
+      "step": 76
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 0.2779410264901997,
+      "learning_rate": 4.920606424301424e-06,
+      "loss": 0.6408,
+      "step": 77
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.2897057665750394,
+      "learning_rate": 4.916281321544362e-06,
+      "loss": 0.6402,
+      "step": 78
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 0.2761996704216673,
+      "learning_rate": 4.911843517236867e-06,
+      "loss": 0.653,
+      "step": 79
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.29413202875425243,
+      "learning_rate": 4.907293218369499e-06,
+      "loss": 0.6298,
+      "step": 80
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 0.2861680279307969,
+      "learning_rate": 4.9026306371798526e-06,
+      "loss": 0.6553,
+      "step": 81
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.2848851913581759,
+      "learning_rate": 4.897855991142658e-06,
+      "loss": 0.6076,
+      "step": 82
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 0.2687848093353044,
+      "learning_rate": 4.892969502959639e-06,
+      "loss": 0.6311,
+      "step": 83
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.27061397240144314,
+      "learning_rate": 4.8879714005491205e-06,
+      "loss": 0.6148,
+      "step": 84
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.2663532374960906,
+      "learning_rate": 4.882861917035403e-06,
+      "loss": 0.6412,
+      "step": 85
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.27752950332016424,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 0.642,
+      "step": 86
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 0.2772792789989426,
+      "learning_rate": 4.87230976515995e-06,
+      "loss": 0.6184,
+      "step": 87
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.29699617925202587,
+      "learning_rate": 4.8668675889776095e-06,
+      "loss": 0.6275,
+      "step": 88
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 0.2736517750983177,
+      "learning_rate": 4.861315016027902e-06,
+      "loss": 0.6347,
+      "step": 89
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.2871346395772671,
+      "learning_rate": 4.855652305297052e-06,
+      "loss": 0.6132,
+      "step": 90
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 0.27131438304958966,
+      "learning_rate": 4.849879720908394e-06,
+      "loss": 0.6026,
+      "step": 91
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.2701400539855458,
+      "learning_rate": 4.843997532110051e-06,
+      "loss": 0.6385,
+      "step": 92
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 0.2870430498497826,
+      "learning_rate": 4.8380060132623776e-06,
+      "loss": 0.624,
+      "step": 93
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.2889305346509075,
+      "learning_rate": 4.83190544382516e-06,
+      "loss": 0.6375,
+      "step": 94
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.2832554152572974,
+      "learning_rate": 4.825696108344583e-06,
+      "loss": 0.6348,
+      "step": 95
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.282963454209734,
+      "learning_rate": 4.819378296439962e-06,
+      "loss": 0.6425,
+      "step": 96
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 0.28136329883499284,
+      "learning_rate": 4.812952302790226e-06,
+      "loss": 0.6238,
+      "step": 97
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.2751896445755537,
+      "learning_rate": 4.80641842712018e-06,
+      "loss": 0.6453,
+      "step": 98
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 0.2802941094985609,
+      "learning_rate": 4.799776974186523e-06,
+      "loss": 0.6362,
+      "step": 99
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2816828378634338,
+      "learning_rate": 4.793028253763633e-06,
+      "loss": 0.6394,
+      "step": 100
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 0.28942806582562414,
+      "learning_rate": 4.786172580629118e-06,
+      "loss": 0.6106,
+      "step": 101
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.28396225609673553,
+      "learning_rate": 4.7792102745491345e-06,
+      "loss": 0.6302,
+      "step": 102
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 0.269131748983874,
+      "learning_rate": 4.772141660263472e-06,
+      "loss": 0.6247,
+      "step": 103
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.28932510717249166,
+      "learning_rate": 4.764967067470409e-06,
+      "loss": 0.6201,
+      "step": 104
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2734040302258933,
+      "learning_rate": 4.757686830811332e-06,
+      "loss": 0.6092,
+      "step": 105
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.28628481564556507,
+      "learning_rate": 4.750301289855128e-06,
+      "loss": 0.6284,
+      "step": 106
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 0.30932729909286755,
+      "learning_rate": 4.742810789082345e-06,
+      "loss": 0.6332,
+      "step": 107
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.2707515621211506,
+      "learning_rate": 4.735215677869129e-06,
+      "loss": 0.6107,
+      "step": 108
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 0.29859925040242785,
+      "learning_rate": 4.72751631047092e-06,
+      "loss": 0.6477,
+      "step": 109
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.2974079849667466,
+      "learning_rate": 4.7197130460059385e-06,
+      "loss": 0.632,
+      "step": 110
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 0.28109309454092835,
+      "learning_rate": 4.711806248438428e-06,
+      "loss": 0.6308,
+      "step": 111
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.287627270908265,
+      "learning_rate": 4.7037962865616795e-06,
+      "loss": 0.6322,
+      "step": 112
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 0.2859506113795605,
+      "learning_rate": 4.695683533980835e-06,
+      "loss": 0.6196,
+      "step": 113
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.27768505471724575,
+      "learning_rate": 4.687468369095457e-06,
+      "loss": 0.6107,
+      "step": 114
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.2985912133376052,
+      "learning_rate": 4.679151175081879e-06,
+      "loss": 0.6316,
+      "step": 115
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.27790254502289174,
+      "learning_rate": 4.6707323398753346e-06,
+      "loss": 0.6194,
+      "step": 116
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 0.2770496916475714,
+      "learning_rate": 4.662212256151865e-06,
+      "loss": 0.5938,
+      "step": 117
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.2750067208531331,
+      "learning_rate": 4.6535913213100005e-06,
+      "loss": 0.6125,
+      "step": 118
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 0.2640533408637943,
+      "learning_rate": 4.644869937452224e-06,
+      "loss": 0.6245,
+      "step": 119
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.27591929390872805,
+      "learning_rate": 4.636048511366222e-06,
+      "loss": 0.6186,
+      "step": 120
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 0.29643778935625803,
+      "learning_rate": 4.627127454505902e-06,
+      "loss": 0.6086,
+      "step": 121
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.28076149524670235,
+      "learning_rate": 4.618107182972209e-06,
+      "loss": 0.6158,
+      "step": 122
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 0.28214439623978305,
+      "learning_rate": 4.6089881174937146e-06,
+      "loss": 0.6299,
+      "step": 123
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.2885430172419291,
+      "learning_rate": 4.599770683406992e-06,
+      "loss": 0.6367,
+      "step": 124
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.28978271139767015,
+      "learning_rate": 4.590455310636778e-06,
+      "loss": 0.6248,
+      "step": 125
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.2763777911865909,
+      "learning_rate": 4.58104243367592e-06,
+      "loss": 0.6235,
+      "step": 126
+    },
+    {
+      "epoch": 0.508,
+      "grad_norm": 0.2788581607213461,
+      "learning_rate": 4.571532491565115e-06,
+      "loss": 0.6201,
+      "step": 127
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.28522419436506885,
+      "learning_rate": 4.561925927872421e-06,
+      "loss": 0.6287,
+      "step": 128
+    },
+    {
+      "epoch": 0.516,
+      "grad_norm": 0.2759422238312871,
+      "learning_rate": 4.55222319067258e-06,
+      "loss": 0.6105,
+      "step": 129
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.271521828303117,
+      "learning_rate": 4.542424732526105e-06,
+      "loss": 0.6004,
+      "step": 130
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 0.2832768486502443,
+      "learning_rate": 4.532531010458188e-06,
+      "loss": 0.6438,
+      "step": 131
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.28545986352466657,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.6147,
+      "step": 132
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 0.2843650568512383,
+      "learning_rate": 4.512459624854017e-06,
+      "loss": 0.6347,
+      "step": 133
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.2758779923686556,
+      "learning_rate": 4.5022828974986044e-06,
+      "loss": 0.6111,
+      "step": 134
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.28471240078326554,
+      "learning_rate": 4.4920127785397615e-06,
+      "loss": 0.6161,
+      "step": 135
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.27215538114487603,
+      "learning_rate": 4.481649747002146e-06,
+      "loss": 0.6019,
+      "step": 136
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 0.27161590017753495,
+      "learning_rate": 4.471194286244094e-06,
+      "loss": 0.6229,
+      "step": 137
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.2786884282741861,
+      "learning_rate": 4.460646883935079e-06,
+      "loss": 0.6217,
+      "step": 138
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 0.29095908793086706,
+      "learning_rate": 4.4500080320329615e-06,
+      "loss": 0.6212,
+      "step": 139
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2797512942233689,
+      "learning_rate": 4.43927822676105e-06,
+      "loss": 0.6183,
+      "step": 140
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 0.2701904530059608,
+      "learning_rate": 4.428457968584945e-06,
+      "loss": 0.6067,
+      "step": 141
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.2924071263588622,
+      "learning_rate": 4.417547762189207e-06,
+      "loss": 0.6167,
+      "step": 142
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 0.2684300131690406,
+      "learning_rate": 4.40654811645381e-06,
+      "loss": 0.6185,
+      "step": 143
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.2774759359262972,
+      "learning_rate": 4.395459544430407e-06,
+      "loss": 0.602,
+      "step": 144
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.2808643430953345,
+      "learning_rate": 4.384282563318403e-06,
+      "loss": 0.598,
+      "step": 145
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.27015365579319356,
+      "learning_rate": 4.373017694440828e-06,
+      "loss": 0.5857,
+      "step": 146
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 0.2856861787094523,
+      "learning_rate": 4.361665463220023e-06,
+      "loss": 0.6206,
+      "step": 147
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.28199517014381215,
+      "learning_rate": 4.35022639915313e-06,
+      "loss": 0.6094,
+      "step": 148
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 0.27010314199532126,
+      "learning_rate": 4.338701035787403e-06,
+      "loss": 0.5947,
+      "step": 149
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2601892508343049,
+      "learning_rate": 4.32708991069531e-06,
+      "loss": 0.5871,
+      "step": 150
+    },
+    {
+      "epoch": 0.604,
+      "grad_norm": 0.27825064672033506,
+      "learning_rate": 4.315393565449472e-06,
+      "loss": 0.6093,
+      "step": 151
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.27958608277896724,
+      "learning_rate": 4.30361254559739e-06,
+      "loss": 0.5951,
+      "step": 152
+    },
+    {
+      "epoch": 0.612,
+      "grad_norm": 0.2758779818206466,
+      "learning_rate": 4.291747400636009e-06,
+      "loss": 0.6062,
+      "step": 153
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.29572303953208817,
+      "learning_rate": 4.279798683986084e-06,
+      "loss": 0.605,
+      "step": 154
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.28194612739384267,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.6078,
+      "step": 155
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.28615376291544004,
+      "learning_rate": 4.255652768767619e-06,
+      "loss": 0.6319,
+      "step": 156
+    },
+    {
+      "epoch": 0.628,
+      "grad_norm": 0.26959219285273633,
+      "learning_rate": 4.243456696426415e-06,
+      "loss": 0.5968,
+      "step": 157
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.27878753771339543,
+      "learning_rate": 4.2311793047988145e-06,
+      "loss": 0.6214,
+      "step": 158
+    },
+    {
+      "epoch": 0.636,
+      "grad_norm": 0.2779844282953486,
+      "learning_rate": 4.218821166533813e-06,
+      "loss": 0.5964,
+      "step": 159
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2767287929857217,
+      "learning_rate": 4.206382858046636e-06,
+      "loss": 0.6187,
+      "step": 160
+    },
+    {
+      "epoch": 0.644,
+      "grad_norm": 0.2652936251998452,
+      "learning_rate": 4.193864959491853e-06,
+      "loss": 0.5897,
+      "step": 161
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.26227694980471933,
+      "learning_rate": 4.181268054736319e-06,
+      "loss": 0.6107,
+      "step": 162
+    },
+    {
+      "epoch": 0.652,
+      "grad_norm": 0.2690441499487734,
+      "learning_rate": 4.16859273133194e-06,
+      "loss": 0.6012,
+      "step": 163
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.26934906424793176,
+      "learning_rate": 4.15583958048827e-06,
+      "loss": 0.6086,
+      "step": 164
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.2727839454931186,
+      "learning_rate": 4.143009197044932e-06,
+      "loss": 0.6156,
+      "step": 165
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.2767715664709689,
+      "learning_rate": 4.130102179443877e-06,
+      "loss": 0.607,
+      "step": 166
+    },
+    {
+      "epoch": 0.668,
+      "grad_norm": 0.27462389864805775,
+      "learning_rate": 4.117119129701468e-06,
+      "loss": 0.598,
+      "step": 167
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.28124958800487015,
+      "learning_rate": 4.104060653380403e-06,
+      "loss": 0.6174,
+      "step": 168
+    },
+    {
+      "epoch": 0.676,
+      "grad_norm": 0.26867080247614167,
+      "learning_rate": 4.090927359561469e-06,
+      "loss": 0.6222,
+      "step": 169
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.27329020109654967,
+      "learning_rate": 4.077719860815132e-06,
+      "loss": 0.6174,
+      "step": 170
+    },
+    {
+      "epoch": 0.684,
+      "grad_norm": 0.2598239429892548,
+      "learning_rate": 4.064438773172966e-06,
+      "loss": 0.5949,
+      "step": 171
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.26610910407219807,
+      "learning_rate": 4.051084716098921e-06,
+      "loss": 0.5876,
+      "step": 172
+    },
+    {
+      "epoch": 0.692,
+      "grad_norm": 0.28832248653224085,
+      "learning_rate": 4.037658312460424e-06,
+      "loss": 0.6038,
+      "step": 173
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.27995126745782395,
+      "learning_rate": 4.024160188499337e-06,
+      "loss": 0.6024,
+      "step": 174
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.2708024464743442,
+      "learning_rate": 4.010590973802737e-06,
+      "loss": 0.6166,
+      "step": 175
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.27379773644645394,
+      "learning_rate": 3.996951301273556e-06,
+      "loss": 0.6172,
+      "step": 176
+    },
+    {
+      "epoch": 0.708,
+      "grad_norm": 0.2704403624062539,
+      "learning_rate": 3.983241807101064e-06,
+      "loss": 0.5848,
+      "step": 177
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.26367325554187204,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 0.6084,
+      "step": 178
+    },
+    {
+      "epoch": 0.716,
+      "grad_norm": 0.2714449492216179,
+      "learning_rate": 3.955615914836678e-06,
+      "loss": 0.6067,
+      "step": 179
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.27396192782433526,
+      "learning_rate": 3.941700805287169e-06,
+      "loss": 0.6049,
+      "step": 180
+    },
+    {
+      "epoch": 0.724,
+      "grad_norm": 0.2712108680127688,
+      "learning_rate": 3.927718451119009e-06,
+      "loss": 0.5981,
+      "step": 181
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.27016877733602884,
+      "learning_rate": 3.913669504505015e-06,
+      "loss": 0.6148,
+      "step": 182
+    },
+    {
+      "epoch": 0.732,
+      "grad_norm": 0.2986908827790219,
+      "learning_rate": 3.8995546207240455e-06,
+      "loss": 0.6293,
+      "step": 183
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.27281610268420575,
+      "learning_rate": 3.8853744581304376e-06,
+      "loss": 0.5937,
+      "step": 184
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.28387181164952147,
+      "learning_rate": 3.871129678123297e-06,
+      "loss": 0.6098,
+      "step": 185
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.2740312224605285,
+      "learning_rate": 3.856820945115655e-06,
+      "loss": 0.6078,
+      "step": 186
+    },
+    {
+      "epoch": 0.748,
+      "grad_norm": 0.2662514099930545,
+      "learning_rate": 3.84244892650347e-06,
+      "loss": 0.6254,
+      "step": 187
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.26802564374459203,
+      "learning_rate": 3.828014292634508e-06,
+      "loss": 0.6121,
+      "step": 188
+    },
+    {
+      "epoch": 0.756,
+      "grad_norm": 0.28248517647364846,
+      "learning_rate": 3.813517716777069e-06,
+      "loss": 0.6202,
+      "step": 189
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.272622897496479,
+      "learning_rate": 3.798959875088584e-06,
+      "loss": 0.5901,
+      "step": 190
+    },
+    {
+      "epoch": 0.764,
+      "grad_norm": 0.27197490333330376,
+      "learning_rate": 3.7843414465840823e-06,
+      "loss": 0.5856,
+      "step": 191
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.26663311683845875,
+      "learning_rate": 3.769663113104516e-06,
+      "loss": 0.5907,
+      "step": 192
+    },
+    {
+      "epoch": 0.772,
+      "grad_norm": 0.2714585682015405,
+      "learning_rate": 3.7549255592849575e-06,
+      "loss": 0.6072,
+      "step": 193
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.2766267849608307,
+      "learning_rate": 3.7401294725226707e-06,
+      "loss": 0.6158,
+      "step": 194
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.26291754258948374,
+      "learning_rate": 3.7252755429450437e-06,
+      "loss": 0.5921,
+      "step": 195
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.26530027759256725,
+      "learning_rate": 3.7103644633774015e-06,
+      "loss": 0.5841,
+      "step": 196
+    },
+    {
+      "epoch": 0.788,
+      "grad_norm": 0.26634011298693916,
+      "learning_rate": 3.695396929310693e-06,
+      "loss": 0.6147,
+      "step": 197
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.26354297421036926,
+      "learning_rate": 3.680373638869047e-06,
+      "loss": 0.6061,
+      "step": 198
+    },
+    {
+      "epoch": 0.796,
+      "grad_norm": 0.2738313781435172,
+      "learning_rate": 3.665295292777214e-06,
+      "loss": 0.5903,
+      "step": 199
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.27041603557150606,
+      "learning_rate": 3.650162594327881e-06,
+      "loss": 0.6216,
+      "step": 200
+    },
+    {
+      "epoch": 0.804,
+      "grad_norm": 0.29233209893761647,
+      "learning_rate": 3.634976249348867e-06,
+      "loss": 0.6221,
+      "step": 201
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.28236083977418097,
+      "learning_rate": 3.6197369661702052e-06,
+      "loss": 0.6048,
+      "step": 202
+    },
+    {
+      "epoch": 0.812,
+      "grad_norm": 0.2610570975246162,
+      "learning_rate": 3.604445455591099e-06,
+      "loss": 0.586,
+      "step": 203
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.27792495585124566,
+      "learning_rate": 3.589102430846773e-06,
+      "loss": 0.6052,
+      "step": 204
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.27390708264043134,
+      "learning_rate": 3.5737086075752054e-06,
+      "loss": 0.5968,
+      "step": 205
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.26341409551542055,
+      "learning_rate": 3.5582647037837446e-06,
+      "loss": 0.6128,
+      "step": 206
+    },
+    {
+      "epoch": 0.828,
+      "grad_norm": 0.2659397773506794,
+      "learning_rate": 3.5427714398156267e-06,
+      "loss": 0.6171,
+      "step": 207
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.278302186061793,
+      "learning_rate": 3.527229538316371e-06,
+      "loss": 0.6001,
+      "step": 208
+    },
+    {
+      "epoch": 0.836,
+      "grad_norm": 0.27935693059901906,
+      "learning_rate": 3.5116397242000748e-06,
+      "loss": 0.5915,
+      "step": 209
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.2681762304000699,
+      "learning_rate": 3.4960027246156043e-06,
+      "loss": 0.5982,
+      "step": 210
+    },
+    {
+      "epoch": 0.844,
+      "grad_norm": 0.26833511905783713,
+      "learning_rate": 3.480319268912676e-06,
+      "loss": 0.5823,
+      "step": 211
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.27282574698411466,
+      "learning_rate": 3.4645900886078388e-06,
+      "loss": 0.6098,
+      "step": 212
+    },
+    {
+      "epoch": 0.852,
+      "grad_norm": 0.2841325964241835,
+      "learning_rate": 3.448815917350355e-06,
+      "loss": 0.6054,
+      "step": 213
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.27811416712297765,
+      "learning_rate": 3.432997490887979e-06,
+      "loss": 0.6071,
+      "step": 214
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.26897184119138856,
+      "learning_rate": 3.417135547032642e-06,
+      "loss": 0.612,
+      "step": 215
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.2752083088143504,
+      "learning_rate": 3.4012308256260366e-06,
+      "loss": 0.6189,
+      "step": 216
+    },
+    {
+      "epoch": 0.868,
+      "grad_norm": 0.27146348269262077,
+      "learning_rate": 3.385284068505113e-06,
+      "loss": 0.5914,
+      "step": 217
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.2616553689610195,
+      "learning_rate": 3.369296019467473e-06,
+      "loss": 0.5935,
+      "step": 218
+    },
+    {
+      "epoch": 0.876,
+      "grad_norm": 0.27439799989957114,
+      "learning_rate": 3.3532674242366764e-06,
+      "loss": 0.5815,
+      "step": 219
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.27322752130009204,
+      "learning_rate": 3.3371990304274654e-06,
+      "loss": 0.593,
+      "step": 220
+    },
+    {
+      "epoch": 0.884,
+      "grad_norm": 0.2776915569429837,
+      "learning_rate": 3.3210915875108895e-06,
+      "loss": 0.636,
+      "step": 221
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.27021599999486623,
+      "learning_rate": 3.304945846779346e-06,
+      "loss": 0.618,
+      "step": 222
+    },
+    {
+      "epoch": 0.892,
+      "grad_norm": 0.27748742860539916,
+      "learning_rate": 3.2887625613115427e-06,
+      "loss": 0.5937,
+      "step": 223
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.28302784990496294,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.6093,
+      "step": 224
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2759446162478654,
+      "learning_rate": 3.25628637720269e-06,
+      "loss": 0.6261,
+      "step": 225
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.2794223898275526,
+      "learning_rate": 3.239994993334059e-06,
+      "loss": 0.6098,
+      "step": 226
+    },
+    {
+      "epoch": 0.908,
+      "grad_norm": 0.2863521541541822,
+      "learning_rate": 3.2236690942033523e-06,
+      "loss": 0.6122,
+      "step": 227
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.2810413939687701,
+      "learning_rate": 3.207309441292325e-06,
+      "loss": 0.6193,
+      "step": 228
+    },
+    {
+      "epoch": 0.916,
+      "grad_norm": 0.2686724574589154,
+      "learning_rate": 3.1909167976570977e-06,
+      "loss": 0.5847,
+      "step": 229
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.27668513115261734,
+      "learning_rate": 3.174491927892561e-06,
+      "loss": 0.6083,
+      "step": 230
+    },
+    {
+      "epoch": 0.924,
+      "grad_norm": 0.2838278304951842,
+      "learning_rate": 3.158035598096715e-06,
+      "loss": 0.597,
+      "step": 231
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.2702238327135827,
+      "learning_rate": 3.1415485758349344e-06,
+      "loss": 0.5884,
+      "step": 232
+    },
+    {
+      "epoch": 0.932,
+      "grad_norm": 0.2677368696260293,
+      "learning_rate": 3.1250316301041727e-06,
+      "loss": 0.5835,
+      "step": 233
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.2848905107931979,
+      "learning_rate": 3.1084855312970897e-06,
+      "loss": 0.6255,
+      "step": 234
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.2788843417615313,
+      "learning_rate": 3.091911051166117e-06,
+      "loss": 0.6215,
+      "step": 235
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.27680715854768223,
+      "learning_rate": 3.0753089627874668e-06,
+      "loss": 0.6022,
+      "step": 236
+    },
+    {
+      "epoch": 0.948,
+      "grad_norm": 0.26897413893634964,
+      "learning_rate": 3.0586800405250677e-06,
+      "loss": 0.6194,
+      "step": 237
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.2657249388294363,
+      "learning_rate": 3.0420250599944525e-06,
+      "loss": 0.5884,
+      "step": 238
+    },
+    {
+      "epoch": 0.956,
+      "grad_norm": 0.26576882569871957,
+      "learning_rate": 3.0253447980265754e-06,
+      "loss": 0.5949,
+      "step": 239
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2754408264706426,
+      "learning_rate": 3.0086400326315853e-06,
+      "loss": 0.5747,
+      "step": 240
+    },
+    {
+      "epoch": 0.964,
+      "grad_norm": 0.26333215813151695,
+      "learning_rate": 2.9919115429625295e-06,
+      "loss": 0.6035,
+      "step": 241
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.2687016604382336,
+      "learning_rate": 2.9751601092790185e-06,
+      "loss": 0.6057,
+      "step": 242
+    },
+    {
+      "epoch": 0.972,
+      "grad_norm": 0.28837866031127346,
+      "learning_rate": 2.958386512910831e-06,
+      "loss": 0.5737,
+      "step": 243
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.27805411098388116,
+      "learning_rate": 2.941591536221469e-06,
+      "loss": 0.6022,
+      "step": 244
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.27696163335286905,
+      "learning_rate": 2.924775962571667e-06,
+      "loss": 0.6081,
+      "step": 245
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.28312029387331156,
+      "learning_rate": 2.907940576282856e-06,
+      "loss": 0.6178,
+      "step": 246
+    },
+    {
+      "epoch": 0.988,
+      "grad_norm": 0.2516197979856304,
+      "learning_rate": 2.8910861626005774e-06,
+      "loss": 0.5812,
+      "step": 247
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.25765553700425475,
+      "learning_rate": 2.8742135076578608e-06,
+      "loss": 0.5868,
+      "step": 248
+    },
+    {
+      "epoch": 0.996,
+      "grad_norm": 0.27540024093918797,
+      "learning_rate": 2.857323398438554e-06,
+      "loss": 0.5976,
+      "step": 249
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2637219036362386,
+      "learning_rate": 2.840416622740617e-06,
+      "loss": 0.6106,
+      "step": 250
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 125,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.0702370831938355e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e091b32b97830aabb8c79a574506925e3fa58e7035cd23f0d221a73e0d787a76
+size 8440