Training in progress, step 375, checkpoint

checkpoint-375/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-375/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-375/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-375/global_step375/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6060f1df867de68f01cb04aab5316f90a3a346509f00a2b2f737dda4e7aa9018
+size 24702840487

checkpoint-375/global_step375/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da006f1544e9938bb0428feed5a3350d439a5f1abdd8ee27006f02ff577a912
+size 24702840487

checkpoint-375/global_step375/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce503b01d9c8a9ea23999482abe9f110be5d213abfb828af1d11e8d5129e613
+size 24702840487

checkpoint-375/global_step375/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8550db49f9867d3b04c2de2984c59f8e798e81f47fed2b34ea8687b8e729a1ea
+size 24702840487

checkpoint-375/global_step375/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9582d83c184a055386a279dbe2d196bdbd4dfbf410c04997ac0203e3b24ee8de
+size 24702840487

checkpoint-375/global_step375/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1f67ab6176964fc551d3fd9e4af57b5e42919edbedcca9e1f17342bcec77db
+size 24702840487

checkpoint-375/global_step375/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f229135f43a64794ac922cb514256a68ff747287c2275ceae6ff1c609f20a4
+size 24702840487

checkpoint-375/global_step375/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5e6bc7d1a25cbd6f3d052f619016ec2aebc7c353549b2e9dbdc99e280a7453
+size 24702840487

checkpoint-375/global_step375/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b35073fef1994d2597ecfce9ee2605599e0ae5220f5669aa48c12b31c934d3
+size 381701

checkpoint-375/global_step375/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81de293bb1b5c13a2a11de3cb6647cfb06682e62d52600931b58cb4ea5ed35f
+size 381701

checkpoint-375/global_step375/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea248f8f8f34e7fb2ca21d53e298285858ab4d2c68449ba116db1ea88abf1f16
+size 381701

checkpoint-375/global_step375/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fdcb5dc0587d718fa9b6b3b4a7dab3e46dfd2cce679ad80aa01296a978ce71
+size 381701

checkpoint-375/global_step375/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9764abf88567d1a52e5032f541cac884a14c50b392f31bc8dab53ad7248f6f3c
+size 381701

checkpoint-375/global_step375/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ad73c60bae308f34139ada8e5df952341795a3b46d5a504bb2f25784a8ac59
+size 381701

checkpoint-375/global_step375/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f0c1066cb00eaf12a83594233a96bffd349898adc04f190a1852122d3904f2
+size 381701

checkpoint-375/global_step375/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b35f7343f7ec2c7e8fe5d235480128eb0ff4d43523685d0277bef8d08aa674
+size 381701

checkpoint-375/latest

@@ -0,0 +1 @@
+global_step375

checkpoint-375/model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941f91cefaf906dc9eedc534df199263d48554f5f6c4b85868dc5ab3f35c098d
+size 4891730992

checkpoint-375/model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e10b1885e766324ef17cc8ce992d679aa4803dd7eb65e02eea45cb9e8de388c
+size 4876059352

checkpoint-375/model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25645cab4c024a18417b2d3c7f8564f474fa12af33d6a8a161611bdb20259475
+size 4876059384

checkpoint-375/model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11eeeab9fddc35b3b9941aa0b65e4989f77fac35439bdbfe0dedca0f32d236b0
+size 4876059416

checkpoint-375/model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8d2b3b4c464fe3e5072051cb3c9d735a6045a78f542d9485857709ed040377
+size 4876059416

checkpoint-375/model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12da516093f0a62f0cd4e6c1d55e03a78b425e247087a9be147a698dc35c6d1
+size 4876059416

checkpoint-375/model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:190933eb8e008d86110c960966c38f817d59c62ec7fc931f235fa943b4b156e9
+size 4876059416

checkpoint-375/model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156016a6abecb914c86e550e8b08d3d779b3c3984a55400f0c10eb6f33258c8a
+size 4876059416

checkpoint-375/model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be0fbb1a3dc589d545a3f55596a4de9127b0e4c7f91159595718126a314523d8
+size 4876059416

checkpoint-375/model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e609ebc95c1089fb91ffc1d06a118502e9bb98b9bba309064c7b6c2490417237
+size 4876059416

checkpoint-375/model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bde0eb6409fad4109925bfd18c036fe492d0d8dce2ba22890bc8a6fa9dedc54
+size 4876059416

checkpoint-375/model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d707e3e0fb4ce04335fd1926e2861e1cab39210098220606e79bc69bcadd9c
+size 4876059416

checkpoint-375/model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb73c4938f60c43cfb402f20bba613d41c11124540ed6872ed4408eaf928626
+size 4876059416

checkpoint-375/model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed6d33ff07eff4f29e971692a82edbbd697edeb9d2625a0dfb12f1433c16978
+size 2123397800

checkpoint-375/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-375/rng_state_0.pth

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

checkpoint-375/rng_state_1.pth

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

checkpoint-375/rng_state_2.pth

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

checkpoint-375/rng_state_3.pth

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

checkpoint-375/rng_state_4.pth

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

checkpoint-375/rng_state_5.pth

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

checkpoint-375/rng_state_6.pth

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

checkpoint-375/rng_state_7.pth

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

checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4c80f97906b06bf11e09798ee50dca4af9fd4fe1df2d487c26eedfbc10005b
+size 1064

checkpoint-375/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-375/tokenizer.json

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

checkpoint-375/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-375/trainer_state.json

@@ -0,0 +1,2658 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5,
+  "eval_steps": 500,
+  "global_step": 375,
+  "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
+    },
+    {
+      "epoch": 1.004,
+      "grad_norm": 0.3270308432987493,
+      "learning_rate": 2.8234939691393765e-06,
+      "loss": 0.5662,
+      "step": 251
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.3032460726332443,
+      "learning_rate": 2.8065562269507464e-06,
+      "loss": 0.589,
+      "step": 252
+    },
+    {
+      "epoch": 1.012,
+      "grad_norm": 0.2761928570311231,
+      "learning_rate": 2.789604186194411e-06,
+      "loss": 0.5654,
+      "step": 253
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.27190181641802363,
+      "learning_rate": 2.7726386375569748e-06,
+      "loss": 0.5908,
+      "step": 254
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.27382272887323905,
+      "learning_rate": 2.7556603723550855e-06,
+      "loss": 0.553,
+      "step": 255
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.2699869769385883,
+      "learning_rate": 2.7386701824985257e-06,
+      "loss": 0.5517,
+      "step": 256
+    },
+    {
+      "epoch": 1.028,
+      "grad_norm": 0.2740431770397761,
+      "learning_rate": 2.721668860453271e-06,
+      "loss": 0.5611,
+      "step": 257
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.27006742872479766,
+      "learning_rate": 2.7046571992045334e-06,
+      "loss": 0.5609,
+      "step": 258
+    },
+    {
+      "epoch": 1.036,
+      "grad_norm": 0.2853628863130536,
+      "learning_rate": 2.6876359922197703e-06,
+      "loss": 0.5839,
+      "step": 259
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.2674934886902205,
+      "learning_rate": 2.670606033411678e-06,
+      "loss": 0.5692,
+      "step": 260
+    },
+    {
+      "epoch": 1.044,
+      "grad_norm": 0.2717961476035451,
+      "learning_rate": 2.653568117101159e-06,
+      "loss": 0.5586,
+      "step": 261
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.2886664885195019,
+      "learning_rate": 2.636523037980275e-06,
+      "loss": 0.5592,
+      "step": 262
+    },
+    {
+      "epoch": 1.052,
+      "grad_norm": 0.2913975175671213,
+      "learning_rate": 2.6194715910751806e-06,
+      "loss": 0.5588,
+      "step": 263
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.26635335287134043,
+      "learning_rate": 2.602414571709036e-06,
+      "loss": 0.5518,
+      "step": 264
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.27589381073650543,
+      "learning_rate": 2.58535277546492e-06,
+      "loss": 0.5588,
+      "step": 265
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.26891839582782207,
+      "learning_rate": 2.5682869981487154e-06,
+      "loss": 0.5671,
+      "step": 266
+    },
+    {
+      "epoch": 1.068,
+      "grad_norm": 0.2699654255248958,
+      "learning_rate": 2.5512180357519913e-06,
+      "loss": 0.5663,
+      "step": 267
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.27268944362101294,
+      "learning_rate": 2.5341466844148775e-06,
+      "loss": 0.5689,
+      "step": 268
+    },
+    {
+      "epoch": 1.076,
+      "grad_norm": 0.2895176432362157,
+      "learning_rate": 2.5170737403889334e-06,
+      "loss": 0.555,
+      "step": 269
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.275834303493974,
+      "learning_rate": 2.5e-06,
+      "loss": 0.5652,
+      "step": 270
+    },
+    {
+      "epoch": 1.084,
+      "grad_norm": 0.27109148773857455,
+      "learning_rate": 2.4829262596110674e-06,
+      "loss": 0.5531,
+      "step": 271
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.2885944970109634,
+      "learning_rate": 2.465853315585123e-06,
+      "loss": 0.5645,
+      "step": 272
+    },
+    {
+      "epoch": 1.092,
+      "grad_norm": 0.3325900759228949,
+      "learning_rate": 2.44878196424801e-06,
+      "loss": 0.567,
+      "step": 273
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.2656725633978504,
+      "learning_rate": 2.431713001851286e-06,
+      "loss": 0.5645,
+      "step": 274
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.28515147451371026,
+      "learning_rate": 2.4146472245350804e-06,
+      "loss": 0.5627,
+      "step": 275
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.2772295325997671,
+      "learning_rate": 2.3975854282909645e-06,
+      "loss": 0.5606,
+      "step": 276
+    },
+    {
+      "epoch": 1.108,
+      "grad_norm": 0.2732258740956759,
+      "learning_rate": 2.3805284089248203e-06,
+      "loss": 0.558,
+      "step": 277
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.2657630056993197,
+      "learning_rate": 2.3634769620197253e-06,
+      "loss": 0.5639,
+      "step": 278
+    },
+    {
+      "epoch": 1.116,
+      "grad_norm": 0.2741360647437433,
+      "learning_rate": 2.3464318828988416e-06,
+      "loss": 0.539,
+      "step": 279
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.27924091679374063,
+      "learning_rate": 2.3293939665883233e-06,
+      "loss": 0.563,
+      "step": 280
+    },
+    {
+      "epoch": 1.124,
+      "grad_norm": 0.2663368697744116,
+      "learning_rate": 2.3123640077802305e-06,
+      "loss": 0.5639,
+      "step": 281
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.2635159398782791,
+      "learning_rate": 2.2953428007954682e-06,
+      "loss": 0.5225,
+      "step": 282
+    },
+    {
+      "epoch": 1.1320000000000001,
+      "grad_norm": 0.26790514294280293,
+      "learning_rate": 2.2783311395467304e-06,
+      "loss": 0.5556,
+      "step": 283
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.27007506595154834,
+      "learning_rate": 2.261329817501475e-06,
+      "loss": 0.545,
+      "step": 284
+    },
+    {
+      "epoch": 1.1400000000000001,
+      "grad_norm": 0.27274462523361476,
+      "learning_rate": 2.2443396276449145e-06,
+      "loss": 0.5724,
+      "step": 285
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.25666672253669337,
+      "learning_rate": 2.2273613624430256e-06,
+      "loss": 0.541,
+      "step": 286
+    },
+    {
+      "epoch": 1.148,
+      "grad_norm": 0.30831325626025924,
+      "learning_rate": 2.2103958138055897e-06,
+      "loss": 0.5544,
+      "step": 287
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.26679849744140743,
+      "learning_rate": 2.1934437730492544e-06,
+      "loss": 0.5544,
+      "step": 288
+    },
+    {
+      "epoch": 1.156,
+      "grad_norm": 0.26795918133510693,
+      "learning_rate": 2.1765060308606243e-06,
+      "loss": 0.5726,
+      "step": 289
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.26692330671607206,
+      "learning_rate": 2.159583377259384e-06,
+      "loss": 0.5771,
+      "step": 290
+    },
+    {
+      "epoch": 1.164,
+      "grad_norm": 0.26800012106006976,
+      "learning_rate": 2.142676601561447e-06,
+      "loss": 0.5376,
+      "step": 291
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.25520584565446575,
+      "learning_rate": 2.1257864923421405e-06,
+      "loss": 0.5439,
+      "step": 292
+    },
+    {
+      "epoch": 1.172,
+      "grad_norm": 0.26220655980779767,
+      "learning_rate": 2.1089138373994226e-06,
+      "loss": 0.552,
+      "step": 293
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.2599229946929615,
+      "learning_rate": 2.092059423717145e-06,
+      "loss": 0.5591,
+      "step": 294
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.26226465656771997,
+      "learning_rate": 2.0752240374283334e-06,
+      "loss": 0.5424,
+      "step": 295
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.27097583397605235,
+      "learning_rate": 2.0584084637785316e-06,
+      "loss": 0.5613,
+      "step": 296
+    },
+    {
+      "epoch": 1.188,
+      "grad_norm": 0.25487494718289816,
+      "learning_rate": 2.0416134870891697e-06,
+      "loss": 0.5531,
+      "step": 297
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.258627059695691,
+      "learning_rate": 2.0248398907209827e-06,
+      "loss": 0.5603,
+      "step": 298
+    },
+    {
+      "epoch": 1.196,
+      "grad_norm": 0.27660938201914487,
+      "learning_rate": 2.008088457037472e-06,
+      "loss": 0.5648,
+      "step": 299
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.26596618229804614,
+      "learning_rate": 1.991359967368416e-06,
+      "loss": 0.574,
+      "step": 300
+    },
+    {
+      "epoch": 1.204,
+      "grad_norm": 0.2618039991994125,
+      "learning_rate": 1.9746552019734246e-06,
+      "loss": 0.5492,
+      "step": 301
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.272654754048079,
+      "learning_rate": 1.957974940005548e-06,
+      "loss": 0.5767,
+      "step": 302
+    },
+    {
+      "epoch": 1.212,
+      "grad_norm": 0.26671171090168844,
+      "learning_rate": 1.9413199594749327e-06,
+      "loss": 0.5338,
+      "step": 303
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.270832034752946,
+      "learning_rate": 1.9246910372125345e-06,
+      "loss": 0.5647,
+      "step": 304
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.2643013014532281,
+      "learning_rate": 1.9080889488338833e-06,
+      "loss": 0.5597,
+      "step": 305
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.27092629093151294,
+      "learning_rate": 1.8915144687029107e-06,
+      "loss": 0.5485,
+      "step": 306
+    },
+    {
+      "epoch": 1.228,
+      "grad_norm": 0.26613235310331923,
+      "learning_rate": 1.874968369895828e-06,
+      "loss": 0.552,
+      "step": 307
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.2582406507610385,
+      "learning_rate": 1.8584514241650667e-06,
+      "loss": 0.5477,
+      "step": 308
+    },
+    {
+      "epoch": 1.236,
+      "grad_norm": 0.2687239346512157,
+      "learning_rate": 1.8419644019032868e-06,
+      "loss": 0.5716,
+      "step": 309
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.2634130471010307,
+      "learning_rate": 1.8255080721074391e-06,
+      "loss": 0.5511,
+      "step": 310
+    },
+    {
+      "epoch": 1.244,
+      "grad_norm": 0.27164814594203673,
+      "learning_rate": 1.8090832023429022e-06,
+      "loss": 0.5605,
+      "step": 311
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.26506994687071844,
+      "learning_rate": 1.792690558707675e-06,
+      "loss": 0.5522,
+      "step": 312
+    },
+    {
+      "epoch": 1.252,
+      "grad_norm": 0.2710404134246902,
+      "learning_rate": 1.7763309057966487e-06,
+      "loss": 0.5754,
+      "step": 313
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.2644648635617096,
+      "learning_rate": 1.7600050066659418e-06,
+      "loss": 0.5542,
+      "step": 314
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.2563441049550618,
+      "learning_rate": 1.7437136227973108e-06,
+      "loss": 0.5428,
+      "step": 315
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.2781486176634604,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.5469,
+      "step": 316
+    },
+    {
+      "epoch": 1.268,
+      "grad_norm": 0.26498925525964123,
+      "learning_rate": 1.7112374386884583e-06,
+      "loss": 0.5671,
+      "step": 317
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.27752994625791155,
+      "learning_rate": 1.695054153220655e-06,
+      "loss": 0.5437,
+      "step": 318
+    },
+    {
+      "epoch": 1.276,
+      "grad_norm": 0.2602835745087367,
+      "learning_rate": 1.678908412489111e-06,
+      "loss": 0.5602,
+      "step": 319
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.2665909274717665,
+      "learning_rate": 1.6628009695725348e-06,
+      "loss": 0.5762,
+      "step": 320
+    },
+    {
+      "epoch": 1.284,
+      "grad_norm": 0.2531045714341802,
+      "learning_rate": 1.6467325757633242e-06,
+      "loss": 0.5674,
+      "step": 321
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.2621120701043234,
+      "learning_rate": 1.630703980532528e-06,
+      "loss": 0.5598,
+      "step": 322
+    },
+    {
+      "epoch": 1.292,
+      "grad_norm": 0.275203318844759,
+      "learning_rate": 1.6147159314948873e-06,
+      "loss": 0.564,
+      "step": 323
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.2603786935372431,
+      "learning_rate": 1.5987691743739636e-06,
+      "loss": 0.5535,
+      "step": 324
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.26776057829072847,
+      "learning_rate": 1.5828644529673592e-06,
+      "loss": 0.5627,
+      "step": 325
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.2623048715119549,
+      "learning_rate": 1.5670025091120219e-06,
+      "loss": 0.5685,
+      "step": 326
+    },
+    {
+      "epoch": 1.308,
+      "grad_norm": 0.26608080729860306,
+      "learning_rate": 1.5511840826496462e-06,
+      "loss": 0.5695,
+      "step": 327
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.2673157087455161,
+      "learning_rate": 1.5354099113921614e-06,
+      "loss": 0.5354,
+      "step": 328
+    },
+    {
+      "epoch": 1.316,
+      "grad_norm": 0.2754778027664838,
+      "learning_rate": 1.519680731087325e-06,
+      "loss": 0.5705,
+      "step": 329
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.2697793809470272,
+      "learning_rate": 1.5039972753843966e-06,
+      "loss": 0.5748,
+      "step": 330
+    },
+    {
+      "epoch": 1.324,
+      "grad_norm": 0.2737068013002947,
+      "learning_rate": 1.488360275799926e-06,
+      "loss": 0.5554,
+      "step": 331
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.2618826312103745,
+      "learning_rate": 1.4727704616836297e-06,
+      "loss": 0.5516,
+      "step": 332
+    },
+    {
+      "epoch": 1.332,
+      "grad_norm": 0.2610637671077678,
+      "learning_rate": 1.457228560184374e-06,
+      "loss": 0.5491,
+      "step": 333
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.2615954274949455,
+      "learning_rate": 1.441735296216256e-06,
+      "loss": 0.5556,
+      "step": 334
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.2650842665446321,
+      "learning_rate": 1.4262913924247956e-06,
+      "loss": 0.5475,
+      "step": 335
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.25585711289460494,
+      "learning_rate": 1.4108975691532273e-06,
+      "loss": 0.5549,
+      "step": 336
+    },
+    {
+      "epoch": 1.3479999999999999,
+      "grad_norm": 0.25250951856873494,
+      "learning_rate": 1.3955545444089017e-06,
+      "loss": 0.5601,
+      "step": 337
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.2569876765702743,
+      "learning_rate": 1.3802630338297956e-06,
+      "loss": 0.548,
+      "step": 338
+    },
+    {
+      "epoch": 1.3559999999999999,
+      "grad_norm": 0.28203813821342777,
+      "learning_rate": 1.3650237506511333e-06,
+      "loss": 0.566,
+      "step": 339
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.27081394807954995,
+      "learning_rate": 1.3498374056721198e-06,
+      "loss": 0.5594,
+      "step": 340
+    },
+    {
+      "epoch": 1.3639999999999999,
+      "grad_norm": 0.26811473148644754,
+      "learning_rate": 1.334704707222787e-06,
+      "loss": 0.5558,
+      "step": 341
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.2635422950339071,
+      "learning_rate": 1.3196263611309539e-06,
+      "loss": 0.5707,
+      "step": 342
+    },
+    {
+      "epoch": 1.3719999999999999,
+      "grad_norm": 0.25640933129102816,
+      "learning_rate": 1.3046030706893079e-06,
+      "loss": 0.5551,
+      "step": 343
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.26144553856379565,
+      "learning_rate": 1.2896355366226e-06,
+      "loss": 0.5689,
+      "step": 344
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.24921356601339556,
+      "learning_rate": 1.2747244570549578e-06,
+      "loss": 0.5223,
+      "step": 345
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.2739025094336896,
+      "learning_rate": 1.2598705274773299e-06,
+      "loss": 0.5553,
+      "step": 346
+    },
+    {
+      "epoch": 1.388,
+      "grad_norm": 0.26711249323543973,
+      "learning_rate": 1.2450744407150427e-06,
+      "loss": 0.5411,
+      "step": 347
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.2695324913604517,
+      "learning_rate": 1.2303368868954848e-06,
+      "loss": 0.567,
+      "step": 348
+    },
+    {
+      "epoch": 1.396,
+      "grad_norm": 0.25781431882124334,
+      "learning_rate": 1.215658553415918e-06,
+      "loss": 0.5674,
+      "step": 349
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.2594657444454727,
+      "learning_rate": 1.2010401249114166e-06,
+      "loss": 0.5366,
+      "step": 350
+    },
+    {
+      "epoch": 1.404,
+      "grad_norm": 0.26265811514812376,
+      "learning_rate": 1.1864822832229319e-06,
+      "loss": 0.5465,
+      "step": 351
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.26623313611028854,
+      "learning_rate": 1.1719857073654923e-06,
+      "loss": 0.564,
+      "step": 352
+    },
+    {
+      "epoch": 1.412,
+      "grad_norm": 0.2702849646886806,
+      "learning_rate": 1.1575510734965305e-06,
+      "loss": 0.5521,
+      "step": 353
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.2689048371097966,
+      "learning_rate": 1.1431790548843464e-06,
+      "loss": 0.5527,
+      "step": 354
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.25819241256540093,
+      "learning_rate": 1.1288703218767027e-06,
+      "loss": 0.54,
+      "step": 355
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.25437896341243765,
+      "learning_rate": 1.1146255418695635e-06,
+      "loss": 0.528,
+      "step": 356
+    },
+    {
+      "epoch": 1.428,
+      "grad_norm": 0.25406879267543436,
+      "learning_rate": 1.1004453792759547e-06,
+      "loss": 0.5471,
+      "step": 357
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.2562241134177116,
+      "learning_rate": 1.0863304954949856e-06,
+      "loss": 0.55,
+      "step": 358
+    },
+    {
+      "epoch": 1.436,
+      "grad_norm": 0.26542441620839063,
+      "learning_rate": 1.072281548880992e-06,
+      "loss": 0.5678,
+      "step": 359
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.269318418298225,
+      "learning_rate": 1.0582991947128324e-06,
+      "loss": 0.5615,
+      "step": 360
+    },
+    {
+      "epoch": 1.444,
+      "grad_norm": 0.2691764014021926,
+      "learning_rate": 1.0443840851633227e-06,
+      "loss": 0.565,
+      "step": 361
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.2594862635555543,
+      "learning_rate": 1.0305368692688175e-06,
+      "loss": 0.5666,
+      "step": 362
+    },
+    {
+      "epoch": 1.452,
+      "grad_norm": 0.25315547667760335,
+      "learning_rate": 1.0167581928989373e-06,
+      "loss": 0.5555,
+      "step": 363
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.2613895044115319,
+      "learning_rate": 1.0030486987264436e-06,
+      "loss": 0.5776,
+      "step": 364
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.2631431546714004,
+      "learning_rate": 9.89409026197264e-07,
+      "loss": 0.5365,
+      "step": 365
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.2647751182203821,
+      "learning_rate": 9.758398115006637e-07,
+      "loss": 0.5573,
+      "step": 366
+    },
+    {
+      "epoch": 1.468,
+      "grad_norm": 0.26208143115660865,
+      "learning_rate": 9.623416875395763e-07,
+      "loss": 0.5605,
+      "step": 367
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.2704474380702507,
+      "learning_rate": 9.489152839010799e-07,
+      "loss": 0.5697,
+      "step": 368
+    },
+    {
+      "epoch": 1.476,
+      "grad_norm": 0.275761932132816,
+      "learning_rate": 9.355612268270339e-07,
+      "loss": 0.5586,
+      "step": 369
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.27242480864427504,
+      "learning_rate": 9.222801391848688e-07,
+      "loss": 0.5573,
+      "step": 370
+    },
+    {
+      "epoch": 1.484,
+      "grad_norm": 0.254674372509468,
+      "learning_rate": 9.090726404385319e-07,
+      "loss": 0.5377,
+      "step": 371
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.25888213496864965,
+      "learning_rate": 8.959393466195973e-07,
+      "loss": 0.5278,
+      "step": 372
+    },
+    {
+      "epoch": 1.492,
+      "grad_norm": 0.2527033545759895,
+      "learning_rate": 8.828808702985325e-07,
+      "loss": 0.5475,
+      "step": 373
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.2669973822070058,
+      "learning_rate": 8.69897820556124e-07,
+      "loss": 0.5652,
+      "step": 374
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.26903334117277744,
+      "learning_rate": 8.569908029550686e-07,
+      "loss": 0.5555,
+      "step": 375
+    }
+  ],
+  "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": 4.6053644267893555e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-375/training_args.bin

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