Training in progress, step 285, checkpoint

checkpoint-285/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-285/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "./qwq",
+  "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-285/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-285/global_step284/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e313e6e58e9d7cc9981cff1d6c99d37e9c380fab3b300a1d6192707eb85c2d2
+size 24702834279

checkpoint-285/global_step284/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:a0914b5489b926c3dda5cab10e5f6a86e334b09c2a40a9c1851d4090541a4011
+size 24702834279

checkpoint-285/global_step284/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:ae091b7ba1f3ee9613567fee6ebd5c9fbbe6caad8d4e357de34b197eea1c14ef
+size 24702834279

checkpoint-285/global_step284/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b22d8330b661f3f8ad5c49ead6dcb7636d303857fcc55e77beb694f00e6997
+size 24702834279

checkpoint-285/global_step284/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:b1bf338c3c6f37bdc4cb69f378b263ae3a8919557ab946837a39137d5190b8b6
+size 24702834279

checkpoint-285/global_step284/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:edd136028008377466f9e4a32cae5bea5fe1cd040fc91b058cec6be9744ca06e
+size 24702834279

checkpoint-285/global_step284/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:c26d27103a860890516b978ccd73a795d8215578158607db8bb49604190dedae
+size 24702834279

checkpoint-285/global_step284/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:f38ae7e2aaf50473a127aebe2d0c5aeeefb0a3d2330d15ac44bd5b67668372d3
+size 24702834279

checkpoint-285/global_step284/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e3588e5352300ce93c5dab2cc1815f81e9088f33f0ef5749997665171efe19
+size 381701

checkpoint-285/global_step284/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de97717a6cc7f76b1468883f2e20adaa00e445b4b4fdfb736dd57305b4a55957
+size 381701

checkpoint-285/global_step284/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97120564906329ffa309d5dc51c50200cb42e89d9b5c7d76826c4f7d24b6938
+size 381701

checkpoint-285/global_step284/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaca3d137ae4fcf72cf6169ef357b593476ba9319d5e75d4a5cafe1e255cd8c9
+size 381701

checkpoint-285/global_step284/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2caf6526efcff42f4f1a98b23d218ae029130b8d0aab426896ed86eb034f5c
+size 381701

checkpoint-285/global_step284/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97438271019c38a7926887f12d8e11ca3e8dbc0cf88bc4db0201f87546ce6897
+size 381701

checkpoint-285/global_step284/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f32e9164f877f869a3d643511c716652ee27566f0053fec9e5c401df28ebe5
+size 381701

checkpoint-285/global_step284/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2293e8d3cd6ddf7f38ced82c273793e37c69b62e34a58653dc5720f921c2fdbd
+size 381701

checkpoint-285/latest

@@ -0,0 +1 @@
+global_step284

checkpoint-285/model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42346fcee4c84b21716f181c28a0c2fdc62a9fadf4b258f468bdc20c9c87ce50
+size 4891730992

checkpoint-285/model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2bded2abc95e816bbfd41d45fdaf02c472b93e39b186c2c67e64c1ef584090c
+size 4876059352

checkpoint-285/model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1381b8a8d48b624aea2de2d3e7dcf7e53a5d4dc237f757b8c263eef405faa9d
+size 4876059384

checkpoint-285/model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac15677e790996976ec66bda89206c21574de8ea8939648e68c9c5e5def35123
+size 4876059416

checkpoint-285/model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:565a75ee8993f80a7040893b826028fc6daf5578d3ba851232548dd5d51862bf
+size 4876059416

checkpoint-285/model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9efb5296f2182c7153f643050a69d2ab537e27fc15b488055775b6ef40f5159
+size 4876059416

checkpoint-285/model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abfe635f0c526f713e09761d51c5305bd3685d47a4669e02588c3e792d5a1d71
+size 4876059416

checkpoint-285/model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c86b874ee5475c8e4698541d2a33a4e89c2a4bb9e78aa3b3175f3e12afc7851e
+size 4876059416

checkpoint-285/model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0993083a57a47d22c37e184fb1fa7dda6ad6c176afb0cad4dbd41951b76a96b7
+size 4876059416

checkpoint-285/model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40d444856e5594ff19f8dd60cc68c223ade5e49a24aa5247616897a01bc473a
+size 4876059416

checkpoint-285/model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296c0eb8bc9910e7f8c211fe26b54269a2e83b438d1a9e2e4967aba5ff9a11e0
+size 4876059416

checkpoint-285/model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:472fb6923b910b57bb3701a378b63e2cea67b082eeb75015675686cbf4340919
+size 4876059416

checkpoint-285/model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf6936306c154f4646fbef8f831d6945fb42944d4c9491c1b28ae5d4cd73e74
+size 4876059416

checkpoint-285/model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b3a32254b03b9773e446fd45437e3f723cdc245ac93955ef1773a93c5b0335
+size 2123397800

checkpoint-285/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-285/rng_state_0.pth

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

checkpoint-285/rng_state_1.pth

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

checkpoint-285/rng_state_2.pth

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

checkpoint-285/rng_state_3.pth

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

checkpoint-285/rng_state_4.pth

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

checkpoint-285/rng_state_5.pth

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

checkpoint-285/rng_state_6.pth

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

checkpoint-285/rng_state_7.pth

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

checkpoint-285/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fe10da9ed8e0631515115e774f569e4b1576f2b9267c4a7ac821a418a1fa16
+size 1064

checkpoint-285/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-285/tokenizer.json

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

checkpoint-285/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-285/trainer_state.json

@@ -0,0 +1,2028 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4934383202099737,
+  "eval_steps": 500,
+  "global_step": 285,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005249343832020997,
+      "grad_norm": 1.134754623075341,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.1087,
+      "step": 1
+    },
+    {
+      "epoch": 0.010498687664041995,
+      "grad_norm": 1.1234145683168772,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1356,
+      "step": 2
+    },
+    {
+      "epoch": 0.015748031496062992,
+      "grad_norm": 1.0799860590372758,
+      "learning_rate": 3e-06,
+      "loss": 1.1152,
+      "step": 3
+    },
+    {
+      "epoch": 0.02099737532808399,
+      "grad_norm": 0.9984297481710986,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.0953,
+      "step": 4
+    },
+    {
+      "epoch": 0.026246719160104987,
+      "grad_norm": 0.8302026280344834,
+      "learning_rate": 5e-06,
+      "loss": 1.0617,
+      "step": 5
+    },
+    {
+      "epoch": 0.031496062992125984,
+      "grad_norm": 0.8911823807745126,
+      "learning_rate": 6e-06,
+      "loss": 1.1297,
+      "step": 6
+    },
+    {
+      "epoch": 0.03674540682414698,
+      "grad_norm": 0.686211615667355,
+      "learning_rate": 7e-06,
+      "loss": 1.0705,
+      "step": 7
+    },
+    {
+      "epoch": 0.04199475065616798,
+      "grad_norm": 0.9091855799181295,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.065,
+      "step": 8
+    },
+    {
+      "epoch": 0.047244094488188976,
+      "grad_norm": 0.8934722980371054,
+      "learning_rate": 9e-06,
+      "loss": 1.0767,
+      "step": 9
+    },
+    {
+      "epoch": 0.05249343832020997,
+      "grad_norm": 0.8688110393935611,
+      "learning_rate": 1e-05,
+      "loss": 1.0303,
+      "step": 10
+    },
+    {
+      "epoch": 0.05774278215223097,
+      "grad_norm": 0.9920393807379069,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 1.0855,
+      "step": 11
+    },
+    {
+      "epoch": 0.06299212598425197,
+      "grad_norm": 0.9220245541797021,
+      "learning_rate": 1.2e-05,
+      "loss": 1.0531,
+      "step": 12
+    },
+    {
+      "epoch": 0.06824146981627296,
+      "grad_norm": 0.736886642754733,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 1.0456,
+      "step": 13
+    },
+    {
+      "epoch": 0.07349081364829396,
+      "grad_norm": 0.771339891024354,
+      "learning_rate": 1.4e-05,
+      "loss": 1.0671,
+      "step": 14
+    },
+    {
+      "epoch": 0.07874015748031496,
+      "grad_norm": 0.7161080553611359,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.0521,
+      "step": 15
+    },
+    {
+      "epoch": 0.08398950131233596,
+      "grad_norm": 0.6788342613059561,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.0674,
+      "step": 16
+    },
+    {
+      "epoch": 0.08923884514435695,
+      "grad_norm": 0.7102848455414168,
+      "learning_rate": 1.7e-05,
+      "loss": 1.0459,
+      "step": 17
+    },
+    {
+      "epoch": 0.09448818897637795,
+      "grad_norm": 0.6425246555654909,
+      "learning_rate": 1.8e-05,
+      "loss": 1.0093,
+      "step": 18
+    },
+    {
+      "epoch": 0.09973753280839895,
+      "grad_norm": 2.099748819540086,
+      "learning_rate": 1.9e-05,
+      "loss": 1.0301,
+      "step": 19
+    },
+    {
+      "epoch": 0.10498687664041995,
+      "grad_norm": 0.6691987921672391,
+      "learning_rate": 2e-05,
+      "loss": 1.0199,
+      "step": 20
+    },
+    {
+      "epoch": 0.11023622047244094,
+      "grad_norm": 0.5883655485426926,
+      "learning_rate": 2.1000000000000002e-05,
+      "loss": 1.0085,
+      "step": 21
+    },
+    {
+      "epoch": 0.11548556430446194,
+      "grad_norm": 0.5443706631485103,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.0432,
+      "step": 22
+    },
+    {
+      "epoch": 0.12073490813648294,
+      "grad_norm": 0.593023936793411,
+      "learning_rate": 2.3e-05,
+      "loss": 1.0196,
+      "step": 23
+    },
+    {
+      "epoch": 0.12598425196850394,
+      "grad_norm": 0.5618656915734137,
+      "learning_rate": 2.4e-05,
+      "loss": 1.0386,
+      "step": 24
+    },
+    {
+      "epoch": 0.13123359580052493,
+      "grad_norm": 0.46871710098096486,
+      "learning_rate": 2.5e-05,
+      "loss": 0.9611,
+      "step": 25
+    },
+    {
+      "epoch": 0.13648293963254593,
+      "grad_norm": 0.5700902276763852,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.0045,
+      "step": 26
+    },
+    {
+      "epoch": 0.14173228346456693,
+      "grad_norm": 0.603692765386866,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.019,
+      "step": 27
+    },
+    {
+      "epoch": 0.14698162729658792,
+      "grad_norm": 0.48456720859923497,
+      "learning_rate": 2.8e-05,
+      "loss": 0.9892,
+      "step": 28
+    },
+    {
+      "epoch": 0.15223097112860892,
+      "grad_norm": 0.45729475661677665,
+      "learning_rate": 2.9e-05,
+      "loss": 0.9645,
+      "step": 29
+    },
+    {
+      "epoch": 0.15748031496062992,
+      "grad_norm": 0.5439846777665153,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 0.9497,
+      "step": 30
+    },
+    {
+      "epoch": 0.16272965879265092,
+      "grad_norm": 0.4965459941185334,
+      "learning_rate": 3.1e-05,
+      "loss": 0.9882,
+      "step": 31
+    },
+    {
+      "epoch": 0.1679790026246719,
+      "grad_norm": 0.4656328962534996,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.0057,
+      "step": 32
+    },
+    {
+      "epoch": 0.1732283464566929,
+      "grad_norm": 0.5241601609773927,
+      "learning_rate": 3.3e-05,
+      "loss": 1.0033,
+      "step": 33
+    },
+    {
+      "epoch": 0.1784776902887139,
+      "grad_norm": 0.5062226992393802,
+      "learning_rate": 3.4e-05,
+      "loss": 1.0166,
+      "step": 34
+    },
+    {
+      "epoch": 0.1837270341207349,
+      "grad_norm": 0.43771829747985674,
+      "learning_rate": 3.5000000000000004e-05,
+      "loss": 1.0102,
+      "step": 35
+    },
+    {
+      "epoch": 0.1889763779527559,
+      "grad_norm": 0.48092156639697076,
+      "learning_rate": 3.6e-05,
+      "loss": 1.018,
+      "step": 36
+    },
+    {
+      "epoch": 0.1942257217847769,
+      "grad_norm": 0.48115559949514536,
+      "learning_rate": 3.7000000000000005e-05,
+      "loss": 1.0079,
+      "step": 37
+    },
+    {
+      "epoch": 0.1994750656167979,
+      "grad_norm": 0.4777546937622387,
+      "learning_rate": 3.8e-05,
+      "loss": 1.0085,
+      "step": 38
+    },
+    {
+      "epoch": 0.2047244094488189,
+      "grad_norm": 0.44755392669080185,
+      "learning_rate": 3.9e-05,
+      "loss": 0.9825,
+      "step": 39
+    },
+    {
+      "epoch": 0.2099737532808399,
+      "grad_norm": 0.44510881962201315,
+      "learning_rate": 4e-05,
+      "loss": 0.9848,
+      "step": 40
+    },
+    {
+      "epoch": 0.2152230971128609,
+      "grad_norm": 0.4746290969046573,
+      "learning_rate": 3.999914623406736e-05,
+      "loss": 0.9888,
+      "step": 41
+    },
+    {
+      "epoch": 0.2204724409448819,
+      "grad_norm": 0.5953130701884418,
+      "learning_rate": 3.9996585009161056e-05,
+      "loss": 0.9882,
+      "step": 42
+    },
+    {
+      "epoch": 0.22572178477690288,
+      "grad_norm": 0.4251472611705547,
+      "learning_rate": 3.999231654394975e-05,
+      "loss": 0.9958,
+      "step": 43
+    },
+    {
+      "epoch": 0.23097112860892388,
+      "grad_norm": 0.44690799367073597,
+      "learning_rate": 3.9986341202860467e-05,
+      "loss": 0.9543,
+      "step": 44
+    },
+    {
+      "epoch": 0.23622047244094488,
+      "grad_norm": 0.5976579403936895,
+      "learning_rate": 3.9978659496047456e-05,
+      "loss": 0.9762,
+      "step": 45
+    },
+    {
+      "epoch": 0.24146981627296588,
+      "grad_norm": 0.3962092871428472,
+      "learning_rate": 3.9969272079348685e-05,
+      "loss": 0.9605,
+      "step": 46
+    },
+    {
+      "epoch": 0.24671916010498687,
+      "grad_norm": 0.43362883575028716,
+      "learning_rate": 3.995817975422981e-05,
+      "loss": 0.9456,
+      "step": 47
+    },
+    {
+      "epoch": 0.25196850393700787,
+      "grad_norm": 0.4139776793240363,
+      "learning_rate": 3.994538346771576e-05,
+      "loss": 0.9165,
+      "step": 48
+    },
+    {
+      "epoch": 0.2572178477690289,
+      "grad_norm": 0.3940723609427906,
+      "learning_rate": 3.9930884312309894e-05,
+      "loss": 0.9071,
+      "step": 49
+    },
+    {
+      "epoch": 0.26246719160104987,
+      "grad_norm": 0.4016006422322008,
+      "learning_rate": 3.991468352590069e-05,
+      "loss": 0.9668,
+      "step": 50
+    },
+    {
+      "epoch": 0.2677165354330709,
+      "grad_norm": 0.9528446542157881,
+      "learning_rate": 3.989678249165612e-05,
+      "loss": 1.0431,
+      "step": 51
+    },
+    {
+      "epoch": 0.27296587926509186,
+      "grad_norm": 0.41600529189619084,
+      "learning_rate": 3.987718273790548e-05,
+      "loss": 0.9464,
+      "step": 52
+    },
+    {
+      "epoch": 0.2782152230971129,
+      "grad_norm": 1.1382476752327089,
+      "learning_rate": 3.9855885938008986e-05,
+      "loss": 1.0186,
+      "step": 53
+    },
+    {
+      "epoch": 0.28346456692913385,
+      "grad_norm": 0.44849148754190465,
+      "learning_rate": 3.983289391021486e-05,
+      "loss": 0.9981,
+      "step": 54
+    },
+    {
+      "epoch": 0.2887139107611549,
+      "grad_norm": 0.4296819710357216,
+      "learning_rate": 3.9808208617504106e-05,
+      "loss": 0.9124,
+      "step": 55
+    },
+    {
+      "epoch": 0.29396325459317585,
+      "grad_norm": 1.4708100276334197,
+      "learning_rate": 3.9781832167422926e-05,
+      "loss": 1.0627,
+      "step": 56
+    },
+    {
+      "epoch": 0.2992125984251969,
+      "grad_norm": 0.436502847615945,
+      "learning_rate": 3.9753766811902756e-05,
+      "loss": 0.9399,
+      "step": 57
+    },
+    {
+      "epoch": 0.30446194225721784,
+      "grad_norm": 0.41131082586189677,
+      "learning_rate": 3.972401494706805e-05,
+      "loss": 0.9381,
+      "step": 58
+    },
+    {
+      "epoch": 0.30971128608923887,
+      "grad_norm": 0.42792569998778285,
+      "learning_rate": 3.969257911303167e-05,
+      "loss": 0.9426,
+      "step": 59
+    },
+    {
+      "epoch": 0.31496062992125984,
+      "grad_norm": 1.0484985550985957,
+      "learning_rate": 3.965946199367804e-05,
+      "loss": 1.0745,
+      "step": 60
+    },
+    {
+      "epoch": 0.32020997375328086,
+      "grad_norm": 0.45563925287513607,
+      "learning_rate": 3.962466641643398e-05,
+      "loss": 1.0085,
+      "step": 61
+    },
+    {
+      "epoch": 0.32545931758530183,
+      "grad_norm": 0.4216131864169055,
+      "learning_rate": 3.958819535202732e-05,
+      "loss": 0.9533,
+      "step": 62
+    },
+    {
+      "epoch": 0.33070866141732286,
+      "grad_norm": 0.47284588975540814,
+      "learning_rate": 3.9550051914233314e-05,
+      "loss": 0.9727,
+      "step": 63
+    },
+    {
+      "epoch": 0.3359580052493438,
+      "grad_norm": 0.4112493584955737,
+      "learning_rate": 3.951023935960874e-05,
+      "loss": 0.9408,
+      "step": 64
+    },
+    {
+      "epoch": 0.34120734908136485,
+      "grad_norm": 0.44123500755805545,
+      "learning_rate": 3.9468761087213864e-05,
+      "loss": 0.9547,
+      "step": 65
+    },
+    {
+      "epoch": 0.3464566929133858,
+      "grad_norm": 0.4160767709488051,
+      "learning_rate": 3.942562063832228e-05,
+      "loss": 0.9862,
+      "step": 66
+    },
+    {
+      "epoch": 0.35170603674540685,
+      "grad_norm": 0.40282812591350464,
+      "learning_rate": 3.9380821696118556e-05,
+      "loss": 0.9301,
+      "step": 67
+    },
+    {
+      "epoch": 0.3569553805774278,
+      "grad_norm": 0.42252313457664165,
+      "learning_rate": 3.933436808538375e-05,
+      "loss": 0.9751,
+      "step": 68
+    },
+    {
+      "epoch": 0.36220472440944884,
+      "grad_norm": 0.4084367556454159,
+      "learning_rate": 3.92862637721689e-05,
+      "loss": 0.9838,
+      "step": 69
+    },
+    {
+      "epoch": 0.3674540682414698,
+      "grad_norm": 0.39446053200993564,
+      "learning_rate": 3.923651286345638e-05,
+      "loss": 0.9237,
+      "step": 70
+    },
+    {
+      "epoch": 0.37270341207349084,
+      "grad_norm": 0.43051114259650114,
+      "learning_rate": 3.9185119606809305e-05,
+      "loss": 0.9543,
+      "step": 71
+    },
+    {
+      "epoch": 0.3779527559055118,
+      "grad_norm": 0.41527447901851827,
+      "learning_rate": 3.913208839000882e-05,
+      "loss": 0.9688,
+      "step": 72
+    },
+    {
+      "epoch": 0.38320209973753283,
+      "grad_norm": 0.4033220715509175,
+      "learning_rate": 3.907742374067956e-05,
+      "loss": 0.9401,
+      "step": 73
+    },
+    {
+      "epoch": 0.3884514435695538,
+      "grad_norm": 0.4039636146150166,
+      "learning_rate": 3.9021130325903076e-05,
+      "loss": 0.9621,
+      "step": 74
+    },
+    {
+      "epoch": 0.3937007874015748,
+      "grad_norm": 0.3896809489063709,
+      "learning_rate": 3.896321295181932e-05,
+      "loss": 0.986,
+      "step": 75
+    },
+    {
+      "epoch": 0.3989501312335958,
+      "grad_norm": 0.7547382513819603,
+      "learning_rate": 3.89036765632164e-05,
+      "loss": 1.0528,
+      "step": 76
+    },
+    {
+      "epoch": 0.4041994750656168,
+      "grad_norm": 0.42422582617937166,
+      "learning_rate": 3.8842526243108326e-05,
+      "loss": 0.9541,
+      "step": 77
+    },
+    {
+      "epoch": 0.4094488188976378,
+      "grad_norm": 0.41581388939730257,
+      "learning_rate": 3.877976721230114e-05,
+      "loss": 0.9711,
+      "step": 78
+    },
+    {
+      "epoch": 0.4146981627296588,
+      "grad_norm": 0.4326138308224312,
+      "learning_rate": 3.8715404828947055e-05,
+      "loss": 0.9261,
+      "step": 79
+    },
+    {
+      "epoch": 0.4199475065616798,
+      "grad_norm": 0.38852695749391314,
+      "learning_rate": 3.864944458808712e-05,
+      "loss": 0.9648,
+      "step": 80
+    },
+    {
+      "epoch": 0.4251968503937008,
+      "grad_norm": 0.3897195092049238,
+      "learning_rate": 3.8581892121181984e-05,
+      "loss": 0.9397,
+      "step": 81
+    },
+    {
+      "epoch": 0.4304461942257218,
+      "grad_norm": 0.43934794613481915,
+      "learning_rate": 3.851275319563113e-05,
+      "loss": 0.9905,
+      "step": 82
+    },
+    {
+      "epoch": 0.4356955380577428,
+      "grad_norm": 0.5323662587576004,
+      "learning_rate": 3.844203371428049e-05,
+      "loss": 0.9896,
+      "step": 83
+    },
+    {
+      "epoch": 0.4409448818897638,
+      "grad_norm": 0.38441956539336747,
+      "learning_rate": 3.836973971491847e-05,
+      "loss": 0.9385,
+      "step": 84
+    },
+    {
+      "epoch": 0.4461942257217848,
+      "grad_norm": 0.38662975914153885,
+      "learning_rate": 3.8295877369760426e-05,
+      "loss": 0.9586,
+      "step": 85
+    },
+    {
+      "epoch": 0.45144356955380577,
+      "grad_norm": 0.41009140101075614,
+      "learning_rate": 3.822045298492177e-05,
+      "loss": 0.9667,
+      "step": 86
+    },
+    {
+      "epoch": 0.4566929133858268,
+      "grad_norm": 0.4258642992742759,
+      "learning_rate": 3.814347299987953e-05,
+      "loss": 0.954,
+      "step": 87
+    },
+    {
+      "epoch": 0.46194225721784776,
+      "grad_norm": 0.40527142541860056,
+      "learning_rate": 3.806494398692258e-05,
+      "loss": 0.9351,
+      "step": 88
+    },
+    {
+      "epoch": 0.4671916010498688,
+      "grad_norm": 0.3743850574341336,
+      "learning_rate": 3.7984872650590516e-05,
+      "loss": 0.9498,
+      "step": 89
+    },
+    {
+      "epoch": 0.47244094488188976,
+      "grad_norm": 0.4151867667600151,
+      "learning_rate": 3.790326582710125e-05,
+      "loss": 0.9466,
+      "step": 90
+    },
+    {
+      "epoch": 0.4776902887139108,
+      "grad_norm": 0.4448011376311795,
+      "learning_rate": 3.782013048376736e-05,
+      "loss": 1.0266,
+      "step": 91
+    },
+    {
+      "epoch": 0.48293963254593175,
+      "grad_norm": 0.38192124855359877,
+      "learning_rate": 3.773547371840124e-05,
+      "loss": 0.978,
+      "step": 92
+    },
+    {
+      "epoch": 0.4881889763779528,
+      "grad_norm": 0.4235778210861527,
+      "learning_rate": 3.764930275870912e-05,
+      "loss": 0.9827,
+      "step": 93
+    },
+    {
+      "epoch": 0.49343832020997375,
+      "grad_norm": 0.4051195260626496,
+      "learning_rate": 3.756162496167396e-05,
+      "loss": 0.963,
+      "step": 94
+    },
+    {
+      "epoch": 0.49868766404199477,
+      "grad_norm": 0.40700055373961197,
+      "learning_rate": 3.7472447812927395e-05,
+      "loss": 0.9437,
+      "step": 95
+    },
+    {
+      "epoch": 0.5039370078740157,
+      "grad_norm": 0.38712614108502513,
+      "learning_rate": 3.738177892611057e-05,
+      "loss": 0.955,
+      "step": 96
+    },
+    {
+      "epoch": 0.5091863517060368,
+      "grad_norm": 0.4099596350735423,
+      "learning_rate": 3.728962604222416e-05,
+      "loss": 0.9741,
+      "step": 97
+    },
+    {
+      "epoch": 0.5144356955380578,
+      "grad_norm": 0.40040635119594403,
+      "learning_rate": 3.719599702896745e-05,
+      "loss": 0.9528,
+      "step": 98
+    },
+    {
+      "epoch": 0.5196850393700787,
+      "grad_norm": 0.4136053200425271,
+      "learning_rate": 3.710089988006662e-05,
+      "loss": 0.9466,
+      "step": 99
+    },
+    {
+      "epoch": 0.5249343832020997,
+      "grad_norm": 0.41412239719227456,
+      "learning_rate": 3.700434271459229e-05,
+      "loss": 0.9242,
+      "step": 100
+    },
+    {
+      "epoch": 0.5301837270341208,
+      "grad_norm": 0.4309979528684408,
+      "learning_rate": 3.690633377626628e-05,
+      "loss": 0.9861,
+      "step": 101
+    },
+    {
+      "epoch": 0.5354330708661418,
+      "grad_norm": 0.4064293156979199,
+      "learning_rate": 3.680688143275786e-05,
+      "loss": 0.931,
+      "step": 102
+    },
+    {
+      "epoch": 0.5406824146981627,
+      "grad_norm": 0.4463450853160405,
+      "learning_rate": 3.670599417496931e-05,
+      "loss": 0.9084,
+      "step": 103
+    },
+    {
+      "epoch": 0.5459317585301837,
+      "grad_norm": 0.4542877579158036,
+      "learning_rate": 3.6603680616311013e-05,
+      "loss": 0.9561,
+      "step": 104
+    },
+    {
+      "epoch": 0.5511811023622047,
+      "grad_norm": 0.4606576229715047,
+      "learning_rate": 3.6499949491966046e-05,
+      "loss": 0.9424,
+      "step": 105
+    },
+    {
+      "epoch": 0.5564304461942258,
+      "grad_norm": 1.6662857295077933,
+      "learning_rate": 3.639480965814443e-05,
+      "loss": 1.0371,
+      "step": 106
+    },
+    {
+      "epoch": 0.5616797900262467,
+      "grad_norm": 0.42684188670392853,
+      "learning_rate": 3.628827009132697e-05,
+      "loss": 0.9635,
+      "step": 107
+    },
+    {
+      "epoch": 0.5669291338582677,
+      "grad_norm": 1.2208350090054685,
+      "learning_rate": 3.6180339887498953e-05,
+      "loss": 0.9917,
+      "step": 108
+    },
+    {
+      "epoch": 0.5721784776902887,
+      "grad_norm": 0.4294502318914682,
+      "learning_rate": 3.6071028261373474e-05,
+      "loss": 0.9446,
+      "step": 109
+    },
+    {
+      "epoch": 0.5774278215223098,
+      "grad_norm": 0.3937562720593612,
+      "learning_rate": 3.5960344545604796e-05,
+      "loss": 0.9278,
+      "step": 110
+    },
+    {
+      "epoch": 0.5826771653543307,
+      "grad_norm": 1.4854854417438403,
+      "learning_rate": 3.584829818999148e-05,
+      "loss": 1.0161,
+      "step": 111
+    },
+    {
+      "epoch": 0.5879265091863517,
+      "grad_norm": 0.4240627994414154,
+      "learning_rate": 3.573489876066967e-05,
+      "loss": 0.9483,
+      "step": 112
+    },
+    {
+      "epoch": 0.5931758530183727,
+      "grad_norm": 0.3995864923040328,
+      "learning_rate": 3.5620155939296314e-05,
+      "loss": 0.9426,
+      "step": 113
+    },
+    {
+      "epoch": 0.5984251968503937,
+      "grad_norm": 0.4085167442197417,
+      "learning_rate": 3.55040795222226e-05,
+      "loss": 0.9189,
+      "step": 114
+    },
+    {
+      "epoch": 0.6036745406824147,
+      "grad_norm": 0.411605976954782,
+      "learning_rate": 3.538667941965758e-05,
+      "loss": 0.9406,
+      "step": 115
+    },
+    {
+      "epoch": 0.6089238845144357,
+      "grad_norm": 0.4510885035850897,
+      "learning_rate": 3.526796565482206e-05,
+      "loss": 0.9609,
+      "step": 116
+    },
+    {
+      "epoch": 0.6141732283464567,
+      "grad_norm": 0.39711542861711363,
+      "learning_rate": 3.514794836309286e-05,
+      "loss": 0.9353,
+      "step": 117
+    },
+    {
+      "epoch": 0.6194225721784777,
+      "grad_norm": 0.3860750426711258,
+      "learning_rate": 3.502663779113747e-05,
+      "loss": 0.9168,
+      "step": 118
+    },
+    {
+      "epoch": 0.6246719160104987,
+      "grad_norm": 0.4324143866853257,
+      "learning_rate": 3.490404429603925e-05,
+      "loss": 0.9412,
+      "step": 119
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "grad_norm": 0.42486288700695524,
+      "learning_rate": 3.478017834441319e-05,
+      "loss": 0.9967,
+      "step": 120
+    },
+    {
+      "epoch": 0.6351706036745407,
+      "grad_norm": 0.42059534343716903,
+      "learning_rate": 3.4655050511512236e-05,
+      "loss": 0.9042,
+      "step": 121
+    },
+    {
+      "epoch": 0.6404199475065617,
+      "grad_norm": 0.375540386715667,
+      "learning_rate": 3.452867148032449e-05,
+      "loss": 0.9261,
+      "step": 122
+    },
+    {
+      "epoch": 0.6456692913385826,
+      "grad_norm": 0.38698966212541075,
+      "learning_rate": 3.44010520406611e-05,
+      "loss": 0.9252,
+      "step": 123
+    },
+    {
+      "epoch": 0.6509186351706037,
+      "grad_norm": 0.41709615104288367,
+      "learning_rate": 3.427220308823505e-05,
+      "loss": 0.9253,
+      "step": 124
+    },
+    {
+      "epoch": 0.6561679790026247,
+      "grad_norm": 0.4293707133542124,
+      "learning_rate": 3.4142135623730954e-05,
+      "loss": 0.9545,
+      "step": 125
+    },
+    {
+      "epoch": 0.6614173228346457,
+      "grad_norm": 0.40563024635145306,
+      "learning_rate": 3.401086075186582e-05,
+      "loss": 0.9424,
+      "step": 126
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.47226124502094396,
+      "learning_rate": 3.3878389680440995e-05,
+      "loss": 0.9408,
+      "step": 127
+    },
+    {
+      "epoch": 0.6719160104986877,
+      "grad_norm": 0.3921360030995963,
+      "learning_rate": 3.374473371938526e-05,
+      "loss": 0.9309,
+      "step": 128
+    },
+    {
+      "epoch": 0.6771653543307087,
+      "grad_norm": 0.4188603496902975,
+      "learning_rate": 3.3609904279789235e-05,
+      "loss": 0.9625,
+      "step": 129
+    },
+    {
+      "epoch": 0.6824146981627297,
+      "grad_norm": 0.40729320283126413,
+      "learning_rate": 3.347391287293115e-05,
+      "loss": 0.9222,
+      "step": 130
+    },
+    {
+      "epoch": 0.6876640419947506,
+      "grad_norm": 0.43355828675253894,
+      "learning_rate": 3.333677110929403e-05,
+      "loss": 0.9245,
+      "step": 131
+    },
+    {
+      "epoch": 0.6929133858267716,
+      "grad_norm": 0.40875412645403303,
+      "learning_rate": 3.319849069757446e-05,
+      "loss": 0.9416,
+      "step": 132
+    },
+    {
+      "epoch": 0.6981627296587927,
+      "grad_norm": 0.4184583102080097,
+      "learning_rate": 3.305908344368289e-05,
+      "loss": 0.9575,
+      "step": 133
+    },
+    {
+      "epoch": 0.7034120734908137,
+      "grad_norm": 0.37949729176161695,
+      "learning_rate": 3.291856124973575e-05,
+      "loss": 0.9283,
+      "step": 134
+    },
+    {
+      "epoch": 0.7086614173228346,
+      "grad_norm": 0.4359197990076154,
+      "learning_rate": 3.277693611303922e-05,
+      "loss": 0.9591,
+      "step": 135
+    },
+    {
+      "epoch": 0.7139107611548556,
+      "grad_norm": 0.4127988509227564,
+      "learning_rate": 3.263422012506502e-05,
+      "loss": 0.9507,
+      "step": 136
+    },
+    {
+      "epoch": 0.7191601049868767,
+      "grad_norm": 0.4119681718108907,
+      "learning_rate": 3.249042547041799e-05,
+      "loss": 0.9252,
+      "step": 137
+    },
+    {
+      "epoch": 0.7244094488188977,
+      "grad_norm": 0.4155554867266832,
+      "learning_rate": 3.234556442579586e-05,
+      "loss": 0.9263,
+      "step": 138
+    },
+    {
+      "epoch": 0.7296587926509186,
+      "grad_norm": 0.37277040517135684,
+      "learning_rate": 3.219964935894114e-05,
+      "loss": 0.9544,
+      "step": 139
+    },
+    {
+      "epoch": 0.7349081364829396,
+      "grad_norm": 0.41745861140292206,
+      "learning_rate": 3.205269272758513e-05,
+      "loss": 0.9213,
+      "step": 140
+    },
+    {
+      "epoch": 0.7401574803149606,
+      "grad_norm": 0.41788351218514774,
+      "learning_rate": 3.190470707838438e-05,
+      "loss": 0.9429,
+      "step": 141
+    },
+    {
+      "epoch": 0.7454068241469817,
+      "grad_norm": 0.3994620013935183,
+      "learning_rate": 3.1755705045849465e-05,
+      "loss": 0.9065,
+      "step": 142
+    },
+    {
+      "epoch": 0.7506561679790026,
+      "grad_norm": 0.4006844018528632,
+      "learning_rate": 3.160569935126632e-05,
+      "loss": 0.9064,
+      "step": 143
+    },
+    {
+      "epoch": 0.7559055118110236,
+      "grad_norm": 0.44223134289541643,
+      "learning_rate": 3.145470280161011e-05,
+      "loss": 0.9247,
+      "step": 144
+    },
+    {
+      "epoch": 0.7611548556430446,
+      "grad_norm": 0.41494829719611687,
+      "learning_rate": 3.130272828845184e-05,
+      "loss": 0.9126,
+      "step": 145
+    },
+    {
+      "epoch": 0.7664041994750657,
+      "grad_norm": 0.38947944768031434,
+      "learning_rate": 3.114978878685771e-05,
+      "loss": 0.8928,
+      "step": 146
+    },
+    {
+      "epoch": 0.7716535433070866,
+      "grad_norm": 0.3945361927140775,
+      "learning_rate": 3.0995897354281347e-05,
+      "loss": 0.889,
+      "step": 147
+    },
+    {
+      "epoch": 0.7769028871391076,
+      "grad_norm": 0.39978716157020916,
+      "learning_rate": 3.084106712944899e-05,
+      "loss": 0.9227,
+      "step": 148
+    },
+    {
+      "epoch": 0.7821522309711286,
+      "grad_norm": 0.39603745657551037,
+      "learning_rate": 3.068531133123777e-05,
+      "loss": 0.8969,
+      "step": 149
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "grad_norm": 1.3504046960889928,
+      "learning_rate": 3.052864325754712e-05,
+      "loss": 1.0631,
+      "step": 150
+    },
+    {
+      "epoch": 0.7926509186351706,
+      "grad_norm": 0.4310383398496922,
+      "learning_rate": 3.0371076284163442e-05,
+      "loss": 0.9262,
+      "step": 151
+    },
+    {
+      "epoch": 0.7979002624671916,
+      "grad_norm": 0.41699772424137066,
+      "learning_rate": 3.021262386361814e-05,
+      "loss": 0.9352,
+      "step": 152
+    },
+    {
+      "epoch": 0.8031496062992126,
+      "grad_norm": 0.4056852584293386,
+      "learning_rate": 3.0053299524039077e-05,
+      "loss": 0.8957,
+      "step": 153
+    },
+    {
+      "epoch": 0.8083989501312336,
+      "grad_norm": 0.4308645558537417,
+      "learning_rate": 2.9893116867995583e-05,
+      "loss": 0.9137,
+      "step": 154
+    },
+    {
+      "epoch": 0.8136482939632546,
+      "grad_norm": 0.39136699559712107,
+      "learning_rate": 2.9732089571337126e-05,
+      "loss": 0.9392,
+      "step": 155
+    },
+    {
+      "epoch": 0.8188976377952756,
+      "grad_norm": 0.39692286867805615,
+      "learning_rate": 2.9570231382025732e-05,
+      "loss": 0.9319,
+      "step": 156
+    },
+    {
+      "epoch": 0.8241469816272966,
+      "grad_norm": 0.389760753952324,
+      "learning_rate": 2.9407556118962192e-05,
+      "loss": 0.9328,
+      "step": 157
+    },
+    {
+      "epoch": 0.8293963254593176,
+      "grad_norm": 0.40644738344754366,
+      "learning_rate": 2.924407767080627e-05,
+      "loss": 0.9511,
+      "step": 158
+    },
+    {
+      "epoch": 0.8346456692913385,
+      "grad_norm": 0.4235598803780184,
+      "learning_rate": 2.9079809994790937e-05,
+      "loss": 0.9443,
+      "step": 159
+    },
+    {
+      "epoch": 0.8398950131233596,
+      "grad_norm": 0.39469735698768543,
+      "learning_rate": 2.891476711553077e-05,
+      "loss": 0.9353,
+      "step": 160
+    },
+    {
+      "epoch": 0.8451443569553806,
+      "grad_norm": 0.4231486830962651,
+      "learning_rate": 2.8748963123824532e-05,
+      "loss": 0.9598,
+      "step": 161
+    },
+    {
+      "epoch": 0.8503937007874016,
+      "grad_norm": 0.4016499332546737,
+      "learning_rate": 2.858241217545218e-05,
+      "loss": 0.9182,
+      "step": 162
+    },
+    {
+      "epoch": 0.8556430446194225,
+      "grad_norm": 0.7416569697844047,
+      "learning_rate": 2.8415128489966308e-05,
+      "loss": 1.017,
+      "step": 163
+    },
+    {
+      "epoch": 0.8608923884514436,
+      "grad_norm": 0.4049886957012087,
+      "learning_rate": 2.8247126349478073e-05,
+      "loss": 0.9377,
+      "step": 164
+    },
+    {
+      "epoch": 0.8661417322834646,
+      "grad_norm": 0.4240641122781046,
+      "learning_rate": 2.80784200974379e-05,
+      "loss": 0.936,
+      "step": 165
+    },
+    {
+      "epoch": 0.8713910761154856,
+      "grad_norm": 0.4010428790320475,
+      "learning_rate": 2.790902413741085e-05,
+      "loss": 0.9076,
+      "step": 166
+    },
+    {
+      "epoch": 0.8766404199475065,
+      "grad_norm": 0.40515062001849617,
+      "learning_rate": 2.773895293184691e-05,
+      "loss": 0.9144,
+      "step": 167
+    },
+    {
+      "epoch": 0.8818897637795275,
+      "grad_norm": 0.4171752905975984,
+      "learning_rate": 2.756822100084621e-05,
+      "loss": 0.9302,
+      "step": 168
+    },
+    {
+      "epoch": 0.8871391076115486,
+      "grad_norm": 0.4018514009140958,
+      "learning_rate": 2.7396842920919384e-05,
+      "loss": 0.9208,
+      "step": 169
+    },
+    {
+      "epoch": 0.8923884514435696,
+      "grad_norm": 0.39277733117068253,
+      "learning_rate": 2.7224833323743064e-05,
+      "loss": 0.9116,
+      "step": 170
+    },
+    {
+      "epoch": 0.8976377952755905,
+      "grad_norm": 0.6692602521355003,
+      "learning_rate": 2.7052206894910653e-05,
+      "loss": 1.0122,
+      "step": 171
+    },
+    {
+      "epoch": 0.9028871391076115,
+      "grad_norm": 0.40843018046933677,
+      "learning_rate": 2.6878978372678567e-05,
+      "loss": 0.9014,
+      "step": 172
+    },
+    {
+      "epoch": 0.9081364829396326,
+      "grad_norm": 0.3862093081092539,
+      "learning_rate": 2.670516254670788e-05,
+      "loss": 0.9367,
+      "step": 173
+    },
+    {
+      "epoch": 0.9133858267716536,
+      "grad_norm": 0.39106222738031376,
+      "learning_rate": 2.6530774256801666e-05,
+      "loss": 0.9253,
+      "step": 174
+    },
+    {
+      "epoch": 0.9186351706036745,
+      "grad_norm": 0.409656789286683,
+      "learning_rate": 2.6355828391638036e-05,
+      "loss": 0.9259,
+      "step": 175
+    },
+    {
+      "epoch": 0.9238845144356955,
+      "grad_norm": 0.41048542482358136,
+      "learning_rate": 2.618033988749895e-05,
+      "loss": 0.9151,
+      "step": 176
+    },
+    {
+      "epoch": 0.9291338582677166,
+      "grad_norm": 0.39649048041899354,
+      "learning_rate": 2.6004323726995057e-05,
+      "loss": 0.9197,
+      "step": 177
+    },
+    {
+      "epoch": 0.9343832020997376,
+      "grad_norm": 0.4041163682720282,
+      "learning_rate": 2.5827794937786497e-05,
+      "loss": 0.9184,
+      "step": 178
+    },
+    {
+      "epoch": 0.9396325459317585,
+      "grad_norm": 0.40988870079100986,
+      "learning_rate": 2.5650768591299905e-05,
+      "loss": 0.9376,
+      "step": 179
+    },
+    {
+      "epoch": 0.9448818897637795,
+      "grad_norm": 0.3918596025187431,
+      "learning_rate": 2.5473259801441663e-05,
+      "loss": 0.9102,
+      "step": 180
+    },
+    {
+      "epoch": 0.9501312335958005,
+      "grad_norm": 0.39082215171197704,
+      "learning_rate": 2.5295283723307517e-05,
+      "loss": 0.9025,
+      "step": 181
+    },
+    {
+      "epoch": 0.9553805774278216,
+      "grad_norm": 0.38010414440929924,
+      "learning_rate": 2.5116855551888715e-05,
+      "loss": 0.9354,
+      "step": 182
+    },
+    {
+      "epoch": 0.9606299212598425,
+      "grad_norm": 0.4141554447250008,
+      "learning_rate": 2.4937990520774664e-05,
+      "loss": 0.8782,
+      "step": 183
+    },
+    {
+      "epoch": 0.9658792650918635,
+      "grad_norm": 0.38201600299774646,
+      "learning_rate": 2.4758703900852376e-05,
+      "loss": 0.9008,
+      "step": 184
+    },
+    {
+      "epoch": 0.9711286089238845,
+      "grad_norm": 0.42204019171609175,
+      "learning_rate": 2.4579010999002683e-05,
+      "loss": 0.8856,
+      "step": 185
+    },
+    {
+      "epoch": 0.9763779527559056,
+      "grad_norm": 0.4270135581368761,
+      "learning_rate": 2.4398927156793376e-05,
+      "loss": 0.9205,
+      "step": 186
+    },
+    {
+      "epoch": 0.9816272965879265,
+      "grad_norm": 0.4150364763728507,
+      "learning_rate": 2.42184677491694e-05,
+      "loss": 0.8947,
+      "step": 187
+    },
+    {
+      "epoch": 0.9868766404199475,
+      "grad_norm": 0.51571681852072,
+      "learning_rate": 2.4037648183140205e-05,
+      "loss": 0.9929,
+      "step": 188
+    },
+    {
+      "epoch": 0.9921259842519685,
+      "grad_norm": 0.38917079851953085,
+      "learning_rate": 2.385648389646434e-05,
+      "loss": 0.9121,
+      "step": 189
+    },
+    {
+      "epoch": 0.9973753280839895,
+      "grad_norm": 0.45530540311855816,
+      "learning_rate": 2.367499035633141e-05,
+      "loss": 0.9113,
+      "step": 190
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.45530540311855816,
+      "learning_rate": 2.3493183058041578e-05,
+      "loss": 0.9347,
+      "step": 191
+    },
+    {
+      "epoch": 1.005249343832021,
+      "grad_norm": 0.7905516160996418,
+      "learning_rate": 2.33110775236826e-05,
+      "loss": 0.6378,
+      "step": 192
+    },
+    {
+      "epoch": 1.010498687664042,
+      "grad_norm": 0.5781672455733289,
+      "learning_rate": 2.312868930080462e-05,
+      "loss": 0.639,
+      "step": 193
+    },
+    {
+      "epoch": 1.015748031496063,
+      "grad_norm": 1.0363184255291382,
+      "learning_rate": 2.2946033961092754e-05,
+      "loss": 0.6442,
+      "step": 194
+    },
+    {
+      "epoch": 1.020997375328084,
+      "grad_norm": 0.4833222962879287,
+      "learning_rate": 2.2763127099037646e-05,
+      "loss": 0.6441,
+      "step": 195
+    },
+    {
+      "epoch": 1.026246719160105,
+      "grad_norm": 0.5713369686471519,
+      "learning_rate": 2.257998433060407e-05,
+      "loss": 0.6667,
+      "step": 196
+    },
+    {
+      "epoch": 1.031496062992126,
+      "grad_norm": 0.4764665095808476,
+      "learning_rate": 2.2396621291897666e-05,
+      "loss": 0.6407,
+      "step": 197
+    },
+    {
+      "epoch": 1.036745406824147,
+      "grad_norm": 0.4588405259893301,
+      "learning_rate": 2.2213053637830016e-05,
+      "loss": 0.6146,
+      "step": 198
+    },
+    {
+      "epoch": 1.041994750656168,
+      "grad_norm": 0.42224522477353676,
+      "learning_rate": 2.2029297040782063e-05,
+      "loss": 0.6108,
+      "step": 199
+    },
+    {
+      "epoch": 1.047244094488189,
+      "grad_norm": 0.43495470036978195,
+      "learning_rate": 2.184536718926604e-05,
+      "loss": 0.6091,
+      "step": 200
+    },
+    {
+      "epoch": 1.05249343832021,
+      "grad_norm": 0.3908883372852395,
+      "learning_rate": 2.166127978658608e-05,
+      "loss": 0.618,
+      "step": 201
+    },
+    {
+      "epoch": 1.057742782152231,
+      "grad_norm": 0.41668658316901935,
+      "learning_rate": 2.147705054949748e-05,
+      "loss": 0.6345,
+      "step": 202
+    },
+    {
+      "epoch": 1.0629921259842519,
+      "grad_norm": 0.38162610574666733,
+      "learning_rate": 2.1292695206864887e-05,
+      "loss": 0.6077,
+      "step": 203
+    },
+    {
+      "epoch": 1.068241469816273,
+      "grad_norm": 0.359243479327879,
+      "learning_rate": 2.11082294983194e-05,
+      "loss": 0.6008,
+      "step": 204
+    },
+    {
+      "epoch": 1.073490813648294,
+      "grad_norm": 0.338388070214759,
+      "learning_rate": 2.0923669172914796e-05,
+      "loss": 0.6198,
+      "step": 205
+    },
+    {
+      "epoch": 1.078740157480315,
+      "grad_norm": 0.3736442857329487,
+      "learning_rate": 2.0739029987782903e-05,
+      "loss": 0.6038,
+      "step": 206
+    },
+    {
+      "epoch": 1.083989501312336,
+      "grad_norm": 0.38343041994799376,
+      "learning_rate": 2.055432770678833e-05,
+      "loss": 0.6283,
+      "step": 207
+    },
+    {
+      "epoch": 1.0892388451443569,
+      "grad_norm": 0.3839775235441468,
+      "learning_rate": 2.03695780991826e-05,
+      "loss": 0.621,
+      "step": 208
+    },
+    {
+      "epoch": 1.094488188976378,
+      "grad_norm": 0.4026675034831997,
+      "learning_rate": 2.018479693825782e-05,
+      "loss": 0.5967,
+      "step": 209
+    },
+    {
+      "epoch": 1.099737532808399,
+      "grad_norm": 0.354604482258031,
+      "learning_rate": 2e-05,
+      "loss": 0.5747,
+      "step": 210
+    },
+    {
+      "epoch": 1.10498687664042,
+      "grad_norm": 0.37448103017465234,
+      "learning_rate": 1.9815203061742188e-05,
+      "loss": 0.6207,
+      "step": 211
+    },
+    {
+      "epoch": 1.110236220472441,
+      "grad_norm": 0.3731173545168172,
+      "learning_rate": 1.9630421900817407e-05,
+      "loss": 0.6658,
+      "step": 212
+    },
+    {
+      "epoch": 1.1154855643044619,
+      "grad_norm": 0.4440821296075456,
+      "learning_rate": 1.9445672293211675e-05,
+      "loss": 0.6147,
+      "step": 213
+    },
+    {
+      "epoch": 1.120734908136483,
+      "grad_norm": 0.37062388694479104,
+      "learning_rate": 1.9260970012217107e-05,
+      "loss": 0.6235,
+      "step": 214
+    },
+    {
+      "epoch": 1.125984251968504,
+      "grad_norm": 0.352789345485834,
+      "learning_rate": 1.9076330827085214e-05,
+      "loss": 0.6186,
+      "step": 215
+    },
+    {
+      "epoch": 1.1312335958005248,
+      "grad_norm": 0.3510249370323435,
+      "learning_rate": 1.8891770501680602e-05,
+      "loss": 0.5919,
+      "step": 216
+    },
+    {
+      "epoch": 1.136482939632546,
+      "grad_norm": 0.36641452500356003,
+      "learning_rate": 1.8707304793135117e-05,
+      "loss": 0.6325,
+      "step": 217
+    },
+    {
+      "epoch": 1.141732283464567,
+      "grad_norm": 0.46538331418150264,
+      "learning_rate": 1.8522949450502522e-05,
+      "loss": 0.6314,
+      "step": 218
+    },
+    {
+      "epoch": 1.1469816272965878,
+      "grad_norm": 0.35158983297625845,
+      "learning_rate": 1.8338720213413924e-05,
+      "loss": 0.6171,
+      "step": 219
+    },
+    {
+      "epoch": 1.152230971128609,
+      "grad_norm": 0.34039327733619856,
+      "learning_rate": 1.815463281073396e-05,
+      "loss": 0.5929,
+      "step": 220
+    },
+    {
+      "epoch": 1.1574803149606299,
+      "grad_norm": 0.3583390822597362,
+      "learning_rate": 1.7970702959217944e-05,
+      "loss": 0.5666,
+      "step": 221
+    },
+    {
+      "epoch": 1.162729658792651,
+      "grad_norm": 0.3328969811354483,
+      "learning_rate": 1.7786946362169987e-05,
+      "loss": 0.6165,
+      "step": 222
+    },
+    {
+      "epoch": 1.167979002624672,
+      "grad_norm": 0.35808562196234894,
+      "learning_rate": 1.760337870810234e-05,
+      "loss": 0.5907,
+      "step": 223
+    },
+    {
+      "epoch": 1.1732283464566928,
+      "grad_norm": 0.3330883120593054,
+      "learning_rate": 1.742001566939594e-05,
+      "loss": 0.6139,
+      "step": 224
+    },
+    {
+      "epoch": 1.178477690288714,
+      "grad_norm": 0.3477344689492317,
+      "learning_rate": 1.7236872900962364e-05,
+      "loss": 0.5772,
+      "step": 225
+    },
+    {
+      "epoch": 1.1837270341207349,
+      "grad_norm": 0.3636049536281939,
+      "learning_rate": 1.705396603890725e-05,
+      "loss": 0.6101,
+      "step": 226
+    },
+    {
+      "epoch": 1.188976377952756,
+      "grad_norm": 0.5140813534017206,
+      "learning_rate": 1.687131069919538e-05,
+      "loss": 0.6455,
+      "step": 227
+    },
+    {
+      "epoch": 1.194225721784777,
+      "grad_norm": 0.3445915498918541,
+      "learning_rate": 1.66889224763174e-05,
+      "loss": 0.6253,
+      "step": 228
+    },
+    {
+      "epoch": 1.1994750656167978,
+      "grad_norm": 0.3817825400306628,
+      "learning_rate": 1.6506816941958425e-05,
+      "loss": 0.6264,
+      "step": 229
+    },
+    {
+      "epoch": 1.204724409448819,
+      "grad_norm": 0.3871021865440479,
+      "learning_rate": 1.6325009643668592e-05,
+      "loss": 0.5875,
+      "step": 230
+    },
+    {
+      "epoch": 1.20997375328084,
+      "grad_norm": 0.4003951939816748,
+      "learning_rate": 1.6143516103535666e-05,
+      "loss": 0.6068,
+      "step": 231
+    },
+    {
+      "epoch": 1.2152230971128608,
+      "grad_norm": 0.377400380096938,
+      "learning_rate": 1.59623518168598e-05,
+      "loss": 0.6216,
+      "step": 232
+    },
+    {
+      "epoch": 1.220472440944882,
+      "grad_norm": 0.3523802116183249,
+      "learning_rate": 1.578153225083061e-05,
+      "loss": 0.5773,
+      "step": 233
+    },
+    {
+      "epoch": 1.2257217847769029,
+      "grad_norm": 0.3774158319806266,
+      "learning_rate": 1.5601072843206634e-05,
+      "loss": 0.6485,
+      "step": 234
+    },
+    {
+      "epoch": 1.2309711286089238,
+      "grad_norm": 0.35618682756111997,
+      "learning_rate": 1.5420989000997324e-05,
+      "loss": 0.57,
+      "step": 235
+    },
+    {
+      "epoch": 1.236220472440945,
+      "grad_norm": 0.329939498867074,
+      "learning_rate": 1.524129609914763e-05,
+      "loss": 0.5922,
+      "step": 236
+    },
+    {
+      "epoch": 1.2414698162729658,
+      "grad_norm": 0.3694137451232253,
+      "learning_rate": 1.5062009479225336e-05,
+      "loss": 0.614,
+      "step": 237
+    },
+    {
+      "epoch": 1.246719160104987,
+      "grad_norm": 0.33955880982317405,
+      "learning_rate": 1.4883144448111288e-05,
+      "loss": 0.5734,
+      "step": 238
+    },
+    {
+      "epoch": 1.2519685039370079,
+      "grad_norm": 0.34083473110033147,
+      "learning_rate": 1.4704716276692483e-05,
+      "loss": 0.5838,
+      "step": 239
+    },
+    {
+      "epoch": 1.257217847769029,
+      "grad_norm": 0.33904875318136807,
+      "learning_rate": 1.4526740198558345e-05,
+      "loss": 0.5721,
+      "step": 240
+    },
+    {
+      "epoch": 1.26246719160105,
+      "grad_norm": 0.3452861169118219,
+      "learning_rate": 1.43492314087001e-05,
+      "loss": 0.5978,
+      "step": 241
+    },
+    {
+      "epoch": 1.2677165354330708,
+      "grad_norm": 0.36203138569672677,
+      "learning_rate": 1.417220506221351e-05,
+      "loss": 0.6061,
+      "step": 242
+    },
+    {
+      "epoch": 1.272965879265092,
+      "grad_norm": 0.3423141141716414,
+      "learning_rate": 1.3995676273004948e-05,
+      "loss": 0.617,
+      "step": 243
+    },
+    {
+      "epoch": 1.2782152230971129,
+      "grad_norm": 0.35751648695826527,
+      "learning_rate": 1.3819660112501054e-05,
+      "loss": 0.6393,
+      "step": 244
+    },
+    {
+      "epoch": 1.2834645669291338,
+      "grad_norm": 0.3703820503916198,
+      "learning_rate": 1.364417160836197e-05,
+      "loss": 0.6767,
+      "step": 245
+    },
+    {
+      "epoch": 1.288713910761155,
+      "grad_norm": 0.48807956046543455,
+      "learning_rate": 1.3469225743198337e-05,
+      "loss": 0.6156,
+      "step": 246
+    },
+    {
+      "epoch": 1.2939632545931758,
+      "grad_norm": 0.3687500146311602,
+      "learning_rate": 1.329483745329213e-05,
+      "loss": 0.6587,
+      "step": 247
+    },
+    {
+      "epoch": 1.2992125984251968,
+      "grad_norm": 0.5835964568778699,
+      "learning_rate": 1.3121021627321438e-05,
+      "loss": 0.5912,
+      "step": 248
+    },
+    {
+      "epoch": 1.304461942257218,
+      "grad_norm": 0.35312287301928247,
+      "learning_rate": 1.2947793105089347e-05,
+      "loss": 0.622,
+      "step": 249
+    },
+    {
+      "epoch": 1.3097112860892388,
+      "grad_norm": 0.3442037878519564,
+      "learning_rate": 1.2775166676256942e-05,
+      "loss": 0.5905,
+      "step": 250
+    },
+    {
+      "epoch": 1.3149606299212597,
+      "grad_norm": 0.3407336842366384,
+      "learning_rate": 1.260315707908062e-05,
+      "loss": 0.6023,
+      "step": 251
+    },
+    {
+      "epoch": 1.3202099737532809,
+      "grad_norm": 0.3532792670283708,
+      "learning_rate": 1.2431778999153796e-05,
+      "loss": 0.5994,
+      "step": 252
+    },
+    {
+      "epoch": 1.3254593175853018,
+      "grad_norm": 0.33944334283473854,
+      "learning_rate": 1.2261047068153098e-05,
+      "loss": 0.6136,
+      "step": 253
+    },
+    {
+      "epoch": 1.330708661417323,
+      "grad_norm": 0.32837150028469475,
+      "learning_rate": 1.2090975862589151e-05,
+      "loss": 0.6655,
+      "step": 254
+    },
+    {
+      "epoch": 1.3359580052493438,
+      "grad_norm": 0.4777003027087777,
+      "learning_rate": 1.1921579902562103e-05,
+      "loss": 0.6005,
+      "step": 255
+    },
+    {
+      "epoch": 1.341207349081365,
+      "grad_norm": 0.3348911333128937,
+      "learning_rate": 1.1752873650521934e-05,
+      "loss": 0.5908,
+      "step": 256
+    },
+    {
+      "epoch": 1.3464566929133859,
+      "grad_norm": 0.32219847234981497,
+      "learning_rate": 1.1584871510033707e-05,
+      "loss": 0.599,
+      "step": 257
+    },
+    {
+      "epoch": 1.3517060367454068,
+      "grad_norm": 0.32820186480956876,
+      "learning_rate": 1.1417587824547822e-05,
+      "loss": 0.5949,
+      "step": 258
+    },
+    {
+      "epoch": 1.356955380577428,
+      "grad_norm": 0.35813565851987533,
+      "learning_rate": 1.1251036876175476e-05,
+      "loss": 0.6273,
+      "step": 259
+    },
+    {
+      "epoch": 1.3622047244094488,
+      "grad_norm": 0.34029610416797407,
+      "learning_rate": 1.1085232884469236e-05,
+      "loss": 0.6026,
+      "step": 260
+    },
+    {
+      "epoch": 1.3674540682414698,
+      "grad_norm": 0.3319785571663989,
+      "learning_rate": 1.0920190005209066e-05,
+      "loss": 0.5993,
+      "step": 261
+    },
+    {
+      "epoch": 1.372703412073491,
+      "grad_norm": 0.3368980390679111,
+      "learning_rate": 1.0755922329193739e-05,
+      "loss": 0.5763,
+      "step": 262
+    },
+    {
+      "epoch": 1.3779527559055118,
+      "grad_norm": 0.32898129554439637,
+      "learning_rate": 1.0592443881037816e-05,
+      "loss": 0.5687,
+      "step": 263
+    },
+    {
+      "epoch": 1.3832020997375327,
+      "grad_norm": 0.3518104139897649,
+      "learning_rate": 1.0429768617974271e-05,
+      "loss": 0.5934,
+      "step": 264
+    },
+    {
+      "epoch": 1.3884514435695539,
+      "grad_norm": 0.329339944599712,
+      "learning_rate": 1.0267910428662878e-05,
+      "loss": 0.6384,
+      "step": 265
+    },
+    {
+      "epoch": 1.3937007874015748,
+      "grad_norm": 0.3385813426254148,
+      "learning_rate": 1.0106883132004428e-05,
+      "loss": 0.6055,
+      "step": 266
+    },
+    {
+      "epoch": 1.3989501312335957,
+      "grad_norm": 0.36895054605374145,
+      "learning_rate": 9.946700475960933e-06,
+      "loss": 0.6145,
+      "step": 267
+    },
+    {
+      "epoch": 1.4041994750656168,
+      "grad_norm": 0.3996589842241198,
+      "learning_rate": 9.787376136381866e-06,
+      "loss": 0.5953,
+      "step": 268
+    },
+    {
+      "epoch": 1.4094488188976377,
+      "grad_norm": 0.32114805305907074,
+      "learning_rate": 9.628923715836558e-06,
+      "loss": 0.5807,
+      "step": 269
+    },
+    {
+      "epoch": 1.4146981627296589,
+      "grad_norm": 0.3463735106041919,
+      "learning_rate": 9.471356742452881e-06,
+      "loss": 0.5991,
+      "step": 270
+    },
+    {
+      "epoch": 1.4199475065616798,
+      "grad_norm": 0.3218652005510028,
+      "learning_rate": 9.314688668762232e-06,
+      "loss": 0.615,
+      "step": 271
+    },
+    {
+      "epoch": 1.425196850393701,
+      "grad_norm": 0.35660358239424667,
+      "learning_rate": 9.158932870551012e-06,
+      "loss": 0.5915,
+      "step": 272
+    },
+    {
+      "epoch": 1.4304461942257218,
+      "grad_norm": 0.328623251389403,
+      "learning_rate": 9.004102645718655e-06,
+      "loss": 0.594,
+      "step": 273
+    },
+    {
+      "epoch": 1.4356955380577427,
+      "grad_norm": 0.3269276651095935,
+      "learning_rate": 8.85021121314229e-06,
+      "loss": 0.6032,
+      "step": 274
+    },
+    {
+      "epoch": 1.4409448818897639,
+      "grad_norm": 0.3563617148746268,
+      "learning_rate": 8.697271711548163e-06,
+      "loss": 0.5727,
+      "step": 275
+    },
+    {
+      "epoch": 1.4461942257217848,
+      "grad_norm": 0.3379353625795505,
+      "learning_rate": 8.545297198389896e-06,
+      "loss": 0.572,
+      "step": 276
+    },
+    {
+      "epoch": 1.4514435695538057,
+      "grad_norm": 0.32800047402633126,
+      "learning_rate": 8.394300648733688e-06,
+      "loss": 0.5784,
+      "step": 277
+    },
+    {
+      "epoch": 1.4566929133858268,
+      "grad_norm": 0.353294123585671,
+      "learning_rate": 8.24429495415054e-06,
+      "loss": 0.5948,
+      "step": 278
+    },
+    {
+      "epoch": 1.4619422572178478,
+      "grad_norm": 0.33905615123641586,
+      "learning_rate": 8.095292921615628e-06,
+      "loss": 0.6164,
+      "step": 279
+    },
+    {
+      "epoch": 1.4671916010498687,
+      "grad_norm": 0.34568179548405675,
+      "learning_rate": 7.947307272414874e-06,
+      "loss": 0.587,
+      "step": 280
+    },
+    {
+      "epoch": 1.4724409448818898,
+      "grad_norm": 0.31900836965125545,
+      "learning_rate": 7.800350641058867e-06,
+      "loss": 0.5829,
+      "step": 281
+    },
+    {
+      "epoch": 1.4776902887139107,
+      "grad_norm": 0.33258497484716926,
+      "learning_rate": 7.654435574204145e-06,
+      "loss": 0.5891,
+      "step": 282
+    },
+    {
+      "epoch": 1.4829396325459316,
+      "grad_norm": 0.32711726879832903,
+      "learning_rate": 7.509574529582022e-06,
+      "loss": 0.5915,
+      "step": 283
+    },
+    {
+      "epoch": 1.4881889763779528,
+      "grad_norm": 0.3332370756155197,
+      "learning_rate": 7.365779874934987e-06,
+      "loss": 0.5925,
+      "step": 284
+    },
+    {
+      "epoch": 1.4934383202099737,
+      "grad_norm": 0.3454414557061501,
+      "learning_rate": 7.223063886960779e-06,
+      "loss": 0.5729,
+      "step": 285
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 380,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 95,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.000110270806753e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-285/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c0d2528dcfd8d62d3c517248c2d231cc9ff64ec148911ec3ce58a9d39f7507d
+size 8376